WO2026013473A1

WO2026013473A1 - Fraud check device, system, and fraud check method

Info

Publication number: WO2026013473A1
Application number: PCT/IB2025/056265
Authority: WO
Inventors: Tadaaki Oyama; Masamoto Nakazawa; Ayumu Hashimoto; Ryo Kobayashi
Original assignee: Ricoh Co Ltd
Current assignee: Ricoh Co Ltd
Priority date: 2024-07-08
Filing date: 2025-06-20
Publication date: 2026-01-15
Anticipated expiration: 2027-01-08
Also published as: JP2026009664A

Abstract

A fraud check device includes a light source, a reading unit that reads reflected light from a subject to obtain an invisible light image, a control unit that detects image characteristics from image areas in the invisible light image, and determines that the subject is in a first state based on the image characteristics. The control unit detects, from a first image area of the image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light, and detects, from a second image area of the image areas, an image characteristic of an area of an image formed with at least a material that does not absorb invisible light. The control unit makes the determination based on a first image characteristic of the first image area and a second image characteristic of the second image area.

Description

[DESCRIPTION] [Title of Invention] FRAUD CHECK DEVICE, SYSTEM, AND FRAUD CHECK METHOD [Technical Field]

[0001]

The present disclosure relates to a fraud check device, a system, and a fraud check method. [Background Art] [0002]

A fraud check device has been proposed that determines the authenticity or otherwise of various documents read by a reading device, to thereby detect fraud such as forgery or falsification of the various documents.

Patent Literature (PTL) 1 discloses a technique of determining the authenticity or otherwise of a bank note, a passport, or the like with infrared rays in at least two wavelength bands. [Citation List] [Patent Literature] [0003] [PTL 1]

Japanese Unexamined Patent Application Publication No. 2005-246821 [Summary of Invention] [Technical Problem] [0004]

However, the technique of PTL 1 causes an increase in cost due to the involvement of spectral irradiation of light ranging from visible wavelengths to approximately 3000 nm with at least two infrared bandpass filters, or irradiation with at least two infrared light-emitting diodes (LEDs) with different emission wavelengths or at least two infrared lasers with different oscillation wavelengths.

[0005]

The fraud check device that causes the increase in cost as described above is less suitable to be applied to determine the authenticity or otherwise of a generalized and inexpensive object such as a ticket or coupon, for example, mainly in terms of cost performance. Consequently, there is a risk of overlooking fraud such as forgery of such a generalized and inexpensive object.

[Solution to Problem] [0006]

The present disclosure described herein provides a fraud check device that includes an invisible light source, an image reading unit, and a control unit. The invisible light source irradiates a subject with invisible light. The image reading unit reads reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The control unit detects identical or different image characteristics from a plurality of image areas in the invisible light image. The control unit determines that the subject is in a first state based on the image characteristics that is detected. The control unit detects, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light, and detects, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. The control unit determines that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

The present disclosure described herein further provides a system that includes a fraud check device and a server. The fraud check device includes a light source, an image reading unit, and a control unit. The light source irradiates a subject with invisible light. The image reading unit reads reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The control unit detects identical or different image characteristics from a plurality of image areas in the invisible light image. The server includes a control device that determines that the subject is in a first state based on the image characteristics that is detected by the control unit. The control unit detects, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light, and detects, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. The control device determines that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

The present disclosure described herein further provides a fraud check method performed by a fraud check device. The fraud check method includes irradiating a subject with invisible light, and reading reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The fraud check method further includes detecting identical or different image characteristics from a plurality of image areas in the invisible light image, and determining that the subject is in a first state based on the detected image characteristics. The detecting includes detecting, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light, and detecting, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. The determining includes determining that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

[Advantageous Effects of Invention] [0007] According to one or more aspects of the present disclosure, the authenticity or otherwise of a generalized and inexpensive object is determined accurately with a less expensive structure. [Brief Description of Drawings] [0008]

A more complete appreciation of embodiments of the present disclosure and many of the attendant advantages and features thereof can be readily obtained and understood from the following detailed description with reference to the accompanying drawings.

FIG. 1 is a diagram illustrating a configuration example of an image reading device according to a first embodiment.

FIG. 2 is a diagram illustrating a configuration example of control blocks of the image reading device.

FIG. 3 is a graph illustrating an example of a spectral sensitivity characteristic of an image sensor.

FIG. 4 is a graph illustrating an example of a reflectance spectral characteristic obtained from a white sheet surface with toners of respective colors applied thereto.

FIG. 5 is a diagram illustrating an example of a device configuration to check for fraud.

FIG. 6 is a flowchart illustrating an example of determination of the state of a subject by a state determination unit.

FIG. 7 is a flowchart illustrating another example of the determination of the state of the subject by the state determination unit.

FIG. 8 is a flowchart illustrating yet another example of the determination of the state of the subject by the state determination unit.

FIG. 9 is a diagram illustrating an example of a ticket original.

FIG. 10 is a diagram illustrating an example of an invisible light image obtained by reading the ticket original in FIG. 9 with near-infrared light.

FIG. 11 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original in FIG. 9 with black (K) toner, with near-infrared light.

FIG. 12 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original in FIG. 9 with dye-paint toner, with near-infrared light.

FIG. 13 is a diagram illustrating an example of image areas.

FIG. 14 is a table illustrating a data example of mean values of image characteristics of the invisible light images.

FIG. 15 is a flowchart illustrating an example of the determination of the state of the subject by the state determination unit based on threshold determination.

FIG. 16 is a flowchart illustrating another example of the determination of the state of the subject by the state determination unit based on the threshold determination.

FIG. 17 is a flowchart illustrating yet another example of the determination of the state of the subject by the state determination unit based on the threshold determination. FIG. 18 is a diagram illustrating a modified example of the ticket original.

FIG. 19 is a diagram illustrating an example of an invisible light image obtained by reading the ticket original in FIG. 18 with near-infrared light.

FIG. 20 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original in FIG. 18 with the black (K) toner, with near-infrared light.

FIG. 21 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original in FIG. 18 with the dye-paint toner, with near-infrared light.

FIG. 22 is a diagram illustrating a configuration of a fraud check system.

FIG. 23 is a graph illustrating an example of detection of image characteristics by an image characteristic detection unit according to a second embodiment.

FIG. 24 is a diagram illustrating a configuration example of a fraud check device according to a third embodiment.

FIG. 25 is a diagram illustrating an example of an admission pass according to a fourth embodiment.

FIG. 26 is a diagram illustrating an example of an invisible light image obtained by reading the admission pass in FIG. 25 with near-infrared light.

FIG. 27 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the admission pass in FIG. 25 with the black (K) toner, with near-infrared light.

FIG. 28 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the admission pass in FIG. 25 with the dye-paint toner, with near-infrared light.

The accompanying drawings are intended to depict embodiments of the present disclosure and should not be interpreted to limit the scope thereof. The accompanying drawings are not to be considered as drawn to scale unless explicitly noted. Also, identical or similar reference numerals designate identical or similar components throughout the several views. [Description of Embodiments] [0009]

In describing embodiments illustrated in the drawings, specific terminology is employed for the sake of clarity. However, the disclosure of this specification is not intended to be limited to the specific terminology so selected and it is to be understood that each specific element includes all technical equivalents that have a similar function, operate in a similar manner, and achieve a similar result.

Referring now to the drawings, embodiments of the present disclosure are described below. As used herein, the singular forms “a,” “an,” and “the” are intended to include the plural forms as well, unless the context clearly indicates otherwise.

[0010] With reference to the accompanying drawings, embodiments of a fraud check device, a system, and a fraud check method will be described in detail below. The following description is of an image reading device as an example of the fraud check device and an image forming apparatus as another example of the fraud check device. In the following examples, an image sensor is applied as an image reading unit. However, the image reading unit is not limited to the image sensor, and may have any configuration that converts light into electrical signals. Image information or an image output by the image sensor (also referred to as the read image) is an example of “information (or read information)” output by the image reading unit. Further, the fraud check device is not limited to the image reading device or the image forming apparatus, and may be a dedicated device with a function for checking for fraud. Fraud check may also be performed by a device with another function, as long as the function for checking for fraud is applicable to the device.

[0011]

(First Embodiment)

FIG. 1 is a diagram illustrating a configuration example of an image reading device 1 according to a first embodiment. FIG. 1 illustrates the image reading device 1 as an example of the fraud check device.

[0012]

The image reading device 1 irradiates a reading target such as a type of certificate or a document with light from a light source, and receives reflected light from the reading target with an image sensor to read an image.

[0013]

Specifically, in the example illustrated in FIG. 1, an upper surface of an image reading device body 10 has a contact glass 11. The image reading device body 10 includes therein reading means (first reading means). The image reading device body 10 includes therein a light source 13, a first carriage 14, a second carriage 15, a lens unit 16, a sensor board 17, and so forth as the first reading means. The first carriage 14 includes the light source 13 and a reflecting mirror 14-1. The second carriage 15 includes reflecting mirrors 15-1 and 15-2. The image reading device body 10 further includes a control board (corresponding to a control unit 300 illustrated in FIG. 2) to control the entire device.

[0014]

The control board moves the first carriage 14 and the second carriage 15 and emits the light from the light source 13 to sequentially read beams of the reflected light from the reading target placed on the contact glass 11 with an image sensor 402 (see FIGs. 2 and 5, for example). The light emitted from the light source 13 and reflected by the reading target is reflected by the mirror 14-1 of the first carriage 14 and the mirrors 15-1 and 15-2 of the second carriage 15 and is incident on the lens unit 16. The light output from the lens unit 16 is formed into an image on the image sensor 402 (a first reading unit) disposed on the sensor board 17. The image sensor 402 is a charge coupled device (CCD) or complementary metal- oxide semiconductor (CMOS) image sensor, for example. The image sensor 402 converts the reflected light from the reading target into electrical signals and outputs image information. The light source 13 is not limited to a single light source, and may include a plurality of light sources. Further, the image sensor 402 is not limited to a single image sensor, and may include a plurality of image sensors. Device settings related to the numbers of these components to be combined will be described later as necessary. A reference white plate 12 is a member that is previously read to perform white correction on the read image.

[0015]

The image reading device 1 illustrated in FIG. 1 further includes an automatic document feeder (ADF) 20 to read the reading target with the ADF 20 in accordance with a sheet- through method. In the ADF 20, pickup rollers 22 separate a sheet from a stack of sheets in a tray 21 as the reading target. The ADF 20 then controls components such as various transport rollers 24 to read one side or both sides of the reading target transported on a transport path 23 and eject the reading target onto a sheet ejection tray 25.

[0016]

The reading target is read at a reading window 19. In this example, the first carriage 14 and the second carriage 15 are moved to and fixed at respective particular home positions. When the reading target passes the space between the reading window 19 and a background unit 26, a first side (front side) of the reading target facing the reading window 19 is irradiated with the light from the light source 13 to read an image. The reading window 19 is a slit-like reading window formed in a part of the contact glass 11. The background unit 26 is a background member.

[0017]

To read both sides of the reading target, a reading module 27 provided as second reading means to face a second side (rear side) of the reading target reads the second side after the reading target passes the reading window 19. The reading module 27 includes an irradiation unit including a light source and a contact-type image sensor 402 (see FIGs. 2 and 5, for example) functioning as a second reading unit. The light directed to and reflected by the second surface is read by the contact-type image sensor 402. This light source is also not limited to a single light source, and may include a plurality of light sources. Further, the image sensor 402 is not limited to a single image sensor, and may include a plurality of image sensors. A background member 28 is formed with a density reference member.

[0018]

When reading the reading target, each of the first reading means and the second reading means performs shading correction with shading data generated based on the density reference member. The shading correction corrects, for example, variations in accuracy between pixels of the reading unit.

[0019]

A configuration of control blocks of the image reading device 1 will be described.

[0020] FIG. 2 is a diagram illustrating a configuration example of the control blocks of the image reading device 1. As illustrated in FIG. 2, the image reading device 1 includes a control unit 300, an operation panel 301, various sensors 302, a scanner motor 303, various motors 304, an image output unit 305, and reading means 400. Various other control targets are also connected to the control blocks. The various sensors 302 are sensors that detect the reading target. The scanner motor 303 is a motor that drives the first carriage 14 and the second carriage 15 in the image reading device body 10. The various motors 304 are various motors provided in the ADF 20. [0021]

The operation panel 301 is a liquid crystal display device with a touch panel, for example.

The operation panel 301 receives an input operation from a user to perform various settings or execute reading (execute scanning) via an operation button or touch input, for example, and transmits corresponding operation signals to the control unit 300.

[0022]

The operation panel 301 further displays various display information from the control unit 300 on a display screen. For example, the operation panel 301 includes an execution button for the user to execute fraud check on various certificates or documents to check whether there is fraud such as forgery or falsification in the certificates or documents. In response to an input operation via the execution button, the operation panel 301 transmits an instruction to the control unit 300 to execute a fraud check process.

[0023]

Whether or not to execute the fraud check may be selected on a setting screen in the display screen of the operation panel 301. Further, the fraud check process may be set to execute each time a scan execution button is operated.

[0024]

The control unit 300 visually outputs a result of executing the fraud check process. For example, the control unit 300 displays a fraud check process execution screen (check screen) on the display screen of the operation panel 301. The control unit 300 may further store the data of the check screen in an externally attached memory or output the data of the check screen to an external printer to print out the data.

[0025]

FIG. 2 illustrates an example of functional blocks of the reading means 400 for reading an image. The first reading means and the second reading means are not limited to this example. The reading means 400 includes a light source 401, sensor chips 402a, amplifiers 403, analog- to-digital (A/D) converters 404, an image processing unit 405, a frame memory 406, an output control circuit 407, and an interface (I/F) circuit 408.

[0026]

Image data (read image) is output frame by frame to the control unit 300 from the output control circuit 407 via the I/F circuit 408.

[0027] The sensor chips 402a, the amplifiers 403, the A/D converters 404, the image processing unit 405, the frame memory 406, the output control circuit 407, and the I/F circuit 408 are disposed on the sensor board 17 (see FIG. 1). Each of the sensor chips 402a is a pixel sensor disposed on the image sensor 402, which is an image reading unit.

[0028]

The reading means 400 is driven by a controller 307 based on a reading control signal (e.g., a timing signal) output from the control unit 300. For example, the reading means 400 turns on the light source 401 based on a turn-on signal from the controller 307 to irradiate the reading target with light. The reading means 400 further converts the light from the reading target, which is formed into an image on a sensor surface of the image sensor 402, into electrical signals with the sensor chips 402a and outputs the electrical signals.

[0029]

In the reading means 400, the amplifiers 403 amplify the electrical signals (pixel signals) output from the sensor chips 402a, and the A/D converters 404 convert the electrical signals from analog signals to digital signals to output level signals of the pixels. The image processing unit 405 performs image processing on the output signals from the pixels. For example, the image processing unit 405 performs shading correction on the output signals from the pixels.

[0030]

After the image processing, the data is accumulated in the frame memory 406, and the read image is transferred to the control unit 300 via the output control circuit 407 and the I/F circuit 408.

[0031]

The control unit 300, which includes a central processing unit (CPU) and a memory, controls the entire device to execute the operation of reading the reading target or the fraud check process, for example. A processing unit that performs the fraud check may be implemented by a functional unit that is embodied by a particular program executed by the CPU, or may be implemented by hardware such as an application specific integrated circuit (ASIC). Further, the functionality of the processing unit may be divided and allocated to the functional unit and the hardware.

[0032]

The program executed on the image reading device 1 may be provided as recorded on a computer readable recording medium such as a compact disc read only memory (CD-ROM), a flexible disc (FD), a CD-recordable (CD-R), or a digital versatile disc (DVD) in a file of an installable or executable format.

[0033]

Further, the program executed on the image reading device 1 may be stored in a computer connected to a network such as the Internet and be provided as downloaded via the network. The program executed on the image reading device 1 may also be provided or distributed via a network such as the Internet. [0034]

In response to receipt of an operation to execute scanning, to which the fraud check is applied, the control unit 300 causes, for example, the reading means 400, which performs the fraud check process in the scanning, to perform a reading operation on the reading target with a combination of a particular light source and a particular image sensor 402. [0035]

The control unit 300 further executes the fraud check process one or more times on the read image transferred from the reading means 400, and visually outputs the result of the fraud check process. For example, the control unit 300 displays the fraud check process execution screen (check screen) on the display screen of the operation panel 301. The control unit 300 may further store the data of the check screen in an externally attached memory or output the data of the check screen to an external printer to print out the data. [0036]

The image output unit 305 receives from the control unit 300 the read image transferred from the reading means 400 (e.g., a visible light image of the subject, which is described below) and outputs the read image to an external device. [0037]

The fraud check will be described in detail.

[0038]

In the following description, a “visible light image” refers to information perceivable by the human eye under natural light or an image detectable by a sensing device such as the image sensor 402, which has sensitivity to visible light (light in the visible wavelength range). Further, an “invisible light image” refers to an image unperceivable by the human eye under natural light or an image undetectable by a sensing device that senses visible light, e.g., an image detectable by a sensing device such as the image sensor 402, which has sensitivity to light in the invisible wavelength range such as infrared light (including near-infrared light) and ultraviolet light. In the device configuration described below, information previously printed on a print side of the subject for fraud check and the settings such as the numbers and wavelength ranges of the light sources and the image sensors 402 used in the reading means are also included in the configuration of the fraud check device in a broad sense. [0039]

FIG. 3 is a graph illustrating an example of a spectral sensitivity characteristic of the image sensor 402. FIG. 4 is a graph illustrating an example of a reflectance spectral characteristic obtained from a white sheet surface with toners of respective colors (cyan (C) toner, magenta (M) toner, yellow (Y) toner, black (K) toner, and black (C+M+Y) toner) applied thereto. [0040]

As illustrated in FIG. 3, typical silicon forming the pixels of the image sensor 402 has sensitivity to light in the visible wavelength range (wavelengths of approximately 380 nm to approximately 780 nm) and also to light in the near- infrared wavelength range (the invisible region with wavelengths of approximately 780 nm and higher). That is, light in the near- infrared wavelength range is unperceivable by the human eye. However, near-infrared light is detectable by the image sensor 402, which has sensitivity to light in the near-infrared wavelength range. Therefore, an image is formed by irradiation with near-infrared light. [0041]

As illustrated in FIG. 4, the toners of the respective colors (the C toner, the M toner, the Y toner, and the black (K) toner) exhibit different characteristics in the visible wavelength range (wavelengths of approximately 400 nm to approximately 750 nm), and thus are visually perceived as different colors. Further, as illustrated in FIG. 4, the black (C+M+Y) toner combining the C toner, the M toner, and the Y toner exhibits the characteristic of black with low reflectance in the visible wavelength range, and exhibits the characteristic of white with high reflectance in the near-infrared range (wavelengths of 750 nm and higher). The black (K) toner, on the other hand, exhibits the characteristic of black with low reflectance over the entire wavelength range.

[0042]

That is, in the near-infrared wavelength range, the black (K) toner is read as black text or image, and the black (C+M+Y) toner is read as white, even though the black (K) toner and the black (C+M+Y) toner are both visually perceived as the same “black” color. This indicates that the black (K) toner and the black (C+M+Y) toner are distinguished from each other with near-infrared light. Based on this feature, the black (K) toner and the black (C+M+Y) toner are identified with near-infrared light, even though the black (K) toner and the black (C+M+Y) toner are both visually perceived as the same black color.

[0043]

As described above, using near-infrared light as the light for reading the invisible light image enables checking a document such as a ticket formed with general-purpose toner with the general-purpose image sensor 402.

[0044]

Carbon is a material having a reflectance characteristic similar to that of the black (K) toner in FIG. 4 and used in toner or ink. It is therefore effective to set an area containing or not containing carbon as a target area from which the characteristic is to be extracted.

[0045]

In the present embodiment, the color visually perceived as black is described as an example of the color distinguishable with near-infrared light. However, the color distinguishable with near-infrared light is not limited to black. For example, gray as an intermediate color or a color including the black (K) toner such as red, green, or blue with a certain level of density (darkness) is similarly distinguishable with near-infrared light.

[0046]

FIG. 5 is a diagram illustrating an example of a device configuration to check for fraud. [0047]

The reading means 400 in FIG. 5 includes the light source 401 and the image sensor 402. The reading means 400 also includes other components such as those in the reading means 400 illustrated in FIG. 2. The light source 401 illustrated in FIG. 5 uses a light source of light including at least an invisible wavelength component, and the image sensor 402 illustrated in FIG. 5 uses an image sensor with sensitivity to the light in the invisible wavelength range from the light source 401. For example, the reading means 400 uses the light source 401 of light including a near-infrared wavelength range component and a visible wavelength range component, and uses the image sensor 402 with sensitivity to light in a wavelength range covering the near-infrared wavelength range component and the visible wavelength range component.

[0048]

As illustrated in the example of the present embodiment, an image containing the black (K) toner and an image not containing the black (K) toner are distinguishable based on an invisible light image obtained with invisible light in a wavelength band; it is unnecessary to receive at least multiple types of reflected light. That is, a light emitting unit of the reading means 400 does not need to use and switch between multiple types of invisible light sources, and a light receiving unit of the reading means 400 does not need to use and switch between multiple types of spectral filters or photoreceivers. Consequently, accurate authenticity determination is performed with a less expensive structure.

[0049]

As illustrated in FIG. 5, the fraud check device includes an image characteristic detection unit 500, a state determination unit 600, and a state determination information notification unit 700, which is a notification unit. As described above, in one example, the image characteristic detection unit 500, the state determination unit 600, and the state determination information notification unit 700 are each implemented by the control unit 300 that executes the program.

[0050]

The image characteristic detection unit 500, which includes a plurality of characteristic detection units 501 (501a and 501b), detects identical or different image characteristics from a plurality of image areas in an invisible light image.

[0051]

The state determination unit 600, which includes a plurality of threshold determination units 601, determines the state of the subject based on the image characteristics detected by the characteristic detection units 501.

[0052]

For example, the state determination unit 600 determines the state of the subject as an authentic state with no fraud such as forgery or falsification of the subject (a first state), a fraudulent state with fraud such as forgery or falsification of the subject (a second state), or a state unidentifiable as the authentic state (the first state) or the fraudulent state (the second state) due to a factor such as a stain or a scratch (a third state).

[0053] The state determination unit 600 further determines the state of the subject as a state at least not confirmed as authentic for a reason such as the difficulty to distinguish between possible fraud and the influence of a factor such as a stain or a scratch (a state other than the first state) or a state at least not confirmed as fraudulent from the detection result for a reason such as that conditions for being an authentic item are met but a stain or scratch is too severe to distinguish therefrom possible fraud (a state other than the second state).

[0054]

FIG. 6 is a flowchart illustrating an example of determination of the state of the subject by the state determination unit 600.

[0055]

As illustrated in FIG. 6, the state determination unit 600 first determines whether the subject is authentic based on determination results obtained by the threshold determination units 601, which are based on the image characteristics detected by the characteristic detection units 501 (step SI). If the determination results obtained by the threshold determination units 601 meet the conditions for being authentic (YES at step SI), the state determination unit 600 determines that the subject is the authentic item (the first state) (step S2).

[0056]

If the determination results obtained by the threshold determination units 601 do not meet the conditions for being authentic (NO at step SI), the state determination unit 600 determines whether the subject is a fraudulent item (step S3). If the determination results obtained by the threshold determination units 601 meet conditions for being a fraudulent item (YES at step S3), the state determination unit 600 determines that the subject is a fraudulent item (the second state) (step S4). If the determination results obtained by the threshold determination units 601 do not meet the conditions for being a fraudulent item (NO at step S3), the state determination unit 600 determines that the subject is in the unidentifiable state (the third state) (step S5).

[0057]

FIG. 7 is a flowchart illustrating another example of the determination of the state of the subject by the state determination unit 600.

[0058]

For example, as illustrated in FIG. 7, the state determination unit 600 first determines whether the subject is authentic based on the determination results obtained by the threshold determination units 601, which are based on the image characteristics detected by the characteristic detection units 501 (step Si l).

[0059]

If the determination results obtained by the threshold determination units 601 meet the conditions for being authentic (YES at step Si l), the state determination unit 600 determines that the subject is the authentic item (the first state) (step S12).

[0060] If the determination results obtained by the threshold determination units 601 do not meet the conditions for being authentic (NO at step Si l), the state determination unit 600 determines that the subject is not the authentic item (the first state) (step S13).

[0061]

There are numerous means and types of fraud on commonly distributed objects such as tickets. There are also numerous patterns and types of stains and scratches. It is therefore difficult to recognize and accurately identify characteristics of all of the means and types of fraud and the patterns and types of stains and scratches. Accordingly, it is effective to avoid distinctly distinguishing between possible fraud and a stain or scratch to reduce the risk of erroneously reporting the second state as the third state or vice versa.

[0062]

FIG. 8 is a flowchart illustrating yet another example of the determination of the state of the subject by the state determination unit 600.

[0063]

For example, as illustrated in FIG. 8, the state determination unit 600 first determines whether the subject is a fraudulent item based on the determination results obtained by the threshold determination units 601, which are based on the image characteristics detected by the characteristic detection units 501 (step S21).

[0064]

If the determination results obtained by the threshold determination units 601 meet the conditions for being a fraudulent item (YES at step S21), the state determination unit 600 determines that the subject is a fraudulent item (the second state) (step S22).

[0065]

If the determination results obtained by the threshold determination units 601 do not meet the conditions for being a fraudulent item (NO at step S21), the state determination unit 600 determines that the subject is not a fraudulent item (the second state) (step S23).

[0066]

For example, in the case of an admission pass, the issuance or management of which is normally limited to a particular area, means of fraud are limited to revision, falsification, and the like. In some cases, therefore, it suffices if fraud is detectable and if no fraud is detected. Such fraud check is effective in an environment such as a particular factory where there is a concern that the admission pass may be easily stained or scratched.

[0067]

Referring back to FIG. 5, the state determination information notification unit 700 visually outputs the state determined by the state determination unit 600 to the display screen of the operation panel 301. Alternatively, the state determination information notification unit 700 visually outputs the processing result as print information to be printed with an external printer.

[0068] That is, the state determination information notification unit 700 notifies an external device or the user of the information of the state determined by the state determination unit 600 (the first state, the second state, the third state, a state other than the first state, or a state other than the second state). The state determination information notification unit 700 may perform the notification by using a display device such as the operation panel 301 or a display, printing out on a sheet, changing the color or brightness of a display lamp, or outputting sound such as alarm sound, for example. Each of these methods visually or auditorily conveys authenticity determination information to the user, further improving convenience.

[0069]

An example of application to authenticity determination using the difference in image characteristics will be described with an example of an original and a copy of a ticket, which is a generalized and inexpensive object.

[0070]

FIG. 9 is a diagram illustrating an example of a ticket original Tl. The example illustrated in FIG. 9 is an example of a ticket with a design of a pictorial pattern.

[0071]

As illustrated in FIG. 9, text descriptions on the ticket original Tl are for displaying or checking detailed information such as the information of the item and the expiration date. It is therefore desirable that the text information is visually clearly recognizable and well resistant to abrasion and heat. Accordingly, the text information is printed with a carbon (pigment)-based material. Carbon is common and widely used as black ink or toner, and a dedicated or special system is not required to print a common ticket with carbon. Further, carbon has a characteristic of absorbing light in a wide wavelength range including ultraviolet light and infrared light as well as visible light, and thus is read as black by a reading device that covers the entire wavelength range.

[0072]

The image of text on the ticket original Tl illustrated in FIG. 9 is formed with the black (K) toner containing carbon.

[0073]

As illustrated in FIG. 9, the image of a design (pictorial pattern) of a coffee cup on the ticket original Tl, on the other hand, is formed with more refined and vivid dye paint for purposes such as supplementing the text information about the effectiveness or validity of the ticket and encouraging a user to use the ticket. The dye paint is, for example, cyan, magenta, yellow, red, green, or blue ink or toner or black ink or toner not containing carbon. Such dye paint is also widely and commonly used. Including a high-density color close to black in the design (pictorial pattern) of the coffee cup further enhances the security level. For example, the color arrangement and shadow with the high-density color as illustrated in FIG. 9 are natural and effective.

[0074] The image of the pictorial pattern area in the ticket original T1 illustrated in FIG. 9 is formed with dye toner not containing carbon (the C toner, the M toner, and the Y toner).

[0075]

The fraud check device of the present embodiment uses near-infrared light, for example, as the invisible light to read the subject such as the ticket original T1 illustrated in FIG. 9.

[0076]

FIG. 10 is a diagram illustrating an example of an invisible light image obtained by reading the ticket original T1 in FIG. 9 with near-infrared light.

[0077]

As described above, in the ticket original T1 illustrated in FIG. 9, the image of the text area (a first image area) is formed with at least the black toner as a material that contains carbon, and the image of the pictorial pattern area (a second image area) is formed with at least the noncarbon dye toner as a material that does not contain carbon. The black toner as the material that contains carbon is a material that at least absorbs invisible light. The non-carbon dye toner as the material that does not contain carbon is a material that at least does not absorb invisible light. In the invisible light image obtained by reading the ticket original T1 with near-infrared light, therefore, the text is all read as black, and the pictorial pattern area is read as white, which is a color substantially equal to the color of a bare surface of the sheet.

[0078]

Reading a ticket copy, which is obtained by copying the ticket original T1 in FIG. 9, with near-infrared light will be described.

[0079]

FIG. 11 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original T1 in FIG. 9 with the black (K) toner, with near-infrared light. The black (K) toner is toner containing carbon, as described above. [0080]

In the invisible light image in FIG. 11 obtained by reading the ticket copy with near- infrared light, black areas are all formed with black toner having the spectral characteristic of the black (K) toner in FIG. 4. Therefore, an image appears in the pictorial pattern area unlike in the example of the invisible light image obtained by reading the ticket original T1 in FIG. 9 with near-infrared light. That is, this example indicates that whether the ticket as the subject is the original or a copy is determined by detecting whether the picture level of the pictorial pattern area is the white level.

[0081]

FIG. 12, on the other hand, is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original T1 in FIG. 9 with the dye-paint toner, with near-infrared light. The dye-paint is, for example, cyan, magenta, or yellow toner or black toner not containing carbon.

[0082] In the invisible light image in FIG. 12 obtained by reading the ticket copy with near- infrared light, the black areas are all formed with black toner having the spectral characteristic of the black (C+M+Y) toner in FIG. 4. Therefore, the text area and the pictorial pattern area of the ticket original T1 both disappear unlike in the example of the invisible light image in FIG. 10 obtained by reading the ticket original T1 with near- infrared light. That is, this example indicates that whether the ticket as the subject is the original or a copy is determined by detecting whether the picture level of the text area includes the black level.

[0083]

The threshold determination units 601 of the state determination unit 600 will be described in detail.

[0084]

As described above, the image as illustrated in FIG. 10 is obtained as the invisible light image by reading the ticket original T1 (the authentic item). The image of the text is formed with the black (K) toner containing carbon, and the image of the pictorial pattern area is formed with the dye toner not containing carbon. Therefore, the text is read as black, and the pictorial pattern area is read as white, which is a color substantially equal to the color of the bare surface of the sheet.

[0085]

FIG. 13 is a diagram illustrating an example of image areas. As illustrated in FIG. 13, for example, the image characteristic detection unit 500 previously specifies an area including text as the first image area for the detection by the characteristic detection unit 501a. The image characteristic detection unit 500 also previously specifies an area including a pictorial pattern as the second image area for the detection by the characteristic detection unit 501b. [0086]

That is, the image characteristic detection unit 500 performs the detection in the first image area as an area of an image including text information, and performs the detection in the second image area as an area of an image other than the image including the text information (e.g., the pictorial pattern area).

[0087]

In other words, the image characteristic detection unit 500 performs the detection in the first image area as an area including an image formed with at least a material that contains carbon, and performs the detection in the second image area as an area including an image formed with at least a material that does not contain carbon.

[0088]

It suffices if respective characteristics of the first image area and the second image area in the invisible light image are detected. Therefore, the image characteristic detection unit 500 may perform the detection in areas including a background area and a bare sheet surface area, as illustrated in FIG. 13. The image characteristic detection unit 500 may of course specify the area including text and the area including a pictorial pattern and perform the detection specifically in the areas. [0089]

The image characteristic detection unit 500 detects an image characteristic Cl and an image characteristic C2 from these image areas with the characteristic detection unit 501a and the characteristic detection unit 501b, respectively, and transmits the detected image characteristics Cl and C2 to a subsequent unit, i.e., the state determination unit 600. [0090]

As described above, the image characteristic detection unit 500 performs the detection in the plurality of image areas, from which the characteristics are to be extracted, and which include at least an area where information visually recognizable under visible light is clearly presented.

[0091]

In general, in an object such as a ticket, the text area and the pictorial pattern area are different depending on the type of the object. That is, the area containing the black toner (carbon) and absorbing invisible light and the area not containing the black toner (carbon) and not absorbing invisible light are visually recognizable.

[0092]

As illustrated in FIG. 13, the plurality of image areas, from which the image characteristics are to be extracted, are made visually recognizable, which allows the user to specify the area to check, thereby further improving convenience, versatility, and accuracy.

[0093]

Each of the threshold determination units 601 determines whether the image characteristic detected by the corresponding characteristic detection unit 501 is equal to or greater than a threshold value or is equal to or less than a threshold value. More specifically, the threshold determination unit 601 determines whether the image characteristic Cl as a first image characteristic is equal to or less than a first threshold value, or determines whether the image characteristic C2 as a second image characteristic is equal to or greater than a second threshold value. For example, with the image characteristic Cl, the state determination unit 600 determines whether the black text is present. Further, with the image characteristic C2, the state determination unit 600 determines whether the pictorial pattern has disappeared. Then, if the black text is present, and if the pictorial pattern has disappeared, the state determination unit 600 determines that the ticket is the authentic item (the first state). If otherwise, the state determination unit 600 processes the ticket by determining that the ticket is not the authentic item (the first state) (e.g., a forgery or copy).

[0094]

That is, based on the image of FIG. 10, the state determination unit 600 determines that the subject is the authentic item (the first state) or performs state determination for the user of the fraud check device of the present embodiment to determine that the subject is the authentic item (the first state).

[0095] If the invisible light image as illustrated in FIG. 11 is obtained, for example, the characteristic detection unit 501a detects the image characteristic Cl of the text area of the ticket, and the characteristic detection unit 501b detects the image characteristic C2 of the pictorial pattern area of the ticket. Since the image characteristic C2 indicates the presence of a black pictorial pattern, the state determination unit 600 determines that the subject is a fraudulent item (the second state) or that the subject is not the authentic item (the first state).

[0096]

Further, if the invisible light image as illustrated in FIG. 12 is obtained, for example, the characteristic detection unit 501a detects the image characteristic Cl of the text area of the ticket, and the characteristic detection unit 501b detects the image characteristic C2 of the pictorial pattern area of the ticket. The characteristic detection units 501a and 501b then transmit the detected image characteristics 1 and 2 to the state determination unit 600. Since the image characteristic Cl does not indicate the presence of black text, the state determination unit 600 determines that the subject is a fraudulent item (the second state) or that the subject is not the authentic item (the first state).

[0097]

That is, based on the image in FIG. 11 or 12, the fraud check device of the present embodiment determines that the subject is a fraudulent item (the second state) or that the subject is not the authentic item (the first state). Alternatively, the fraud check device of the present embodiment performs state determination for the user of the fraud check device of the present embodiment to determine that the subject is a fraudulent item (the second state) or that the subject is not the authentic item (the first state).

[0098]

In an example described below, the image characteristic detection unit 500 calculates the mean values of the image characteristics of the invisible light images, and the threshold determination units 601 set threshold values for the mean values. Herein, the target image is an 8-bit image ranging from 0 digit (black) to 255 digits (white).

[0099]

FIG. 14 is a table illustrating a data example of mean values of the image characteristics of the invisible light images. “BLACK TEXT” in FIG. 14 indicates the mean values in the image of text “COFFEE” in FIG. 9 obtained at the same position in the respective invisible light images of FIGs. 10 to 12. “PICTORIAL PATTERN” in FIG. 14 indicates the mean values in the image of a central portion of the coffee cup in FIG. 9 obtained at the same position in the respective invisible light images of FIGs. 10 to 12.

[0100]

In the invisible light image obtained from the authentic item (FIG. 10), the text remains in black, and the pictorial pattern has disappeared. Therefore, the characteristic detection units 501 calculate 10 digits and 200 digits as the mean value (the image characteristic) of the image data of the text and the mean value (the image characteristic) of the image data of the pictorial pattern, respectively. [0101]

In the invisible light image obtained from the copy (FIG. 11), on the other hand, the text and the pictorial pattern both remain in black. Therefore, the characteristic detection units 501 calculate lower values as the mean value (the image characteristic) of the image data of the text and the mean value (the image characteristic) of the image data of the pictorial pattern. In the invisible light image obtained from the copy (FIG. 12), the text and the pictorial pattern both have disappeared. Therefore, the characteristic detection units 501 calculate higher values as the mean value (the image characteristic) of the image data of the text and the mean value (the image characteristic) of the image data of the pictorial pattern.

[0102]

FIG. 15 is a flowchart illustrating an example of the determination of the state of the subject by the state determination unit 600 based on threshold determination. For example, the threshold determination units 601 set 20 digits as the threshold value for the black text area, and set 100 digits as the threshold value for the pictorial pattern area, as illustrated in FIG. 15. [0103]

As illustrated in FIG. 15, based on the image characteristics detected by the characteristic detection units 501, the threshold determination units 601 of the state determination unit 600 determine whether the value of the black text area is equal to or less than the threshold value (20 digits) and whether the value of the pictorial pattern area is equal to or greater than the threshold value (100 digits) (step S31).

[0104]

If it is determined that the value of the black text area is equal to or less than the threshold value (20 digits) and that the value of the pictorial pattern area is equal to or greater than the threshold value (100 digits) (YES at step S31), the threshold determination units 601 determine that the subject is the authentic item (the first state) (step S32).

[0105]

If it is not determined that the value of the black text area is equal to or less than the threshold value (20 digits) and that the value of the pictorial pattern area is equal to or greater than the threshold value (100 digits) (NO at step S31), the threshold determination units 601 compare the value of the black text area with 15 digits, which is another threshold value for the black text area. The threshold determination units 601 further compare the value of the pictorial pattern area with 150 digits, which is another threshold value for the pictorial pattern area. Then, if the data meets either one of the conditions, the threshold determination units 601 determine that the subject is a fraudulent item. That is, based on the image characteristics detected by the characteristic detection units 501, the threshold determination units 601 determine whether the value of the black text area is equal to or less than the threshold value (15 digits) or whether the value of the pictorial pattern area is equal to or greater than the threshold value (150 digits) (step S33).

[0106] If it is determined that the value of the black text area is equal to or less than the threshold value (15 digits) or that the value of the pictorial pattern area is equal to or greater than the threshold value (150 digits) (YES at step S33), the threshold determination units 601 determine that the subject is a fraudulent item (the second state) (step S34).

[0107]

Further, if it is not determined that the value of the black text area is equal to or less than the threshold value (15 digits) or that the value of the pictorial pattern area is equal to or greater than the threshold value (150 digits) (NO at step S33), i.e., if the data does not meet either one of the conditions, the threshold determination units 601 determine that the subject is in the unidentifiable state (the third state) (step S35).

[0108]

In the case of data shift due to a factor such as a stain, an intermediate value may be obtained instead of extreme data indicating white or black. As an example of a mechanism for detecting such data shift, if the obtained value slightly exceeds or falls below the threshold value, the threshold determination units 601 determine that an unintentional factor such as the above-described one has occurred.

[0109]

FIG. 16 is a flowchart illustrating another example of the determination of the state of the subject by the state determination unit 600 based on the threshold determination.

[0110]

As illustrated in FIG. 16, based on the image characteristics detected by the characteristic detection units 501, the threshold determination units 601 of the state determination unit 600 determine whether the value of the black text area is equal to or less than the threshold value (20 digits) and whether the value of the pictorial pattern area is equal to or greater than the threshold value (100 digits) (step S41).

[0111]

If it is determined that the value of the black text area is equal to or less than the threshold value (20 digits) and that the value of the pictorial pattern area is equal to or greater than the threshold value (100 digits) (YES at step S41), the threshold determination units 601 determine that the subject is the authentic item (the first state) (step S42).

[0112]

If it is not determined that the value of the black text area is equal to or less than the threshold value (20 digits) and that the value of the pattern area is equal to or greater than the threshold value (100 digits) (NO at step S41), the threshold determination units 601 determine that the subject is not the authentic item (the first state) (step S43).

[0113]

FIG. 17 is a flowchart illustrating yet another example of the determination of the state of the subject by the state determination unit 600 based on the threshold determination.

[0114] As illustrated in FIG. 17, based on the image characteristics detected by the characteristic detection units 501, the threshold determination units 601 of the state determination unit 600 determine whether the value of the black text area is equal to or greater than the threshold value (20 digits) and whether the value of the pictorial pattern area is equal to or less than the threshold value (100 digits) (step S51).

[0115]

If it is determined that the value of the black text area is equal to or greater than the threshold value (20 digits) and that the value of the pictorial pattern area is equal to or less than the threshold value (100 digits) (YES at step S51), the threshold determination units 601 determine that the subject is a fraudulent item (the second state) (step S52).

[0116]

If it is not determined that the value of the black text area is equal to or greater than the threshold value (20 digits) and that the value of the pictorial pattern area is equal to or less than the threshold value (100 digits) (NO at step S51), the threshold determination units 601 determine that the subject is not a fraudulent item (the second state) (step S53).

[0117]

As described above, with the fraud check device of the present embodiment, whether the picture level of the pictorial pattern area is the white level and whether the picture level of the text area includes the black level are both detected, enabling accurately determining whether the target ticket is the authentic item, a fraudulent item, or unidentifiable. Further, the ticket does not require special ink or toner, and it is unnecessary to extract dedicated or special embedded information such as encoded information from the ticket. Consequently, the present embodiment enables both the party that issues (prints) the ticket and the party that receives (reads) the ticket to determine the authenticity or otherwise of the ticket with an inexpensive structure.

[0118]

In the present embodiment, the position to be checked in the image such as the position of the text area or the pictorial pattern area should be previously specified. The position should be specified before the fraud check device provides a determination, being specified as a prefixed setting, automatically decided or determined based on the read image, selected by the user from multiple prepared options, or specified by the user at prompt, for example. Therefore, the specification of the position is not limited to any particular means.

[0119]

As described above, according to the present embodiment, with the detection of the image characteristics from the plurality of image areas in the invisible light image and the state determination using the information of the characteristics, the authenticity or otherwise of a generalized and inexpensive object is accurately determined with a less expensive structure. The present embodiment therefore provides a fraud check device that detects various states other than the state of the authentic item. Whether the subject is authentic is determined based on at least one image obtained through at least one execution of subject reading control. [0120]

As illustrated in FIG. 5, the light source 401 may include a single light source or a plurality of light sources, and the image sensor 402 may include a single image sensor or a plurality of image sensors. Further, the configuration example described above includes the N characteristic detection units 501. However, the characteristic detection units 501 are not limited to this configuration, and may be formed as a single block and divided to or switch between a plurality of image areas to detect the image characteristics. Further, identical or different methods may be used to detect characteristic values or data of the image characteristics Cl, C2, . . and CN.

[0121]

Modified Example

A modified example of the ticket original will now be described.

[0122]

FIG. 18 is a diagram illustrating a ticket original T2 as a modified example. The ticket original T2 illustrated in FIG. 18 is a ticket with a color pattern or ground pattern without a pictorial pattern. In the ticket original T2 illustrated in FIG. 18, the image of text is formed with the black toner containing carbon, and the image of a background area is formed with the dye toner not containing carbon. In the ticket original T2 illustrated in FIG. 18, the image characteristic detection unit 500 sets an area with text as the first image area, and sets a background area without text (a background area with the color pattern or ground pattern) as the second image area.

[0123]

FIG. 19 is a diagram illustrating an example of an invisible light image obtained by reading the ticket original T2 in FIG. 18 with near-infrared light. In the ticket original T2 illustrated in FIG. 18, the image of the text is formed with the black toner containing carbon, and the image of the background area is formed with the dye toner not containing carbon. In the invisible light image obtained by reading the ticket original T2 with near-infrared light, therefore, the text is all read as black, and the background area is read as white, which is a color substantially equal to the color of the bare surface of the sheet.

[0124]

FIG. 20 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original T2 in FIG. 18 with the black (K) toner, with near-infrared light. The black (K) toner contains carbon, as described above.

[0125]

In the invisible light image in FIG. 20 obtained by reading the ticket copy with near-infrared light, black areas are all formed with black toner having the spectral characteristic of the black (K) toner in FIG. 4. Therefore, an image appears in the background area unlike in the example of the invisible light image obtained by reading the ticket original T2 in FIG. 18 with near-infrared light. That is, this example indicates that whether the ticket as the subject is the original or a copy is determined by detecting whether the picture level of the background area other than the text area is the white level.

[0126]

FIG. 21, on the other hand, is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the ticket original T2 in FIG. 18 with the dye-paint toner, with near-infrared light.

[0127]

In the invisible light image in FIG. 21 obtained by reading the ticket copy with near- infrared light, the black areas are all formed with black toner having the spectral characteristic of the black (C+M+Y) toner in FIG. 4. Therefore, the text area and the background area of the ticket original T2 both disappear unlike in the example of the invisible light image obtained by reading the ticket original T2 in FIG. 18 with near-infrared light. That is, this example indicates that whether the ticket as the subject is the original or a copy is determined by detecting whether the picture level of each of the text area and the background area other than the text area includes the black level.

[0128]

In the present embodiment, the state determination unit 600 is included in the fraud check device. However, the configuration is not limited thereto. The state determination unit 600 may be included in a server of a fraud check system that includes the server and a fraud check device.

[0129]

FIG. 22 is a diagram illustrating a configuration of the fraud check system. As illustrated in FIG. 22, the fraud check system is a system in which the image reading device 1 as an example of the fraud check device and a server S are connected to each other via a network N. The network N is the Internet or a local area network (LAN), for example.

[0130]

The server S includes a control device such as a central processing unit (CPU), storage devices such as a read only memory (ROM) and a random access memory (RAM), external storage devices such as a hard disk drive (HDD) and a digital versatile disc (DVD) drive, a display device such as a display, and input devices such as a keyboard and a mouse. The server S has a hardware configuration using a typical computer.

[0131]

As illustrated in FIG. 22, the image reading device 1 as an example of the fraud check device includes the image characteristic detection unit 500 and the state determination information notification unit 700, and the server S includes the state determination unit 600. In the server S, the CPU reads and executes a program from the ROM or the HDD. Thereby, the state determination unit 600 is loaded onto and generated in the RAM.

[0132]

The state determination unit 600 of the server S includes the plurality of threshold determination units 601 to receive, via the network N, the image characteristics detected by the characteristic detection units 501 of the image reading device 1. The state determination unit 600 of the server S determines the state of the subject based on the image characteristics detected by the characteristic detection units 501 of the image reading device 1.

[0133]

The state determination information notification unit 700 of the image reading device 1 receives, via the network N, the state determined by the state determination unit 600 of the server S. The state determination information notification unit 700 of the image reading device 1 visually outputs the state determined by the state determination unit 600 of the server S to the display screen of the operation panel 301. Alternatively, the state determination information notification unit 700 of the image reading device 1 visually outputs the processing result as print information to be printed with an external printer.

[0134]

(Second Embodiment)

A second embodiment will be described.

[0135]

The second embodiment is different from the first embodiment in using one of the mean value, the standard deviation value, the median value, and the mode value of each of the image characteristics of the invisible light image in the operation method for the characteristic detection units 501 to calculate the image characteristics, while the first embodiment uses the mean value, which is simple to calculate. In the following description of the second embodiment, differences from the first embodiment will be described, with the description of the same components as those of the first embodiment being omitted.

[0136]

FIG. 23 is a graph illustrating an example of detection of the image characteristics by the characteristic detection units 501 according to the second embodiment. FIG. 23 illustrates histograms of an invisible light image obtained by reading the ticket original (the authentic item). The horizontal axis of the histograms represents the image data level (digits), and the vertical axis of the histograms represents the frequency (count).

[0137]

In the first embodiment, a description has been given of an example in which the detection of the image characteristics by the characteristic detection units 501 uses the mean value of each of the image characteristics of the invisible light image, which is simple to calculate. However, the value used in the detection of the image characteristics by the characteristic detection units 501 is not limited thereto. For example, if the respective median values of the text area and the pictorial pattern area are used in the detection of the image characteristics by the characteristic detection units 501, the influence of an outlier as a singular point due to a factor such as a stain is efficiently eliminated. Alternatively, using the size of the standard deviation enables accurate determination including the determination of the size of data, as illustrated in FIG. 23. Further, using the mode value in the detection of the image characteristics by the characteristic detection units 501 enables simple area specification and makes the operation resistant to image shift. Furthermore, two or more of the mean value, the standard deviation value, the median value, and the mode value of each of the image characteristics of the invisible light image may be combined in the detection of the image characteristics by the characteristic detection units 501.

[0138]

(Third Embodiment)

FIG. 24 is a diagram illustrating a configuration example of a fraud check device according to a third embodiment. FIG. 24 illustrates an image forming apparatus 2 typically called a multifunction peripheral (MFP) as an example of the fraud check device. The multifunction peripheral (MFP) has at least two functions out of a copier function, a printer function, a scanner function, and a facsimile function.

[0139]

An upper portion of the image forming apparatus 2 illustrated in FIG. 24 includes the image reading device 1 (the image reading device body 10 and the ADF 20) as the fraud check device. The configuration of this image reading device 1 is the same as the above-described one of the first embodiment, and thus a description thereof will be omitted here.

[0140]

The image forming apparatus 2 illustrated in FIG. 24 includes an image forming unit 80 and a sheet feeding unit 90 under the image reading device body 10. With the image forming unit 80, the image forming apparatus 2 prints an output image on a recording sheet (an example of a recording medium) based on an image read in the image reading device body 10. The output image is a visible image or an invisible image.

[0141]

The image forming unit 80 includes components such as an optical writing device 81, tandem-type imaging units (Y, M, C and K) 82, an intermediate transfer belt 83, and a second transfer belt 84. In the image forming unit 80, the optical writing device 81 writes images of a print target on photoconductor drums 820 in the imaging units 82, and toner images of respective plates are transferred onto the intermediate transfer belt 83 from the photoconductor drums 820. The K plate is formed with the K toner containing carbon black. [0142]

In the example illustrated in FIG. 24, the imaging units (Y, M, C and K) 82 include four rotatable photoconductor drums (Y, M, C and K) 820. Each of the photoconductor drums 820 is surrounded by imaging components including a charging roller, a development device, a first transfer roller, a cleaner unit, and a discharger. With the imaging components operating around the photoconductor drums 820 in a particular imaging process, images are formed on the photoconductor drums 820. The images formed on the photoconductor drums 820 are then transferred onto the intermediate transfer belt 83 as toner images by the first transfer rollers.

[0143] The intermediate transfer belt 83 is stretched by a drive roller and a driven roller and disposed in respective nips between the photoconductor drums 820 and the first transfer rollers. With the intermediate transfer belt 83 rotating, the toner images first-transferred to the intermediate transfer belt 83 are second-transferred onto the recording sheet on the second transfer belt 84 by a second transfer device. With the second transfer belt 84 rotating, the recording sheet is transported to a fixing device 85, and the toner images are fixed on the recording sheet as a color image. Thereafter, the recording sheet is ejected onto the sheet ejection tray 25 outside the image forming apparatus 2. [0144]

The sheet feeding unit 90 feeds a particular recording sheet from one of sheet feeding cassettes 91 and 92 that store recording sheets of different sheet sizes, for example, and transports and supplies the recording sheet to the second transfer belt 84 with transport means 93 including various rollers.

[0145]

The image forming unit 80 is not limited to the above-described configuration that forms an image with an electrophotographic method, and may form an image with an inkjet method. [0146]

The image reading device 1 (the image reading device body 10 and the ADF 20) may include, in addition to the light source 401 that emits light including at least an invisible wavelength range component (a near-infrared wavelength range component), a light source that emits light including a visible wavelength range component. This enables the image reading device 1 to copy the subject or obtain electronic image data of the subject as a scanner and determine the authenticity or otherwise of the subject simultaneously, thereby further improving convenience.

[0147]

In the above-described embodiment, a description has been given of an example in which a fraud check device according to the present disclosure is applied to the MFP with at least two functions out of the copier function, the printer function, the scanner function, and the facsimile function. A fraud check device according to the present disclosure is also applicable to any image forming apparatus such as a copier, a printer, a scanner, or a facsimile machine. [0148]

(Fourth Embodiment)

A fourth embodiment will be described.

[0149]

The fourth embodiment is different from the first embodiment in being applied to a security checking mechanism. In the following description of the fourth embodiment, differences from the first embodiment will be described, with the description of the same components as those of the first embodiment being omitted.

[0150] In the present embodiment, an example using an admission pass will be described as an example of application to the security checking mechanism. For example, in a case where the entry to an area off limits to outsiders is controlled with a gate pass (admission pass), identifying a copy of the pass enhances the security level.

[0151]

FIG. 25 is a diagram illustrating an example of an admission pass T3 according to the fourth embodiment. The example illustrated in FIG. 25 is an example of the admission pass T3 with a design of a pictorial pattern.

[0152]

In the admission pass T3 illustrated in FIG. 25, the image of a text area (the first image area) is formed with the black (K) toner containing carbon. In the admission pass T3 illustrated in FIG. 25, the image of a pictorial pattern area (the second image area), on the other hand, is formed with the dye toner not containing carbon (the C toner, the M toner, and the Y toner). [0153]

FIG. 26 is a diagram illustrating an example of an invisible light image obtained by reading the admission pass T3 in FIG. 25 with near-infrared light.

[0154]

In the admission pass T3 illustrated in FIG. 25, the image of the text area (the first image area) is formed with the black toner containing carbon, and the image of the pictorial pattern area (the second image area) is formed with the dye toner not containing carbon, as described above. In the invisible light image obtained by reading the admission pass T3 with nearinfrared light, therefore, the text is all read as black, and the pictorial pattern area is read as white, which is a color substantially equal to the color of the bare surface of the sheet.

[0155]

Reading an admission pass copy, which is obtained by copying the admission pass T3 illustrated in FIG. 25, with near-infrared light will be described.

[0156]

FIG. 27 is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the admission pass T3 in FIG. 25 with the black (K) toner, with near-infrared light. The black (K) toner is toner containing carbon, as described above.

[0157]

In the invisible light image in FIG. 27 obtained by reading the admission pass copy with nearinfrared light, black areas are all formed with black toner having the spectral characteristic of the black (K) toner in FIG. 4. Therefore, an image appears in the pictorial pattern area unlike in the example of the invisible light image obtained by reading the admission pass T3 in FIG. 25 with near-infrared light. That is, this example indicates that whether the admission pass as the subject is the original or a copy is determined by detecting whether the picture level of the pictorial pattern area is the white level.

[0158] FIG. 28, on the other hand, is a diagram illustrating an example of an invisible light image obtained by reading a copy, which is obtained by copying the admission pass T3 in FIG. 25 with the dye-paint toner, with near-infrared light. The dye-paint is, for example, cyan, magenta, or yellow toner or black toner not containing carbon.

[0159]

In the invisible light image in FIG. 28 obtained by reading the admission pass copy, the black areas are all formed with black toner having the spectral characteristic of the black (C+M+Y) toner in FIG. 4. Therefore, the text area and the pictorial pattern area of the admission pass T3 both disappear unlike in the example of the invisible light image obtained by reading the admission pass T3 in FIG. 25 with near-infrared light. That is, this example indicates that whether the admission pass as the subject is the original or a copy is determined by detecting whether the picture level of the text area includes the black level.

[0160]

As described above, according to the present embodiment, whether the admission pass is an authentic pass or a copy (fraudulent item) is accurately determined by detecting both whether the picture level of the pictorial pattern area is the white level and whether the picture level of the text area includes the black level.

[0161]

Further, the admission pass does not require special ink or toner, and it is unnecessary to extract dedicated or special embedded information such as encoded information from the admission pass. Consequently, the following effects are obtained.

[0162]

A first effect obtained is preventing a reduction in a provided security effect. The security effect is nowadays often provided by adding a quick response (QR) code®. However, adding a QR code to a document limits and allows inference of a security-related area in the document, causing a possible reduction in the security level. In the present embodiment, the information on the pass is limited to a natural pictorial pattern and text information. The present embodiment therefore has an effect of making it difficult to infer the security-related area and thus preventing a reduction in the security effect.

[0163]

A second effect obtained is enabling inexpensive issuance of a document. The present embodiment does not require a configuration causing an increase in cost such as creating and embedding a special QR code or embedding an integrated circuit (IC) chip.

[0164]

The above-described embodiments are illustrative and do not limit the present invention. Thus, numerous additional modifications and variations are possible in light of the above teachings. For example, elements and/or features of different illustrative embodiments may be combined with each other and/or substituted for each other within the scope of the present invention. Any one of the above-described operations may be performed in various other ways, for example, in an order different from the one described above. [0165]

Aspects of the present disclosure are as follows, for example.

According to a first aspect, a fraud check device includes an invisible light source, an image reading unit, an image characteristic detection unit, and a state determination unit. The invisible light source irradiates a subject with invisible light. The image reading unit reads reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The image characteristic detection unit detects identical or different image characteristics from a plurality of image areas in the invisible light image. Based on the image characteristics detected by the image characteristic detection unit, the state determination unit determines that the subject is in a first state. The image characteristic detection unit detects, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light. The image characteristic detection unit detects, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. The state determination unit determines that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

According to a second aspect, in the fraud check device of the first aspect, the state determination unit includes a plurality of threshold determination units that determine that the first image characteristic is equal to or less than a first threshold value, and that the second image characteristic is equal to or greater than a second threshold value.

According to a third aspect, in the fraud check device of the first or second aspect, the image characteristic detection unit performs the detection in the first image area as an area of an image including text information, and performs the detection in the second image area as an area of an image other than the image including the text information.

According to a fourth aspect, in the fraud check device of the third aspect, the image characteristic detection unit performs the detection in the second image area as a pictorial pattern area.

According to a fifth aspect, in the fraud check device of one of the first to fourth aspects, the invisible light of the invisible light source is infrared light, and the image reading unit reads the reflected light in at least an infrared wavelength band.

According to a sixth aspect, in the fraud check device of one of the first to fifth aspects, the image characteristic detection unit performs the detection in the first image area as an area including an image formed with at least a material that contains carbon, and performs the detection in the second image area as an area including an image formed with at least a material other than the material that contains carbon.

According to a seventh aspect, in the fraud check device of one of the first to sixth aspects, the image characteristic detection unit performs the detection in the plurality of image areas, which includes at least an area where information visually recognizable under visible light is clearly presented.

According to an eighth aspect, in the fraud check device of one of the first to seventh aspects, the image characteristic detection unit uses a mean value, a stand deviation value, a median value, or a mode value of each of the image characteristics of the invisible light image to detect the image characteristics.

According to a ninth aspect, the fraud check device of one of the first to eighth aspects further includes a notification unit that notifies an external device or a user of information of the determination by the state determination unit that the subject is in the first state.

According to a tenth aspect, the fraud check device of one of the first to ninth aspects further includes a visible light source and another image reading unit. The visible light source includes light in at least a visible wavelength band. The another image reading unit reads at least reflected light of the visible light from the subject to obtain a visible light image from the reflected light of the visible light. The reflected light is part of the visible light.

According to an eleventh aspect, the fraud check device of the tenth aspect further includes an image forming unit that forms the visible light image on a recording medium as an image of the subject.

According to a twelfth aspect, the fraud check device of the tenth aspect further includes an image output unit that outputs the visible light image to an external device as an image of the subject.

According to a thirteenth aspect, a system includes a fraud check device and a server. The fraud check device includes a light source, an image reading unit, and an image characteristic detection unit. The light source irradiates a subject with invisible light. The image reading unit reads reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The image characteristic detection unit detects identical or different image characteristics from a plurality of image areas in the invisible light image. The server includes a state determination unit. Based on the image characteristics detected by the image characteristic detection unit, the state determination unit determines that the subject is in a first state. The image characteristic detection unit detects, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light. The image characteristic detection unit detects, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. Based on a first image characteristic of the first image area and a second image characteristic of the second image area, the state determination unit determines that the subject is in the first state.

According to a fourteenth aspect, a fraud check method is performed by a fraud check device that includes an invisible light source and an image reading unit. The invisible light source irradiates a subject with invisible light. The image reading unit reads reflected light from the subject to obtain an invisible light image from the reflected light. The reflected light is part of the invisible light and is in a wavelength band. The fraud check method includes detecting identical or different image characteristics from a plurality of image areas in the invisible light image, and determining that the subject is in a first state based on the image characteristic detected in the detecting. The detecting includes detecting, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material that absorbs invisible light, and detecting, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with at least a material other than the material that absorbs invisible light. The determining includes determining that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

[0166]

The present invention can be implemented in any convenient form, for example, using dedicated hardware, or a mixture of dedicated hardware and software. The present invention may be implemented as computer software implemented by one or more networked processing apparatuses. The processing apparatuses include any suitably programmed apparatuses such as a general purpose computer, a personal digital assistant, a Wireless Application Protocol (WAP) or third-generation (3G)-compliant mobile telephone, and so on. Since the present invention can be implemented as software, each and every aspect of the present invention thus encompasses computer software implementable on a programmable device. The computer software can be provided to the programmable device using any conventional carrier medium (carrier means). The carrier medium includes a transient carrier medium such as an electrical, optical, microwave, acoustic or radio frequency signal carrying the computer code. An example of such a transient medium is a Transmission Control Protocol/Intemet Protocol (TCP/IP) signal carrying computer code over an IP network, such as the Internet. The carrier medium may also include a storage medium for storing processor readable code such as a floppy disk, a hard disk, a compact disc read-only memory (CD- ROM), a magnetic tape device, or a solid state memory device.

[0167]

The functionality of the elements disclosed herein may be implemented using circuitry or processing circuitry which includes general purpose processors, special purpose processors, integrated circuits, application- specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), and/or combinations thereof which are configured or programmed, using one or more programs stored in one or more memories, to perform the disclosed functionality. Processors are considered processing circuitry or circuitry as they include transistors and other circuitry therein. In the disclosure, the circuitry, units, or means are hardware that carry out or are programmed to perform the recited functionality. The hardware may be any hardware disclosed herein which is programmed or configured to carry out the recited functionality.

There is a memory that stores a computer program which includes computer instructions. These computer instructions provide the logic and routines that enable the hardware (e.g., processing circuitry or circuitry) to perform the method disclosed herein. This computer program can be implemented in known formats as a computer-readable storage medium, a computer program product, a memory device, a record medium such as a CD-ROM or DVD, and/or the memory of an FPGA or ASIC.

[0168]

This patent application is based on and claims priority to Japanese Patent Application No. 2024-109700, filed on July 8, 2024, in the Japan Patent Office, the entire disclosure of which is hereby incorporated by reference herein.

[Reference Signs List]

[0169]

1 image reading device (fraud check device)

2 image forming apparatus (fraud check device)

13, 401 light source

80 image forming unit

305 image output unit

402 image sensor (image reading unit)

500 image characteristic detection unit

600 state determination unit

700 state determination information notification unit (notification unit)

Claims

[CLAIMS]

1. A fraud check device comprising: an invisible light source to irradiate a subject with invisible light; an image reading unit configured to read reflected light from the subject to obtain an invisible light image from the reflected light, the reflected light being part of the invisible light and being in a wavelength band; a control unit configured to: detect identical or different image characteristics from a plurality of image areas in the invisible light image; determine that the subject is in a first state based on the image characteristics that is detected; detect, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material that absorbs invisible light; detect, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material other than the material that absorbs invisible light; and determine that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

2. The fraud check device of claim 1, wherein the control unit includes a plurality of threshold determination units configured to determine that the first image characteristic is equal to or less than a first threshold value, and that the second image characteristic is equal to or greater than a second threshold value.

3. The fraud check device of claim 1 or 2, wherein the control unit performs the detection in the first image area as an area of an image including text information, and performs the detection in the second image area as an area of an image other than the image including the text information.

4. The fraud check device of claim 3, wherein the control unit performs the detection in the second image area as a pictorial pattern area.

5. The fraud check device of one of claims 1 to 4, wherein the invisible light of the invisible light source is infrared light, and wherein the image reading unit reads the reflected light in an infrared wavelength band.

6. The fraud check device of one of claims 1 to 5, wherein the control unit performs the detection in the first image area as an area including an image formed with a material that comprises carbon, and performs the detection in the second image area as an area including an image formed with a material other than the material that comprises carbon.

7. The fraud check device of one of claims 1 to 6, wherein the control unit performs the detection in the plurality of image areas, which includes an area where information visually recognizable under visible light is clearly presented.

8. The fraud check device of one of claims 1 to 7, wherein the control unit uses a mean value, a stand deviation value, a median value, or a mode value of each of the image characteristics of the invisible light image to detect the image characteristics.

9. The fraud check device of one of claims 1 to 8, wherein the control unit is further configured to notify an external device or a user of information of the determination that the subject is in the first state.

10. The fraud check device of one of claims 1 to 9, further comprising: a visible light source to irradiate light in a visible wavelength band, and another image reading unit configured to read reflected light of the visible light from the subject to obtain a visible light image from the reflected light of the visible light, the reflected light being part of the visible light.

11. The fraud check device of claim 10, further comprising an image forming unit configured to form the visible light image on a recording medium as an image of the subject.

12. The fraud check device of claim 10, further comprising an image output unit configured to output the visible light image to an external device as an image of the subject.

13. A system comprising: a fraud check device; and a server, the fraud check device including a light source to irradiate a subject with invisible light, an image reading unit configured to read reflected light from the subject to obtain an invisible light image from the reflected light, the reflected light being part of the invisible light and being in a wavelength band, and a control unit configured to detect identical or different image characteristics from a plurality of image areas in the invisible light image, the server including a control device configured to determine that the subject is in a first state based on the image characteristics that is detected by the control unit, wherein the control unit is configured to detect, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material that absorbs invisible light, and detect, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material other than the material that absorbs invisible light, and the control device determines that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.

14. A fraud check method performed by a fraud check device, the fraud check method comprising: irradiating a subject with invisible light; reading reflected light from the subject to obtain an invisible light image from the reflected light, the reflected light being part of the invisible light and being in a wavelength band; detecting identical or different image characteristics from a plurality of image areas in the invisible light image; and determining that the subject is in a first state based on the detected image characteristics, the detecting including detecting, from a first image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material that absorbs invisible light, and detecting, from a second image area included in the plurality of image areas, an image characteristic of an area of an image formed with a material other than the material that absorbs invisible light, and the determining including determining that the subject is in the first state based on a first image characteristic of the first image area and a second image characteristic of the second image area.