WO2017045403A1 - 一种票据重张检测方法和装置 - Google Patents

一种票据重张检测方法和装置 Download PDF

Info

Publication number
WO2017045403A1
WO2017045403A1 PCT/CN2016/080650 CN2016080650W WO2017045403A1 WO 2017045403 A1 WO2017045403 A1 WO 2017045403A1 CN 2016080650 W CN2016080650 W CN 2016080650W WO 2017045403 A1 WO2017045403 A1 WO 2017045403A1
Authority
WO
WIPO (PCT)
Prior art keywords
banknote
image
texture
reverse
identified
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2016/080650
Other languages
English (en)
French (fr)
Inventor
邱新华
刘梦涛
王荣秋
余元超
王卫锋
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
GRG Banking Equipment Co Ltd
Original Assignee
GRG Banking Equipment Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by GRG Banking Equipment Co Ltd filed Critical GRG Banking Equipment Co Ltd
Priority to US15/757,971 priority Critical patent/US20180204405A1/en
Priority to RU2018112269A priority patent/RU2688306C1/ru
Priority to EP16845517.8A priority patent/EP3352146B1/en
Priority to ES16845517T priority patent/ES2944570T3/es
Publication of WO2017045403A1 publication Critical patent/WO2017045403A1/zh
Anticipated expiration legal-status Critical
Priority to ZA2018/02074A priority patent/ZA201802074B/en
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D11/00—Devices accepting coins; Devices accepting, dispensing, sorting or counting valuable papers
    • G07D11/20—Controlling or monitoring the operation of devices; Data handling
    • G07D11/22—Means for sensing or detection
    • G07D11/235—Means for sensing or detection for monitoring or indicating operating conditions; for detecting malfunctions
    • G07D11/237—Means for sensing or detection for monitoring or indicating operating conditions; for detecting malfunctions for detecting transport malfunctions, e.g. jams or misfeeds
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
    • B65H7/00—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles
    • B65H7/02—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles by feelers or detectors
    • B65H7/06—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles by feelers or detectors responsive to presence of faulty articles or incorrect separation or feed
    • B65H7/12—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles by feelers or detectors responsive to presence of faulty articles or incorrect separation or feed responsive to double feed or separation
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
    • B65H7/00—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles
    • B65H7/02—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles by feelers or detectors
    • B65H7/14—Controlling article feeding, separating, pile-advancing, or associated apparatus, to take account of incorrect feeding, absence of articles, or presence of faulty articles by feelers or detectors by photoelectric feelers or detectors
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/40—Analysis of texture
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D7/00—Testing specially adapted to determine the identity or genuineness of valuable papers or for segregating those which are unacceptable, e.g. banknotes that are alien to a currency
    • G07D7/181—Testing mechanical properties or condition, e.g. wear or tear
    • G07D7/183—Detecting folds or doubles
    • B—PERFORMING OPERATIONS; TRANSPORTING
    • B65—CONVEYING; PACKING; STORING; HANDLING THIN OR FILAMENTARY MATERIAL
    • B65H—HANDLING THIN OR FILAMENTARY MATERIAL, e.g. SHEETS, WEBS, CABLES
    • B65H2701/00—Handled material; Storage means
    • B65H2701/10—Handled articles or webs
    • B65H2701/19—Specific article or web
    • B65H2701/1912—Banknotes, bills and cheques or the like
    • G—PHYSICS
    • G07—CHECKING-DEVICES
    • G07D—HANDLING OF COINS OR VALUABLE PAPERS, e.g. TESTING, SORTING BY DENOMINATIONS, COUNTING, DISPENSING, CHANGING OR DEPOSITING
    • G07D2211/00—Paper-money handling devices

Definitions

  • the present invention relates to the field of financial equipment, and in particular, to a method and apparatus for detecting a double-folding of a ticket.
  • the detection capability of banknote re-drawing is an important technical indicator.
  • the coincidence of banknotes sometimes occurs.
  • the improvement of the hardware structure can reduce the probability of occurrence of heavy banknotes, it cannot completely prevent the occurrence of heavy banknotes, so it is accurate and undetectable to detect whether the banknotes are re-expanded for banknote recognition. Words are of great significance.
  • the general method for detecting the weight of the banknote is based on the detection method of the thickness signal, and the thickness sensor is used to collect the thickness signal of each banknote in the banknote channel, and whether the banknote width and the overall thickness are greater than a given threshold value are judged whether the film is re-tensioned.
  • the method has high requirements on the density and precision of the signal collected by the thickness sensor. When there are attachments on the banknote (such as tape attached) or the banknotes are slightly arched and the old banknotes become thick, it is easy to be mistakenly judged as heavy banknotes.
  • the embodiment of the invention provides a method and a device for detecting the re-folding of a ticket, which can solve the problem that the existing multi-sheet detecting method has the attachment on the banknote, the slight arching of the banknote, and the thickening of the old banknote, which is easy to cause misjudgment.
  • the banknote to be identified is a heavy banknote, and if not, the banknote to be identified is not a heavy banknote.
  • the coupling degree measurement is performed on the transmission image of the front image and the reverse image according to the local feature attribute window, and the step of obtaining the measurement result specifically includes at least one of the following sub-steps:
  • the first substep is a first substep
  • the tone texture period including a number of periodic color textures, a number of cycles, and a periodic interval, the structural texture
  • the period includes the number of periodic structural texture features, the number of cycles, and the periodic spacing;
  • texture primitives of the corresponding regions of the transmission image defined by the local feature attribute window refer to texture units having a specific shape structure
  • determining whether the measurement result meets the preset heavy money condition is specifically:
  • the method further includes:
  • the method further includes:
  • the method further includes:
  • a front and back acquisition module for collecting a front image and a reverse image of the banknote to be identified
  • a banknote information obtaining module configured to respectively acquire front banknote information and reverse banknote information of the banknote to be identified according to the front image and the reverse image, and initialize a corresponding local feature property window, where the local feature property window includes a template for identifying a preset identification area of a corresponding feature attribute of the image;
  • a coupling degree measuring module configured to perform a coupling degree measurement on the transmission image of the front image and the reverse image according to the local feature attribute window, to obtain a measurement result
  • a heavy bank determination module configured to determine whether the measurement result meets a preset heavy banknote condition
  • a heavy billing module configured to determine that the banknote to be identified is a heavy bill when the judgment result of the heavy bill judgment module is YES;
  • the non-heavy banknote module is configured to determine that the banknote to be identified is not a heavy banknote when the judgment result of the heavy banknote determination module is negative.
  • the coupling degree measurement module specifically includes at least one of the following submodules:
  • the first sub-module is the first sub-module
  • a tone and structure texture unit configured to calculate a tone texture period and a texture texture period of a corresponding region of the transmission image defined by the local feature attribute window, the tone texture period including a number of periodic color textures, a number of cycles And a periodicity interval, the structural texture period including the number of periodic structural texture features, the number of cycles, and the periodic spacing;
  • a first determining unit configured to determine whether a difference between the tone texture period and the structural texture period and a preset standard value corresponding to the local feature attribute window exceeds a preset first threshold, and obtains the first critical result
  • the second submodule is the first submodule
  • a texture primitive acquiring unit configured to acquire a texture primitive of a corresponding region of the transmission image defined by the local feature attribute window, where the texture primitive refers to a texture unit having a specific shape structure;
  • a second determining unit configured to determine whether a difference between the texture primitive and the preset standard texture primitive corresponding to the local feature attribute window exceeds a preset second threshold, to obtain a second determination result
  • the third sub-module is the third sub-module
  • a texture definition quantity acquisition unit configured to calculate a texture definition amount of the corresponding area of the transmission image defined by the local feature attribute window, where the texture definition quantity refers to a degree of blur of the preset texture
  • a third determining unit configured to determine whether a difference between the texture definition amount and the preset standard metric value corresponding to the local feature attribute window exceeds a preset third threshold, to obtain a third determination result
  • the heavy money determination module includes:
  • the heavy money determination unit is configured to determine whether any of the determination results is yes.
  • the device further comprises at least one module group:
  • the first module group :
  • a front information module configured to acquire front face value information of the banknote to be identified according to the front image
  • a reverse information module configured to acquire, according to the reverse image, a reverse face value information of the banknote to be identified
  • a face value-oriented judging module configured to determine, according to a preset face value rule, whether the front face value information and the back face value information do not match, and obtain a fourth judgment result
  • the second module group :
  • a front size module configured to acquire a front image size of the banknote to be identified according to the front image
  • a reverse size module configured to acquire a reverse image size of the banknote to be identified according to the reverse image
  • An image size determining module configured to determine whether the front image size or the reverse image size exceeds a preset standard size range of the banknote to be identified, to obtain a fifth determination result
  • the third module group is a first module group:
  • a front light transmission metric module configured to acquire a front light transmission metric of the banknote to be identified according to the front image
  • a reverse light transmission metric module configured to acquire a reverse light transmission metric of the banknote to be identified according to the reverse image
  • the light transmission metric determining module is configured to determine whether the front light transmission metric or the reverse light transmission metric exceeds a preset standard light transmission metric range of the banknote to be identified, to obtain a sixth determination result.
  • a ticket multi-sheet detecting method detects the degree of coupling by using a transmission image of a front image or a reverse image of a banknote to be recognized, and determines whether the banknote to be identified is a heavy banknote according to the measurement result, and solves the existing heavy weight.
  • the detection method has the problem that the deposit on the banknote, the slight bulging of the banknote, and the thickening of the old banknote are likely to cause misjudgment.
  • FIG. 1 is a flow chart of an embodiment of a method for detecting a re-folding of a ticket according to an embodiment of the present invention
  • FIG. 2 is a flow chart of another embodiment of a method for detecting a re-folding of a ticket according to an embodiment of the present invention
  • 3a and 3b are schematic diagrams showing a correct combination of face value orientations in an embodiment of the present invention.
  • FIGS. 4a and 4b are schematic diagrams showing the combination of face value of heavy banknotes according to an embodiment of the present invention.
  • FIG. 5a and FIG. 5b are schematic diagrams showing a combination of face value of heavy banknotes according to an embodiment of the present invention.
  • 6a and 6b are schematic views showing the size of a heavy banknote according to an embodiment of the present invention.
  • FIG. 7 is a schematic diagram of a comparison of tone texture periods in an embodiment of the present invention.
  • FIG. 8a and 8b are schematic diagrams showing a comparison of structural texture periods according to an embodiment of the present invention.
  • 9a and 9b are schematic diagrams showing comparison of texture primitives according to an embodiment of the present invention.
  • 10a and 10b are schematic diagrams showing a comparison of texture sharpness in an embodiment of the present invention.
  • FIG. 11 is a structural diagram of an embodiment of a ticket multi-sheet detecting apparatus according to an embodiment of the present invention.
  • FIG. 12 is a structural diagram of another embodiment of a ticket multi-sheet detecting apparatus according to an embodiment of the present invention.
  • the embodiment of the invention provides a method and a device for detecting the re-folding of a ticket, which is used for solving the problem that the existing multi-sheet detecting method has the attachment on the banknote, the slight arching of the banknote, and the thickening of the old banknote, which is easy to cause misjudgment.
  • an embodiment of a method for detecting a re-folding of a ticket in an embodiment of the present invention includes:
  • a front image and a reverse image of the banknote to be identified, and a transmission image of the front image or the reverse image may be acquired.
  • the front banknote information and the reverse banknote information of the banknote to be identified may be respectively acquired according to the front image and the reverse image, and a corresponding local feature attribute window is initialized, and the local feature attribute window is initialized.
  • the degree of coupling of the front image or the transmission image of the reverse image may be measured according to the local feature attribute window to obtain a measurement result.
  • step 104 it is determined whether the measurement result meets the preset re-cash condition, if yes, step 105 is performed, and if not, step 106 is performed;
  • step 105 is performed, and if no, step 106 is performed.
  • the banknote to be identified is a heavy banknote
  • the banknote to be identified may be regarded as a heavy bill.
  • banknote to be identified is not heavy.
  • the banknote to be identified may be considered not to be heavy.
  • the method for detecting the double-sheet detection method of the foregoing is: first, collecting And a reverse image of the front and back images; a feature attribute window, which is a template of a preset identification area including a corresponding feature attribute of the desired recognition image; and then, according to the local feature attribute window, the coupling degree is measured to obtain a measurement result; And determining whether the measurement result meets the preset heavy banknote condition, and if so, the banknote to be identified is a heavy banknote, and if not, the banknote to be identified is not a heavy banknote.
  • a ticket multi-sheet detecting method detects the degree of coupling by the transmission image of the front image or the reverse image of the banknote to be recognized, and determines whether the banknote to be identified is a heavy banknote according to the measurement result, and solves the existing heavy weight.
  • the detection method has the problem that the deposit on the banknote, the slight bulging of the banknote, and the thickening of the old banknote are likely to cause misjudgment.
  • FIG. 2 another embodiment of the bill multi-sheet detecting method in the embodiment of the present invention includes:
  • the front banknote information and the reverse banknote information of the banknote to be identified may be respectively acquired according to the front image and the reverse image, and a corresponding local feature attribute window is initialized, and the local feature attribute window is initialized.
  • the local feature attribute window is predefined, and different banknotes according to different local feature attribute windows.
  • the local feature attribute window is mainly used to quickly locate a corresponding area on the banknote image that needs to acquire specific feature information. Therefore, in this embodiment, the front banknote information and the reverse banknote information of the front image and the reverse image may be obtained.
  • the banknote information is a face value
  • the local feature attribute window corresponding to the front image may be acquired, and the reverse image is obtained.
  • Corresponding local feature property windows and initialize these local feature property windows.
  • the tone texture period and the texture texture period of the corresponding region of the transmission image of the front image or the reverse image defined by the local feature attribute window may be calculated.
  • the tone texture period includes the number of periodic color textures, the number of periods, and the period spacing. As shown in FIG. 7, the letters R/G/B respectively represent texture colors, and the number of tone period textures is 3, and the period is The number is 1, and the period spacing is T.
  • the structural texture period includes the number of periodic texture features, the number of periods, and the period spacing. As shown in FIG. 8a, the number of structural textures is 2, the number of periods is 3 and 9, respectively, and the period spacing is T 1 and T, respectively. 2 .
  • banknotes two banknotes cannot be seamlessly integrated due to factors such as printing accuracy, media size difference, and motion. Therefore, whether the banknote to be identified is a heavy banknote can be determined by judging the difference between the tone texture period and the structural texture period and the standard value. For details, see step 204.
  • the tone texture period and the texture texture period may be determined to correspond to the local feature attribute window. Whether the difference between the preset standard values exceeds a preset first threshold value, and the first judgment result is obtained.
  • the standard value corresponding to the local feature attribute window is preset, and the standard value is a standard value of the corresponding tone texture period and the structure texture period.
  • the tone texture period and the texture texture period of the image to be identified may be considered to be out of the normal range, Then the image to be identified is a heavy banknote.
  • Figure 8a shows the standard texture
  • Figure 8b shows the texture that appears when two banknotes are coincident. It can be seen that the period differs greatly from the standard value.
  • the texture primitive of the corresponding area of the transmission image defined by the local feature attribute window may be acquired.
  • the texture primitive refers to a texture unit having a structure of a particular shape, as shown in Figure 9a. Understandably, the help of the local feature property window Underneath, the texture primitives on the corresponding regions can be easily obtained from the transmission image.
  • the texture primitive of the corresponding region of the transmission image defined by the local feature attribute window After obtaining the texture primitive of the corresponding region of the transmission image defined by the local feature attribute window, it may be determined whether the difference between the texture primitive and the preset standard texture primitive corresponding to the local feature attribute window exceeds a preset second. The threshold value is obtained as a second judgment result.
  • the standard texture primitive corresponding to the local feature attribute window is preset
  • the standard texture primitive is a standard template (or numerical value) of the corresponding texture primitive, by comparing the texture primitive and the standard texture primitive. The difference between the two, if the difference exceeds the preset second threshold, it can be considered that the texture primitive of the image to be recognized is not in the normal range, and the image to be recognized is a heavy banknote.
  • Figure 9a is a quasi-texture template, and when a re-folding occurs, the texture primitives appearing in the transmitted image may become the situation shown in Figure 9b.
  • the texture definition amount of the corresponding area of the transmission image under the local feature attribute window may be calculated.
  • the amount of texture definition refers to the degree of blurring of the preset texture, as shown in Fig. 10a. It can be understood that the higher the degree of blurring, the higher the possibility of heavy bills; on the contrary, the lower the degree of blurring, the lower the possibility of heavy bills.
  • the texture definition amount of the corresponding region of the transmission image defined by the local feature attribute window After calculating the texture definition amount of the corresponding region of the transmission image defined by the local feature attribute window, it may be determined whether the difference between the texture definition amount and the preset standard metric value corresponding to the local feature attribute window exceeds a preset third.
  • the threshold value is obtained as a third judgment result.
  • the standard metric value corresponding to the local feature attribute window is preset, and the standard metric value is a standard value of the corresponding texture definition quantity, and the difference between the calculated texture definition quantity and the standard metric value is obtained. If the difference exceeds the preset third threshold, the image to be recognized of the image to be recognized may be considered to be out of the normal range, and the image to be recognized is a heavy banknote. For example, the texture in Figure 10a is clear, while in the heavy notes shown in Figure 10b, the texture is blurred.
  • the banknote to be identified may be acquired according to the front image
  • the front value is oriented to information.
  • the front face value information includes the face value and the face of the front image.
  • the face value refers to the currency value of the banknote
  • the face value refers to the frontal orientation (positive or reverse placement) of the banknote to be recognized when the front image is imaged.
  • the reverse face value information of the banknote to be identified may be acquired according to the reverse image.
  • the front face value information and the back face value information may be mismatched according to a preset face value rule, and a fourth judgment result is obtained. It can be understood that if the front face value information and the back face value information cannot be paired according to a priori knowledge, the banknote to be identified can be regarded as a heavy banknote. As shown in Figures 3a and 3b, the correct combination, if there is a similar combination of Figure 4a and Figure 4b, Figure 5a and Figure 5b, can not match.
  • the front image size of the banknote to be identified may be acquired according to the front image.
  • the reverse image size of the banknote to be identified may be acquired according to the reverse image.
  • the front image size and the size of the reverse image size include height information of the image and width information of the image. It can be understood that, as shown in FIG. 6a and FIG. 6b, when two banknotes are heavy, that is, misaligned, the size of the obtained banknotes exceeds the preset standard size range.
  • the banknote to be identified may be acquired according to the front image Positive light transmission metric.
  • the reverse light transmission metric of the banknote to be identified may be acquired according to the reverse image.
  • the front light transmission metric and the reverse light transmission metric After obtaining the front light transmission metric and the reverse light transmission metric, it may be determined whether the front light transmission metric or the reverse light transmission metric exceeds a preset standard light transmission metric range of the banknote to be identified, to obtain a sixth determination result.
  • the light transmission metric includes the reflected image gray mean value Gf of the image, the transmitted image gray mean value Gt, and the reflected image and the transmitted image gray correlation Rft, and Rft can be expressed as a combination of Gf and Gt, such as 1); the Gf and Gt may be the gray mean of the entire image or the mean of the local regions.
  • the grayscale mean of the watermark area will be close to the maximum value at the time of re-expansion, which is higher than the tens of gray levels of the normal time. If the obtained light transmission metric exceeds the preset standard light transmission metric range of the banknote to be identified, the banknote to be identified may be regarded as a heavy banknote.
  • the standard light transmission metric range is a preset standard range of the light transmission metric of the banknote to be identified.
  • R ft ⁇ (G f /G t )+ ⁇ (G f ⁇ G t );( ⁇ R, ⁇ R) (1)
  • ⁇ denotes a weight parameter and R denotes a real number field.
  • step 218, determine whether there is any determination result is yes, if yes, proceed to step 219, and if not, proceed to step 220;
  • Step 219 if no, step 220 is performed. That is, as long as one of the first judgment result, the second judgment result, the third judgment result, the fourth judgment result, the fifth judgment result, or the sixth judgment result is YES, the banknote to be recognized may be regarded as If the judgment result is no, the banknote to be identified is not considered to be heavy.
  • the banknote to be identified is a heavy banknote
  • the banknote to be identified is not a heavy banknote.
  • the banknote to be identified is not heavy. banknote.
  • the above steps 205 to 206 are to obtain the second determination result
  • the above steps 207 to 208 are to obtain the third determination result
  • the above steps 209 to 211 are to acquire the fourth determination result.
  • the determination result, the above steps 212 to 214 are to obtain the fifth determination result, and the above steps 215 to 217 are to obtain the third determination result, which can be divided into six modules. These six modules can be combined with each other, or they can be used alone, and the multi-sheet detection of the ticket can be realized. Moreover, when the six modules are used in combination, the order between the six modules can be arbitrarily arranged and combined without affecting the result of the multi-sheet detection.
  • the method for detecting the re-folding of the bill is detected by the degree of coupling of the transmission image of the front image or the reverse image of the banknote to be recognized, and whether the banknote to be identified is a heavy banknote according to the measurement result, and the existing re-tension is solved. Detection method There is a problem that the banknotes are attached, the banknotes are slightly arched, and the old banknotes are thickened, which may cause misjudgment.
  • an embodiment of the apparatus for detecting the weight of the ticket in the embodiment of the present invention includes:
  • the front and back collecting module 111 is configured to collect a front image and a reverse image of the banknote to be identified;
  • the banknote information obtaining module 112 is configured to respectively acquire the front banknote information and the reverse banknote information of the banknote to be identified according to the front image and the reverse image, and initialize a corresponding local feature attribute window, wherein the local feature attribute window includes the required identification image. a template of a preset identification area corresponding to the feature attribute;
  • the coupling degree measuring module 113 is configured to measure the coupling degree of the front image and the transmission image of the reverse image according to the local feature attribute window, to obtain a measurement result;
  • the heavy bank determination module 114 is configured to determine whether the measurement result meets a preset heavy banknote condition
  • the heavy banknote module 115 is configured to determine that the banknote to be identified is a heavy banknote when the judgment result of the heavy banknote determination module 114 is YES;
  • the non-recounting module 116 is configured to: when the judgment result of the heavy bill determination module 114 is negative, It is determined that the banknote to be identified is not a heavy banknote.
  • the front and back collecting module 111 collects the front image and the reverse image of the banknote to be identified;
  • the banknote information acquiring module 112 respectively obtains the front banknote information and the reverse banknote information of the banknote to be identified according to the front image and the reverse image, and initializes Corresponding local feature attribute window, which is a template of a preset identification area containing corresponding feature attributes of the desired recognition image;
  • the coupling degree measurement module 113 according to the local feature attribute window to the front image and the reverse image
  • the transmission image is measured by the degree of coupling, and the measurement result is obtained;
  • the weight determination module 114 determines whether the measurement result meets the preset weight condition; when the determination result of the weight determination module 114 is YES, the heavy money module 115 determines the waiting
  • the banknote is identified as a heavy banknote; when the determination result of the heavy banknote determination module 114 is negative, the non-tick banknote module 116 determines that the banknote to be identified is not a heavy banknote.
  • a bill multi-sheet detecting device detects the degree of coupling by the transmission image of the front image or the reverse image of the banknote to be recognized, and determines whether the banknote to be identified is a heavy banknote according to the measurement result, and solves the existing heavy weight.
  • the detection method has the problem that the deposit on the banknote, the slight bulging of the banknote, and the thickening of the old banknote are likely to cause misjudgment.
  • FIG. 12 another embodiment of the bill multi-sheet detecting apparatus in the embodiment of the present invention includes:
  • the front and back collecting module 121 is configured to collect a front image and a reverse image of the banknote to be identified;
  • the banknote information obtaining module 122 is configured to respectively obtain the front banknote information and the reverse banknote information of the banknote to be identified according to the front image and the reverse image, and initialize a corresponding local feature attribute window, wherein the local feature attribute window includes the required identification image. a template of a preset identification area corresponding to the feature attribute;
  • a coupling degree measuring module 123 configured to perform a coupling degree measurement on the front image and the transmission image of the reverse image according to the local feature attribute window, to obtain a measurement result
  • the heavy bank determination module 124 is configured to determine whether the measurement result meets a preset heavy banknote condition
  • the banknote module 125 is configured to determine that the banknote to be identified is a heavy banknote when the judgment result of the heavy banknote determination module 124 is YES;
  • the non-heavy banknote module 126 is configured to determine that the banknote to be identified is not a heavy banknote when the determination result of the heavy banknote determination module 124 is negative.
  • the coupling degree measurement module 123 in this embodiment may specifically include:
  • a tone and structure texture unit 1231 configured to calculate a tone texture period and a texture texture period of the corresponding region of the transmission image defined by the local feature attribute window, the tone texture period including the number of periodic color textures, the number of cycles, and the period
  • the pitch, the structural texture period includes the number of periodic texture features, the number of cycles, and the periodic spacing;
  • the first determining unit 1232 is configured to determine whether a difference between the tonal texture period and the preset texture value corresponding to the local feature attribute window exceeds a preset first threshold, to obtain a first determination result;
  • a texture primitive acquiring unit 1233 configured to acquire a texture primitive of a corresponding region of the transmission image defined by the local feature attribute window, where the texture primitive refers to a texture unit having a specific shape structure;
  • a second determining unit 1234 configured to determine whether a difference between the texture primitive and the preset standard texture primitive corresponding to the local feature attribute window exceeds a preset second threshold, to obtain a second determination result
  • the texture definition amount obtaining unit 1235 is configured to calculate a texture definition amount of the corresponding area of the transmission image defined by the local feature attribute window, where the texture definition quantity refers to a degree of blur of the preset texture;
  • the third determining unit 1236 is configured to determine whether a difference between the texture definition amount and the preset standard metric value corresponding to the local feature attribute window exceeds a preset third threshold, to obtain a third determination result;
  • the heavy bill determination module 124 may include:
  • the heavy bill determination unit 1241 is configured to determine whether any of the determination results is YES.
  • the front information module 127 is configured to obtain, according to the front image, face front value information of the banknote to be identified;
  • the reverse information module 128 is configured to acquire, according to the reverse image, the reverse face value information of the banknote to be identified;
  • the face value-oriented judging module 129 is configured to determine, according to a preset face value, that the front face value information and the back face value information do not match, and obtain a fourth judgment result;
  • a front size module 130 configured to acquire a front view of the to-be-identified banknote according to the front image Image size
  • a reverse size module 131 configured to acquire a reverse image size of the banknote to be identified according to the reverse image
  • the image size determining module 132 is configured to determine whether the front image size or the reverse image size exceeds a preset standard size range of the banknote to be identified, to obtain a fifth determination result;
  • a front light transmission metric module 133 configured to acquire a front light transmission metric of the banknote to be identified according to the front image
  • a reverse light transmission metric module 134 configured to acquire a reverse light transmission metric of the banknote to be identified according to the reverse image
  • the light transmission metric determination module 135 is configured to determine whether the front light transmission metric or the reverse light transmission metric exceeds a preset standard light transmission metric range of the banknote to be identified, to obtain a sixth determination result.
  • the units 1233 and 1234 in order to obtain the first determination result, the units 1233 and 1234 obtain the second determination result, and the units 1235 and 1236 obtain the third determination result, and the modules 127, 128, and 129 are acquired.
  • the fourth determination result, the modules 130, 131, and 132 are used to obtain the fifth determination result, and the modules 133, 134, and 135 are used to obtain the third determination result, and can be divided into six blocks. These six blocks can be combined with each other or used alone, and the double sheet detection of the bill can be realized. Moreover, when the six blocks are used in combination, the order between the six blocks can be arbitrarily arranged and combined without affecting the result of the multi-sheet detection.
  • the disclosed system, apparatus, and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the unit is only a logical function division.
  • there may be another division manner for example, multiple units or components may be combined or Can be integrated into another system, or some features can be ignored or not executed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separate,
  • the components displayed as units may or may not be physical units, that is, may be located in one place, or may be distributed to multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a computer readable storage medium.
  • the technical solution of the present invention which is essential or contributes to the prior art, or all or part of the technical solution, may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a computer device (which may be a personal computer, server, or network device, etc.) to perform all or part of the steps of the methods described in various embodiments of the present invention.
  • the foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, and the like. .

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Theoretical Computer Science (AREA)
  • Inspection Of Paper Currency And Valuable Securities (AREA)
  • Controlling Sheets Or Webs (AREA)
  • Image Analysis (AREA)

Abstract

一种票据重张检测方法和检测装置，检测方法包括：采集待识别钞票的正面图像和反面图像，以及透射图像（101）；根据正面图像和反面图像分别获取待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板（102）；根据局部特征属性窗对正面图像和反面图像的透射图像进行耦合程度测量，得到测量结果（103）；判断测量结果是否符合预设的重钞条件（104），若是，则待识别钞票为重钞（105），若否，则待识别钞票不为重钞（106）。票据重张检测方法解决了钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。

Description

一种票据重张检测方法和装置
本申请要求于2015年9月17日提交中国专利局、申请号为201510594951.0、发明名称为“一种票据重张检测方法和装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及金融设备领域，尤其涉及一种票据重张检测方法和装置。
背景技术
在智能验钞仪、清分机的识别能力中，钞票重张的检测能力是一项重要的技术指标。在钞票清点过程中，钞票重合的情况时有发生，改进硬件结构虽然可以降低重钞出现的概率，但无法根本杜绝重钞情况的发生，因此准确无误的检测出钞票是否重张对钞票识别而言具有重大意义。
目前，一般的钞票重张检测方法为基于厚度信号的检测方法，采用厚度传感器采集过钞通道中的每张钞票的厚度信号，通过判断钞票宽度和整体厚度是否大于给定阈值来判断是否重张，该方法对厚度传感器采集信号的密度和精度要求都很高，当钞票上有附着物(如贴有胶带)或钞票轻微拱起以及旧钞变厚时容易误判为重钞。
发明内容
本发明实施例提供了一种票据重张检测方法和装置，能够解决现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
本发明实施例提供的一种票据重张检测方法，包括：
采集待识别钞票的正面图像和反面图像，以及所述正面图像或反面图像的透射图像；
根据所述正面图像和反面图像分别获取所述待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，所述局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
根据所述局部特征属性窗对所述透射图像进行耦合程度测量，得到测量结果；
判断所述测量结果是否符合预设的重钞条件，若是，则所述待识别钞票为重钞，若否，则所述待识别钞票不为重钞。
可选地，根据所述局部特征属性窗对所述正面图像和所述反面图像的透射图像进行耦合程度测量，得到测量结果的步骤具体包括以下至少一个子步骤：
第一子步骤：
计算所述透射图像在所述局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期，所述色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，所述结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距；
判断所述色调纹理周期和结构纹理周期与所述局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果；
第二子步骤：
获取所述透射图像在所述局部特征属性窗限定下的对应区域的纹理基元，所述纹理基元是指具有特定形状结构的纹理单元；
判断所述纹理基元与所述局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
第三子步骤：
计算所述透射图像在所述局部特征属性窗限定下的对应区域的纹理清晰度量，所述纹理清晰度量是指预设纹理的模糊程度；
判断所述纹理清晰度量与所述局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果。
可选地，判断所述测量结果是否符合预设的重钞条件具体为：
判断是否存在任一判断结果为是。
可选地，所述判断是否存在任一判断结果为是之前还包括：
根据所述正面图像获取所述待识别钞票的正面面值面向信息；
根据所述反面图像获取所述待识别钞票的反面面值面向信息；
根据预设的面值面向规则判断所述正面面值面向信息和所述反面面值面向信息是否不匹配，得到第四判断结果。
可选地，所述判断是否存在任一判断结果为是之前还包括：
根据所述正面图像获取所述待识别钞票的正面图像尺寸；
根据所述反面图像获取所述待识别钞票的反面图像尺寸；
判断所述正面图像尺寸或所述反面图像尺寸是否超出所述待识别钞票的预设标准尺寸范围，得到第五判断结果。
可选地，所述判断是否存在任一判断结果为是之前还包括：
根据所述正面图像获取所述待识别钞票的正面透光度量；
根据所述反面图像获取所述待识别钞票的反面透光度量；
判断所述正面透光度量或所述反面透光度量是否超出所述待识别钞票的预设标准透光度量范围，得到第六判断结果。
本发明实施例提供的一种票据重张检测装置，包括：
正反面采集模块，用于采集待识别钞票的正面图像和反面图像；
钞票信息获取模块，用于根据所述正面图像和反面图像分别获取所述待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，所述局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
耦合程度测量模块，用于根据所述局部特征属性窗对所述正面图像和所述反面图像的透射图像进行耦合程度测量，得到测量结果；
重钞判断模块，用于判断所述测量结果是否符合预设的重钞条件；
重钞模块，用于当所述重钞判断模块的判断结果为是时，确定所述待识别钞票为重钞；
非重钞模块，用于当所述重钞判断模块的判断结果为否时，确定所述待识别钞票不为重钞。
可选地，所述耦合程度测量模块具体包括以下至少一个子模块：
第一子模块：
色调和结构纹理单元，用于计算所述透射图像在所述局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期，所述色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，所述结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距；
第一判断单元，用于判断所述色调纹理周期和结构纹理周期与所述局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一 判断结果；
第二子模块：
纹理基元获取单元，用于获取所述透射图像在所述局部特征属性窗限定下的对应区域的纹理基元，所述纹理基元是指具有特定形状结构的纹理单元；
第二判断单元，用于判断所述纹理基元与所述局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
第三子模块：
纹理清晰度量获取单元，用于计算所述透射图像在所述局部特征属性窗限定下的对应区域的纹理清晰度量，所述纹理清晰度量是指预设纹理的模糊程度；
第三判断单元，用于判断所述纹理清晰度量与所述局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果；
可选地，所述重钞判断模块包括：
重钞判断单元，用于判断是否存在任一判断结果为是。
可选地，所述装置还包括以下至少一个模块组：
第一模块组：
正面信息模块，用于根据所述正面图像获取所述待识别钞票的正面面值面向信息；
反面信息模块，用于根据所述反面图像获取所述待识别钞票的反面面值面向信息；
面值面向判断模块，用于根据预设的面值面向规则判断所述正面面值面向信息和所述反面面值面向信息是否不匹配，得到第四判断结果；
第二模块组：
正面尺寸模块，用于根据所述正面图像获取所述待识别钞票的正面图像尺寸；
反面尺寸模块，用于根据所述反面图像获取所述待识别钞票的反面图像尺寸；
图像尺寸判断模块，用于判断所述正面图像尺寸或所述反面图像尺寸是否超出所述待识别钞票的预设标准尺寸范围，得到第五判断结果；
第三模块组：
正面透光度量模块，用于根据所述正面图像获取所述待识别钞票的正面透光度量；
反面透光度量模块，用于根据所述反面图像获取所述待识别钞票的反面透光度量；
透光度量判断模块，用于判断所述正面透光度量或所述反面透光度量是否超出所述待识别钞票的预设标准透光度量范围，得到第六判断结果。
从以上技术方案可以看出，本发明实施例具有以下优点：
本发明实施例中，一种票据重张检测方法通过对待识别钞票的正面图像或反面图像的透射图像作耦合程度检测，并根据测量结果判断该待识别钞票是否为重钞，解决了现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
附图说明
图1为本发明实施例中一种票据重张检测方法一个实施例流程图；
图2为本发明实施例中一种票据重张检测方法另一个实施例流程图；
图3a和图3b为本发明实施例中一种正确的面值面向组合示意图；
图4a和图4b为本发明实施例中一种重钞面值面向组合示意图；
图5a和图5b为本发明实施例中一种重钞面值面向组合示意图；
图6a和图6b为本发明实施例中一种重钞尺寸示意图；
图7为本发明实施例中一种色调纹理周期对比示意图；
图8a和图8b为本发明实施例中一种结构纹理周期对比示意图；
图9a和图9b为本发明实施例中一种纹理基元对比示意图；
图10a和图10b为本发明实施例中一种纹理清晰度对比示意图；
图11为本发明实施例中一种票据重张检测装置一个实施例结构图；
图12为本发明实施例中一种票据重张检测装置另一个实施例结构图。
具体实施方式
本发明实施例提供了一种票据重张检测方法和装置，用于解决现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
为使得本发明的发明目的、特征、优点能够更加的明显和易懂，下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，下面所描述的实施例仅仅是本发明一部分实施例，而非全部的实施例。基于本发明中的实施例，本领域普通技术人员在没有做出创造性劳动前提下所获得的所有其它实施例，都属于本发明保护的范围。
请参阅图1，本发明实施例中一种票据重张检测方法一个实施例包括：
101、采集待识别钞票的正面图像和反面图像，以及该正面图像或反面图像的透射图像；
首先，可以采集待识别钞票的正面图像和反面图像，以及该正面图像或反面图像的透射图像。
102、根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗；
在采集待识别钞票的正面图像和反面图像之后，可以根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板。
103、根据该局部特征属性窗对该透射图像进行耦合程度测量，得到测量结果；
在初始化对应的局部特征属性窗之后，可以根据该局部特征属性窗对该正面图像或该反面图像的透射图像进行耦合程度测量，得到测量结果。
104、判断该测量结果是否符合预设的重钞条件，若是，则执行步骤105，若否，则执行步骤106；
在得到测量结果之后，可以判断该测量结果是否符合预设的重钞条件，若是，则执行步骤105，若否，则执行步骤106。
105、该待识别钞票为重钞；
若该测量结果符合预设的重钞条件，则可以认为该待识别钞票为重钞。
106、该待识别钞票不为重钞。
若该测量结果不符合预设的重钞条件，则可以认为该待识别钞票不为重钞。
本实施例中，前面所说的一种票据重张检测方法步骤为：首先，采集 待识别钞票的正面图像和反面图像，以及该正面图像或反面图像的透射图像；然后，根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；再之，根据该局部特征属性窗对该透射图像进行耦合程度测量，得到测量结果；最后，判断该测量结果是否符合预设的重钞条件，若是，则该待识别钞票为重钞，若否，则该待识别钞票不为重钞。在本实施例中，一种票据重张检测方法通过对待识别钞票的正面图像或反面图像的透射图像作耦合程度检测，并根据测量结果判断该待识别钞票是否为重钞，解决了现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
为便于理解，下面对本发明实施例中的一种票据重张检测方法进行详细描述，请参阅图2，本发明实施例中一种票据重张检测方法另一个实施例包括：
201、采集待识别钞票的正面图像和反面图像，以及该正面图像或反面图像的透射图像；
首先，需要采集待识别钞票的正面图像和反面图像，以及该正面图像或反面图像的透射图像。
202、根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗；
在采集待识别钞票的正面图像和反面图像之后，可以根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板。
可以理解的是，局部特征属性窗是预先定义的，根据的不同的钞票对应不同的局部特征属性窗。该局部特征属性窗主要用于在钞票图像上快速定位需要采集特定特征信息的对应区域。因此，本实施例中可以通过获取正面图像和反面图像的正面钞票信息和反面钞票信息，比如该钞票信息为面值，则可以获取到该正面图像对应的局部特征属性窗，以及获取到该反面图像对应的局部特征属性窗，并对这些局部特征属性窗进行初始化。
203、计算该正面图像或反面图像的透射图像在该局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期；
在初始化对应的局部特征属性窗之后，可以计算该正面图像或反面图像的透射图像在该局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期。可以理解的是，该色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，如图7所示，字母R/G/B分别代表纹理颜色，色调周期纹理个数为3，周期数目为1，周期间距为T。而该结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距，如图8a所示，结构纹理个数为2，周期数目分别为3和9，周期间距分别为T1和T2。
需要说明的是，对于钞票来说，由于印刷精度、介质尺寸差异以及运动等因素影响，两张钞票不可能无缝融合。因此可以通过判断其色调纹理周期和结构纹理周期与标准值的差异来判断该待识别钞票是否为重钞，详细见步骤204。
204、判断该色调纹理周期和结构纹理周期与该局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果；
在计算该正面图像或反面图像的透射图像在该局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期之后，可以判断该色调纹理周期和结构纹理周期与该局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果。
可以理解的是，该局部特征属性窗对应的标准值为预先设置，该标准值即对应的色调纹理周期和结构纹理周期的标准数值。通过计算得到的色调纹理周期和结构纹理周期与标准值的差值，如果该差值超过预设的第一阈值，则可以认为该待识别图像的色调纹理周期和结构纹理周期不在正常范围内，则该待识别图像为重钞。例如，图8a为标准纹理，图8b为两张钞票重合时出现的纹理，可见其周期与标准值差异较大。
205、获取该透射图像在该局部特征属性窗限定下的对应区域的纹理基元；
在初始化对应的局部特征属性窗之后，可以获取该透射图像在该局部特征属性窗限定下的对应区域的纹理基元。该纹理基元是指具有特定形状结构的纹理单元，如图9a所示。可以理解的是，在局部特征属性窗的帮助 下，可以轻易地从透射图像上获取到对应区域上的纹理基元。
206、判断该纹理基元与该局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
在获取该透射图像在该局部特征属性窗限定下的对应区域的纹理基元之后，可以判断该纹理基元与该局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果。
可以理解的是，该局部特征属性窗对应的标准纹理基元为预先设置，该标准纹理基元即对应的纹理基元的标准模板(或数值)，通过对比纹理基元和标准纹理基元之间的差异，如果该差异超过预设的第二阈值，可以认为该待识别图像的纹理基元不在正常范围内，则该待识别图像为重钞。例如，图9a为准纹理模板，出现重张时，透射图像中出现的纹理基元可能变成图9b中所示情况。
207、计算该透射图像在该局部特征属性窗限定下的对应区域的纹理清晰度量；
在初始化对应的局部特征属性窗之后，可以计算该透射图像在该局部特征属性窗限定下的对应区域的纹理清晰度量。该纹理清晰度量是指预设纹理的模糊程度，如图10a所示。可以理解的是，模糊程度越高，重钞的可能性越高；反之，模糊程度越低，重钞的可能性越低。
208、判断该纹理清晰度量与该局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果；
在计算该透射图像在该局部特征属性窗限定下的对应区域的纹理清晰度量之后，可以判断该纹理清晰度量与该局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果。
可以理解的是，该局部特征属性窗对应的标准度量值为预先设置，该标准度量值即对应的纹理清晰度量的标准数值，通过计算得到的纹理清晰度量与标准度量值之间的差值，如果该差值超过预设的第三阈值，则可以认为该待识别图像的该待识别图像的不在正常范围内，则该待识别图像为重钞。例如，图10a中纹理清晰，而图10b所示的重钞中则纹理模糊。
209、根据该正面图像获取该待识别钞票的正面面值面向信息；
在采集得到该正面图像之后，可以根据该正面图像获取该待识别钞票 的正面面值面向信息。需要说明的是，该正面面值面向信息包括了该正面图像的面值和面向。其中，面值指的是钞票的币值，而面向指的是正面图像成像时该待识别钞票的正面的朝向(正向放置或者颠倒放置)。
210、根据该反面图像获取该待识别钞票的反面面值面向信息；
同理，在采集得到该正面图像之后，可以根据该反面图像获取该待识别钞票的反面面值面向信息。
211、根据预设的面值面向规则判断该正面面值面向信息和该反面面值面向信息是否不匹配，得到第四判断结果；
在获取到该正面面值面向信息和该反面面值面向信息之后，可以根据预设的面值面向规则判断该正面面值面向信息和该反面面值面向信息是否不匹配，得到第四判断结果。可以理解的是，若该正面面值面向信息和该反面面值面向信息无法按照先验知识配对，则可以认为该待识别钞票为重钞。如图3a和图3b所示为正确组合，若出现图4a和图4b、图5a和图5b类似组合则无法匹配。
212、根据该正面图像获取该待识别钞票的正面图像尺寸；
在采集得到该正面图像之后，可以根据该正面图像获取该待识别钞票的正面图像尺寸。
213、根据该反面图像获取该待识别钞票的反面图像尺寸；
在采集得到该正面图像之后，可以根据该反面图像获取该待识别钞票的反面图像尺寸。
214、判断该正面图像尺寸或该反面图像尺寸是否超出该待识别钞票的预设标准尺寸范围，得到第五判断结果。
在获取到该正面图像尺寸和该反面图像尺寸之后，可以判断该正面图像尺寸或该反面图像尺寸是否超出该待识别钞票的预设标准尺寸范围，得到第五判断结果。该正面图像尺寸和该反面图像尺寸所指的尺寸包括图像的高度信息以及图像的宽度信息。可以理解的是，如图6a和图6b所示，当两张钞票重钞，即错位黏在一起时，所获取到的钞票尺寸会超出预设的标准尺寸范围。
215、根据该正面图像获取该待识别钞票的正面透光度量；
在采集得到该正面图像之后，可以根据该正面图像获取该待识别钞票 的正面透光度量。
216、根据该反面图像获取该待识别钞票的反面透光度量；
在采集得到该正面图像之后，可以根据该反面图像获取该待识别钞票的反面透光度量。
217、判断该正面透光度量或该反面透光度量是否超出该待识别钞票的预设标准透光度量范围，得到第六判断结果；
在获取到该正面透光度量和该反面透光度量之后，可以判断该正面透光度量或该反面透光度量是否超出该待识别钞票的预设标准透光度量范围，得到第六判断结果。
需要说明的是，透光度量包括该图像的反射图像灰度均值Gf、透射图像灰度均值Gt以及反射图像与透射图像灰度相关性Rft，Rft可表示为Gf与Gt的组合，如式(1)所示；该Gf和Gt可以是整幅图像的灰度均值也可以是局部区域的均值。例如，重张时水印区域灰度均值将接近最大值，高出正常时刻几十个灰度等级。若所得透光度量超出该待识别钞票的预设标准透光度量范围，则可以认为该待识别钞票为重钞。其中，标准透光度量范围为预设的该待识别钞票透光度量的标准范围。
Rft＝α(Gf/Gt)+β(Gf±Gt)；(α∈R,β∈R)         (1)
式中α，β表示权重参数，R表示实数域。
218、判断是否存在任一判断结果为是，若是，则执行步骤219，若否，则执行步骤220；
在得到上述的第一判断结果、第二判断结果、第三判断结果、第四判断结果、第五判断结果或者第六判断结果之后，可以判断是否存在任一判断结果为是，若是，则执行步骤219，若否，则执行步骤220。也即，只要上述的第一判断结果、第二判断结果、第三判断结果、第四判断结果、第五判断结果或者第六判断结果中存在一个判断结果为是，则可以认为该待识别钞票为重钞；若均不存在为否的判断结果，则可以认为该待识别钞票不为重钞。
219、该待识别钞票为重钞；
若上述的第一判断结果、第二判断结果、第三判断结果、第四判断结果、第五判断结果或者第六判断结果中存在一个判断结果为是，则该待识 别钞票为重钞。
220、该待识别钞票不为重钞。
若上述的第一判断结果、第二判断结果、第三判断结果、第四判断结果、第五判断结果和第六判断结果中均不存在为否的判断结果，则该待识别钞票不为重钞。
需要说明的是，上述步骤203至204为获取第一判断结果、上述步骤205至206为获取第二判断结果、上述步骤207至208为获取第三判断结果、上述步骤209至211为获取第四判断结果、上述步骤212至214为获取第五判断结果、以及上述步骤215至217为获取第三判断结果，可以以此分为六个模块。这六个模块之间可以相互组合，也可以单独使用，均可实现票据的重张检测。并且，这六个模块共同组合使用时，六个模块之间的顺序可以任意排列组合，不影响重张检测的结果。
本实施例中，一种票据重张检测方法通过对待识别钞票的正面图像或反面图像的透射图像作耦合程度检测，并根据测量结果判断该待识别钞票是否为重钞，解决了现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
上面主要描述了一种票据重张检测方法，下面将对一种票据重张检测装置进行详细的描述，请参阅图11，本发明实施例中一种票据重张检测装置一个实施例包括：
正反面采集模块111，用于采集待识别钞票的正面图像和反面图像；
钞票信息获取模块112，用于根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
耦合程度测量模块113，用于根据该局部特征属性窗对该正面图像和该反面图像的透射图像进行耦合程度测量，得到测量结果；
重钞判断模块114，用于判断该测量结果是否符合预设的重钞条件；
重钞模块115，用于当该重钞判断模块114的判断结果为是时，确定该待识别钞票为重钞；
非重钞模块116，用于当该重钞判断模块114的判断结果为否时，确 定该待识别钞票不为重钞。
本实施例中，正反面采集模块111采集待识别钞票的正面图像和反面图像；钞票信息获取模块112根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；耦合程度测量模块113根据该局部特征属性窗对该正面图像和该反面图像的透射图像进行耦合程度测量，得到测量结果；重钞判断模块114判断该测量结果是否符合预设的重钞条件；当该重钞判断模块114的判断结果为是时，重钞模块115确定该待识别钞票为重钞；当该重钞判断模块114的判断结果为否时，非重钞模块116确定该待识别钞票不为重钞。在本实施例中，一种票据重张检测装置通过对待识别钞票的正面图像或反面图像的透射图像作耦合程度检测，并根据测量结果判断该待识别钞票是否为重钞，解决了现有重张检测方法钞票上有附着物、钞票轻微拱起以及旧钞变厚等情况下容易造成误判的问题。
为便于理解，下面对本发明实施例中的一种票据重张检测装置进行详细描述，请参阅图12，本发明实施例中一种票据重张检测装置另一个实施例包括：
正反面采集模块121，用于采集待识别钞票的正面图像和反面图像；
钞票信息获取模块122，用于根据该正面图像和反面图像分别获取该待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，该局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
耦合程度测量模块123，用于根据该局部特征属性窗对该正面图像和该反面图像的透射图像进行耦合程度测量，得到测量结果；
重钞判断模块124，用于判断该测量结果是否符合预设的重钞条件；
重钞模块125，用于当该重钞判断模块124的判断结果为是时，确定该待识别钞票为重钞；
非重钞模块126，用于当该重钞判断模块124的判断结果为否时，确定该待识别钞票不为重钞。
本实施例中该耦合程度测量模块123具体可以包括：
色调和结构纹理单元1231，用于计算该透射图像在该局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期，该色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，该结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距；
第一判断单元1232，用于判断该色调纹理周期和结构纹理周期与该局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果；
或者
纹理基元获取单元1233，用于获取该透射图像在该局部特征属性窗限定下的对应区域的纹理基元，该纹理基元是指具有特定形状结构的纹理单元；
第二判断单元1234，用于判断该纹理基元与该局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
或者
纹理清晰度量获取单元1235，用于计算该透射图像在该局部特征属性窗限定下的对应区域的纹理清晰度量，该纹理清晰度量是指预设纹理的模糊程度；
第三判断单元1236，用于判断该纹理清晰度量与该局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果；
本实施例中该重钞判断模块124可以包括：
重钞判断单元1241，用于判断是否存在任一判断结果为是。
本实施例中该票据重张检测装置还可以包括：
正面信息模块127，用于根据该正面图像获取该待识别钞票的正面面值面向信息；
反面信息模块128，用于根据该反面图像获取该待识别钞票的反面面值面向信息；
面值面向判断模块129，用于根据预设的面值面向规则判断该正面面值面向信息和该反面面值面向信息是否不匹配，得到第四判断结果；
或者
正面尺寸模块130，用于根据该正面图像获取该待识别钞票的正面图 像尺寸；
反面尺寸模块131，用于根据该反面图像获取该待识别钞票的反面图像尺寸；
图像尺寸判断模块132，用于判断该正面图像尺寸或该反面图像尺寸是否超出该待识别钞票的预设标准尺寸范围，得到第五判断结果；
或者
正面透光度量模块133，用于根据该正面图像获取该待识别钞票的正面透光度量；
反面透光度量模块134，用于根据该反面图像获取该待识别钞票的反面透光度量；
透光度量判断模块135，用于判断该正面透光度量或该反面透光度量是否超出该待识别钞票的预设标准透光度量范围，得到第六判断结果。
需要说明的是，上述单元1231和1232为获取第一判断结果、上述单元1233和1234为获取第二判断结果、上述单元1235和1236为获取第三判断结果、上述模块127、128和129为获取第四判断结果、上述模块130、131和132为获取第五判断结果、以及上述模块133、134和135为获取第三判断结果，可以以此分为六大块。这六大块之间可以相互组合，也可以单独使用，均可实现票据的重张检测。并且，这六大块共同组合使用时，六大块之间的顺序可以任意排列组合，不影响重张检测的结果。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性，机械或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的， 作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本发明各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明的技术方案本质上或者说对现有技术做出贡献的部分或者该技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本发明各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。
以上所述，以上实施例仅用以说明本发明的技术方案，而非对其限制；尽管参照前述实施例对本发明进行了详细的说明，本领域的普通技术人员应当理解：其依然可以对前述各实施例所记载的技术方案进行修改，或者对其中部分技术特征进行等同替换；而这些修改或者替换，并不使相应技术方案的本质脱离本发明各实施例技术方案的精神和范围。

Claims (10)

  1. 一种票据重张检测方法，其特征在于，包括：
    采集待识别钞票的正面图像和反面图像，以及所述正面图像或反面图像的透射图像；
    根据所述正面图像和反面图像分别获取所述待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，所述局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
    根据所述局部特征属性窗对所述透射图像进行耦合程度测量，得到测量结果；
    判断所述测量结果是否符合预设的重钞条件，若是，则所述待识别钞票为重钞，若否，则所述待识别钞票不为重钞。
  2. 根据权利要求1所述的方法，其特征在于，根据所述局部特征属性窗对所述正面图像和所述反面图像的透射图像进行耦合程度测量，得到测量结果的步骤具体包括以下至少一个子步骤：
    第一子步骤：
    计算所述透射图像在所述局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期，所述色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，所述结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距；
    判断所述色调纹理周期和结构纹理周期与所述局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果；
    第二子步骤：
    获取所述透射图像在所述局部特征属性窗限定下的对应区域的纹理基元，所述纹理基元是指具有特定形状结构的纹理单元；
    判断所述纹理基元与所述局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
    第三子步骤：
    计算所述透射图像在所述局部特征属性窗限定下的对应区域的纹理清晰度量，所述纹理清晰度量是指预设纹理的模糊程度；
    判断所述纹理清晰度量与所述局部特征属性窗对应的预置标准度量值 的差值是否超过预设第三阈值，得到第三判断结果。
  3. 根据权利要求2所述的方法，其特征在于，判断所述测量结果是否符合预设的重钞条件具体为：
    判断是否存在任一判断结果为是。
  4. 根据权利要求3所述的方法，其特征在于，所述判断是否存在任一判断结果为是之前还包括：
    根据所述正面图像获取所述待识别钞票的正面面值面向信息；
    根据所述反面图像获取所述待识别钞票的反面面值面向信息；
    根据预设的面值面向规则判断所述正面面值面向信息和所述反面面值面向信息是否不匹配，得到第四判断结果。
  5. 根据权利要求3所述的方法，其特征在于，所述判断是否存在任一判断结果为是之前还包括：
    根据所述正面图像获取所述待识别钞票的正面图像尺寸；
    根据所述反面图像获取所述待识别钞票的反面图像尺寸；
    判断所述正面图像尺寸或所述反面图像尺寸是否超出所述待识别钞票的预设标准尺寸范围，得到第五判断结果。
  6. 根据权利要求3所述的方法，其特征在于，所述判断是否存在任一判断结果为是之前还包括：
    根据所述正面图像获取所述待识别钞票的正面透光度量；
    根据所述反面图像获取所述待识别钞票的反面透光度量；
    判断所述正面透光度量或所述反面透光度量是否超出所述待识别钞票的预设标准透光度量范围，得到第六判断结果。
  7. 一种票据重张检测装置，其特征在于，包括：
    正反面采集模块，用于采集待识别钞票的正面图像和反面图像；
    钞票信息获取模块，用于根据所述正面图像和反面图像分别获取所述待识别钞票的正面钞票信息和反面钞票信息，并初始化对应的局部特征属性窗，所述局部特征属性窗为包含所需识别图像的对应特征属性的预设识别区域的模板；
    耦合程度测量模块，用于根据所述局部特征属性窗对所述正面图像和所述反面图像的透射图像进行耦合程度测量，得到测量结果；
    重钞判断模块，用于判断所述测量结果是否符合预设的重钞条件；
    重钞模块，用于当所述重钞判断模块的判断结果为是时，确定所述待识别钞票为重钞；
    非重钞模块，用于当所述重钞判断模块的判断结果为否时，确定所述待识别钞票不为重钞。
  8. 根据权利要求7所述的装置，其特征在于，所述耦合程度测量模块具体包括以下至少一个子模块：
    第一子模块：
    色调和结构纹理单元，用于计算所述透射图像在所述局部特征属性窗限定下的对应区域的色调纹理周期和结构纹理周期，所述色调纹理周期包括周期性彩色纹理的个数、周期数目和周期间距，所述结构纹理周期包括周期性结构纹理特征的个数、周期数目和周期间距；
    第一判断单元，用于判断所述色调纹理周期和结构纹理周期与所述局部特征属性窗对应的预置标准值的差值是否超过预设第一阈值，得到第一判断结果；
    第二子模块：
    纹理基元获取单元，用于获取所述透射图像在所述局部特征属性窗限定下的对应区域的纹理基元，所述纹理基元是指具有特定形状结构的纹理单元；
    第二判断单元，用于判断所述纹理基元与所述局部特征属性窗对应的预置标准纹理基元的差异是否超过预设第二阈值，得到第二判断结果；
    第三子模块：
    纹理清晰度量获取单元，用于计算所述透射图像在所述局部特征属性窗限定下的对应区域的纹理清晰度量，所述纹理清晰度量是指预设纹理的模糊程度；
    第三判断单元，用于判断所述纹理清晰度量与所述局部特征属性窗对应的预置标准度量值的差值是否超过预设第三阈值，得到第三判断结果；
  9. 根据权利要求8所述的装置，其特征在于，所述重钞判断模块包括：
    重钞判断单元，用于判断是否存在任一判断结果为是。
  10. 根据权利要求9所述的装置，其特征在于，所述装置还包括以下 至少一个模块组：
    第一模块组：
    正面信息模块，用于根据所述正面图像获取所述待识别钞票的正面面值面向信息；
    反面信息模块，用于根据所述反面图像获取所述待识别钞票的反面面值面向信息；
    面值面向判断模块，用于根据预设的面值面向规则判断所述正面面值面向信息和所述反面面值面向信息是否不匹配，得到第四判断结果；
    第二模块组：
    正面尺寸模块，用于根据所述正面图像获取所述待识别钞票的正面图像尺寸；
    反面尺寸模块，用于根据所述反面图像获取所述待识别钞票的反面图像尺寸；
    图像尺寸判断模块，用于判断所述正面图像尺寸或所述反面图像尺寸是否超出所述待识别钞票的预设标准尺寸范围，得到第五判断结果；
    第三模块组：
    正面透光度量模块，用于根据所述正面图像获取所述待识别钞票的正面透光度量；
    反面透光度量模块，用于根据所述反面图像获取所述待识别钞票的反面透光度量；
    透光度量判断模块，用于判断所述正面透光度量或所述反面透光度量是否超出所述待识别钞票的预设标准透光度量范围，得到第六判断结果。
PCT/CN2016/080650 2015-09-17 2016-04-29 一种票据重张检测方法和装置 Ceased WO2017045403A1 (zh)

Priority Applications (5)

Application Number Priority Date Filing Date Title
US15/757,971 US20180204405A1 (en) 2015-09-17 2016-04-29 Detection method and apparatus for overlapped notes
RU2018112269A RU2688306C1 (ru) 2015-09-17 2016-04-29 Способ и устройство обнаружения для наслоившихся друг на друга банкнот
EP16845517.8A EP3352146B1 (en) 2015-09-17 2016-04-29 Detection method and apparatus for overlapped notes
ES16845517T ES2944570T3 (es) 2015-09-17 2016-04-29 Método y aparato de detección de billetes superpuestos
ZA2018/02074A ZA201802074B (en) 2015-09-17 2018-03-28 Detection method and apparatus for overlapped notes

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201510594951.0 2015-09-17
CN201510594951.0A CN105069901B (zh) 2015-09-17 2015-09-17 一种票据重张检测方法和装置

Publications (1)

Publication Number Publication Date
WO2017045403A1 true WO2017045403A1 (zh) 2017-03-23

Family

ID=54499257

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/080650 Ceased WO2017045403A1 (zh) 2015-09-17 2016-04-29 一种票据重张检测方法和装置

Country Status (9)

Country Link
US (1) US20180204405A1 (zh)
EP (1) EP3352146B1 (zh)
CN (1) CN105069901B (zh)
CL (1) CL2018000682A1 (zh)
ES (1) ES2944570T3 (zh)
PT (1) PT3352146T (zh)
RU (1) RU2688306C1 (zh)
WO (1) WO2017045403A1 (zh)
ZA (1) ZA201802074B (zh)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105069901B (zh) * 2015-09-17 2017-10-31 广州广电运通金融电子股份有限公司 一种票据重张检测方法和装置
CN107067540B (zh) * 2017-03-21 2019-07-09 深圳怡化电脑股份有限公司 一种纸张重张的检测方法及装置
CN109741516A (zh) * 2018-12-20 2019-05-10 恒银金融科技股份有限公司 一种钞票厚度检验方法
CN111666886A (zh) * 2020-06-08 2020-09-15 成都知识视觉科技有限公司 一种医疗单证结构化知识提取的图像预处理方法
CN114120518B (zh) * 2021-11-26 2024-02-02 深圳怡化电脑股份有限公司 纸币连张检测方法、装置、电子设备及存储介质
CN117058805A (zh) * 2023-07-06 2023-11-14 中银金融科技有限公司 纸币图像处理方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2004352399A (ja) * 2003-05-27 2004-12-16 Canon Electronics Inc 重送シート検知装置及び該装置を備えた画像読取装置
JP2005231903A (ja) * 1994-10-05 2005-09-02 Musashi:Kk ２枚ずれシート判定方法及びシート枚数計数装置
US20090121163A1 (en) * 2005-10-12 2009-05-14 Siemens Aktiengesellschaft Apparatus and method for detecting overlapping mail items
CN101661645A (zh) * 2008-08-28 2010-03-03 富士通先端科技株式会社 纸页类处理装置、纸页类处理方法及纸页类处理程序
KR20100060996A (ko) * 2008-11-28 2010-06-07 엘지엔시스(주) 매체 겹침 검지 장치 및 그 방법
CN102456246A (zh) * 2010-10-19 2012-05-16 山东新北洋信息技术股份有限公司 纸币重张的检测方法及装置、自助终端
CN105069901A (zh) * 2015-09-17 2015-11-18 广州广电运通金融电子股份有限公司 一种票据重张检测方法和装置

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE2936573A1 (de) * 1978-09-15 1980-03-27 De La Rue Crosfield Blattzaehlverfahren und -vorrichtung
US6573983B1 (en) * 1996-11-15 2003-06-03 Diebold, Incorporated Apparatus and method for processing bank notes and other documents in an automated banking machine
GB0106288D0 (en) * 2001-03-14 2001-05-02 Rue De Int Ltd Item handling apparatus and method
JP3693993B2 (ja) * 2002-01-28 2005-09-14 日立オムロンターミナルソリューションズ株式会社 紙葉類確定装置
DE102005009332B4 (de) * 2005-03-01 2014-02-13 Giesecke & Devrient Gmbh Vorrichtung für die Überprüfung der Vereinzelung von Banknoten
US7706593B2 (en) * 2006-09-20 2010-04-27 Primax Electronics Ltd. Verification method for determining areas within an image corresponding to monetary banknotes
JP2008100783A (ja) * 2006-10-17 2008-05-01 Canon Electronics Inc シート状部材重送検知装置
EP2246825B1 (en) * 2009-04-28 2014-10-08 Banqit AB Method for a banknote detector device, and a banknote detector device
KR101387271B1 (ko) * 2009-12-21 2014-04-21 가부시끼가이샤 도시바 지엽류 처리 장치
CN102903172B (zh) * 2012-09-26 2015-04-01 深圳怡化电脑股份有限公司 一种纸币重张和连张的检测方法和检测装置
CN104390611A (zh) * 2014-11-11 2015-03-04 哈尔滨市君诚信电子有限公司 一种超声波纸张检测系统及其检测方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2005231903A (ja) * 1994-10-05 2005-09-02 Musashi:Kk ２枚ずれシート判定方法及びシート枚数計数装置
JP2004352399A (ja) * 2003-05-27 2004-12-16 Canon Electronics Inc 重送シート検知装置及び該装置を備えた画像読取装置
US20090121163A1 (en) * 2005-10-12 2009-05-14 Siemens Aktiengesellschaft Apparatus and method for detecting overlapping mail items
CN101661645A (zh) * 2008-08-28 2010-03-03 富士通先端科技株式会社 纸页类处理装置、纸页类处理方法及纸页类处理程序
KR20100060996A (ko) * 2008-11-28 2010-06-07 엘지엔시스(주) 매체 겹침 검지 장치 및 그 방법
CN102456246A (zh) * 2010-10-19 2012-05-16 山东新北洋信息技术股份有限公司 纸币重张的检测方法及装置、自助终端
CN105069901A (zh) * 2015-09-17 2015-11-18 广州广电运通金融电子股份有限公司 一种票据重张检测方法和装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3352146A4 *

Also Published As

Publication number Publication date
CN105069901A (zh) 2015-11-18
EP3352146B1 (en) 2023-04-26
EP3352146A1 (en) 2018-07-25
CL2018000682A1 (es) 2018-09-14
EP3352146A4 (en) 2018-10-10
US20180204405A1 (en) 2018-07-19
RU2688306C1 (ru) 2019-05-21
CN105069901B (zh) 2017-10-31
PT3352146T (pt) 2023-05-15
ZA201802074B (en) 2019-01-30
ES2944570T3 (es) 2023-06-22

Similar Documents

Publication Publication Date Title
WO2017045403A1 (zh) 一种票据重张检测方法和装置
CN102682514B (zh) 一种纸类识别方法及相关装置
CN104331978B (zh) 纸币褶皱的识别装置和方法
WO2014173012A1 (zh) 一种金融票据识别模块中积灰检测方法及系统
CN101506851B (zh) 纸张识别装置以及纸张的识别方法
CN106548558B (zh) 一种票据一维信号的检测方法及装置
WO2015032187A1 (zh) 一种纸币处理方法及装置
CN104966349A (zh) 一种基于atm平台的纸币新旧检测方法
CN106875540B (zh) 一种纸币厚度异常检测方法及装置
CN106558143B (zh) 一种100元人民币拼接纸币的识别方法及装置
CN104573647A (zh) 一种非法身份证件的识别方法及装置
CN102004076B (zh) 一种皮棉中异性纤维的检测方法和系统
CN108806058A (zh) 一种纸币检测方法及装置
CN106683261A (zh) 一种纸币的鉴伪方法和装置
CN112257538A (zh) 基于双目深度信息的活体检测方法、设备及存储介质
CN106875543B (zh) 一种基于rgb-d相机的视障人士纸币识别系统及识别方法
CN115330799B (zh) 一种仪表自动化故障诊断方法
WO2015085817A1 (zh) 一种多光谱券类质量检测方法和系统
CN107481391A (zh) 纸币涂鸦的检测方法及装置
CN119152525A (zh) 一种基于ai视觉的透明瓶体曲面印刷图形文字检测系统
CN109858328B (zh) 一种基于视频的人脸识别的方法及装置
CN108932788A (zh) 一种纸币厚度异常等级的检测方法、装置及设备
CN108665604B (zh) 一种纸币新旧等级的检测方法及装置
CN107134046A (zh) 一种纸币厚度异常检测方法及装置
KR100404489B1 (ko) 위조검출방법

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 16845517

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 15757971

Country of ref document: US

NENP Non-entry into the national phase

Ref country code: DE

WWE Wipo information: entry into national phase

Ref document number: 2018112269

Country of ref document: RU

Ref document number: 2016845517

Country of ref document: EP