WO2004032482A1 - 画像読取装置 - Google Patents
画像読取装置 Download PDFInfo
- Publication number
- WO2004032482A1 WO2004032482A1 PCT/JP2003/012313 JP0312313W WO2004032482A1 WO 2004032482 A1 WO2004032482 A1 WO 2004032482A1 JP 0312313 W JP0312313 W JP 0312313W WO 2004032482 A1 WO2004032482 A1 WO 2004032482A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- data
- image
- samples
- reading device
- image reading
- 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
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/387—Composing, repositioning or otherwise geometrically modifying originals
- H04N1/3877—Image rotation
- H04N1/3878—Skew detection or correction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/24—Aligning, centring, orientation detection or correction of the image
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/146—Aligning or centring of the image pick-up or image-field
- G06V30/1475—Inclination or skew detection or correction of characters or of image to be recognised
- G06V30/1478—Inclination or skew detection or correction of characters or of image to be recognised of characters or characters lines
Definitions
- the present invention relates to an image reading apparatus, and more particularly, to an image reading apparatus that detects the inclination of a read color image or multivalued image without deteriorating the quality of the image, and corrects the image.
- an image reading device such as an image scanner
- the read image data is inclined.
- the user does not set the document correctly on the document feeder (ADF)
- the read image data will be inclined.
- Such a state often occurs particularly when, for example, a B5 size document is placed on a so-called A4 size platen or the like, the document is placed obliquely.
- Such tilted image data can be corrected by editing processing such as rotation processing.
- editing processing requires a lot of processing time, and is not suitable for high-speed processing. Therefore, a technique for correcting image data by detecting a tilt (angle) without using such an editing process has been proposed (for example, Japanese Patent Application Laid-Open No. 2002-142024 ( See pages 3 to 12).
- Such conventional detection processing of the inclination of the image data is applicable when the image data is binary data. This is because the skew correction assumes that an image scanner mainly reads a document of characters. In other words, it was included to correct the inclination of the character represented by the binary data and make the output easier to read.
- the image data is (full) color data or multi-valued data (gray scale)
- the image data is once converted to binary data, and then the above-described inclination detection processing of the image data is performed. Had applied.
- color images or multi-valued images In the image after correcting the tilt of the image, due to the conversion of the image de data, for example, like the edge of the figures in the picture becomes jagged, quality of the image was when force s decreases .
- the image to be processed is often a color image including a photograph or the like or a multi-value image. Therefore, the inclination (angle) of a color image or a multi-valued image is detected without using an editing process such as a rotation process that requires a lot of processing time and without deteriorating the quality of a portion such as a photograph. It is hoped that the data will be corrected.
- An object of the present invention is to provide an image reading device that detects the inclination of a read color image or multivalued image and corrects the image without deteriorating the quality of the image. Disclosure of the invention
- the image reading apparatus is configured to obtain moving average data and second derivative data for each of a plurality of samples in the vertical and horizontal directions of reading input image data, each of the plurality of samples being multi-valued data.
- a data calculating unit for calculating; a position detecting unit for detecting first and second positions where a predetermined relationship is established based on the moving average data and the second derivative data for each of the plurality of samples;
- a parallel region determining unit that determines a parallel region based on the first and second positions detected for each of the samples, and a gradient that determines the inclination of four sides of the input image based on the determined parallel region.
- a detection unit; and a tilt correction unit that corrects the input image data based on the detected tilt.
- a parallel region is determined using a plurality of samples composed of multi-valued data, and the inclination of four sides of the image is determined based on the parallel region, and the input image data is corrected. I do.
- the input image data is multi-value data or color data
- the inclination of the image data can be corrected without converting them into binary data. Therefore, it is possible to prevent the image quality from deteriorating due to the conversion of the image data.
- image data read by a color image scanner is subjected to editing processing such as rotation processing that requires a long processing time.
- the tilt can be corrected irrespective of reason and without deteriorating the quality of a portion such as a photograph.
- FIG. 1 is a configuration diagram of the image reading device, and schematically shows the configuration of the image reading device.
- FIG. 2 is a configuration diagram of the image reading device, showing details of the configuration of the image reading device.
- FIG. 3 is an explanatory diagram of an image inclination correction process.
- FIG. 4 is an explanatory diagram of the image inclination correction processing.
- FIG. 5 is an explanatory diagram of the image inclination correction processing.
- FIG. 6 is an explanatory diagram of the image inclination correction processing.
- FIGS. 7 (A), 7 (B), and 7 (C) are explanatory diagrams of the image inclination correction processing.
- FIG. 8 is an explanatory diagram of the image inclination correction processing.
- FIG. 9 is an explanatory diagram of the image inclination correction processing.
- FIGS. 10 (A) and 10 (B) are illustrations for explaining image inclination correction processing.
- FIG. 11 is an image skew correction processing flow, showing the image skew correction processing in the image reading apparatus of the present invention.
- FIG. 1 and 2 are configuration diagrams of an image reading apparatus.
- FIG. 1 schematically shows the configuration of the image reading apparatus of the present invention
- FIG. 2 shows the configuration of the image reading apparatus of FIG. The details are shown below.
- the image data conversion unit 1 processes the input image 100 according to the specified image type.
- the image type is specified accordingly, for example, when the user specifies the reading type as color, multi-valued, or monochrome (binary).
- the image data conversion unit 1 sends the input image 100 to the sample extraction unit 2 as it is.
- the image data conversion unit 1 converts the image data and sends it to the sample extraction unit 2. That is, for example, the full color of 24 bits Generates 8-bit (256 gradation) multi-valued image data based on one image data.
- the input image 100 is converted into multi-valued image data prior to sample extraction.
- the sample extraction unit 2 includes a detection position determination processing unit 21, a one-line extraction processing unit 22 that performs processing in the y direction, and a one-line extraction processing unit 23 that performs processing in the X direction.
- the y direction is the sub-scanning direction and the vertical direction of reading.
- the X direction is the main scanning direction and the horizontal direction of reading.
- FIG. 3 shows a state in which the white paper is read diagonally in the reading area shown in black because the paper is placed diagonally.
- the detection position determination processing unit 21 determines the position where the sample is extracted according to the detection ratio (extraction ratio).
- the sample in the X direction is composed of pixels X0 to xn
- the sample in the y direction is composed of pixels y0 to yn.
- the number of samples (that is,% of the detection ratio) may be increased, but in this case, the processing speed is slightly reduced.
- the number of samples should be reduced, but in this case, the accuracy of tilt detection is slightly reduced.
- the one-line extraction processing unit 22 receives the multi-value image data from the detection position determination processing unit 21.
- a plurality of samples are extracted from the multi-valued image data in the vertical direction (y direction) of reading and sent to the data calculation unit 3.
- the sample consists of data corresponding to one line of the read line (one column of pixels). That is, it is multi-value data obtained from the image data of the one read line of the input image 100.
- the sample extraction position is set to the position of the 20, 40, 60,... Line in accordance with the determination of the detection position determination processing unit 21.
- the one-line extraction processing unit 23 extracts a plurality of samples in the horizontal scanning direction (X direction) from the multi-value image data.
- X direction horizontal scanning direction
- the data calculation unit 3 includes a second derivative processing unit 31 and a moving average generation processing unit 32.
- the second derivative processing unit 31 calculates second derivative data for each of the vertical and horizontal samples and detects the position.
- Send to Part 4 the moving average generation processing unit 32 calculates moving average data for each of the vertical and horizontal samples, and performs position detection.
- Curve A is the moving average data Av en
- Curve B is the two data in which the second derivative data (Curve C) is the maximum of the data obtained by inverting the polarity of the moving average data Av en.
- the data between the points between the points is replaced with the moving average data AV en at the point where the second derivative data (curve C) is maximal.
- the value of the value a of en is reversed.
- the curve C is the second derivative data. It is. Note that the data of the curve B is data that does not actually exist as data based on the read data. This is the data generated for
- FIG. 4 corresponds to, for example, the left part of the extracted sample in the X direction in FIG.
- the moving average data A ven (curve A)
- the paper since the paper (the white portion) is placed diagonally, there is no paper at first, so the area where the pixel value is almost 0 continues, At the edge of, the pixel value rises sharply to a value of about 23.5 (thus, it is not completely white paper).
- the second derivative data (curve B) changes as the pixel value changes as shown in the figure, and a similar curve is obtained in the y direction (same in FIGS. 5 and 6). .
- FIG. 5 corresponds to, for example, the right part of the extracted sample in the X direction in FIG.
- FIG. 6 is a diagram schematically showing the second derivative data and the moving average data when the paper is placed obliquely by combining FIGS. 4 and 5. That is, when the paper is placed obliquely, the curve shown in FIG. 6 is always obtained.
- the position detection unit 4 includes an edge detection processing unit 41 and a detected coordinate storage unit 42.
- the edge detection processing unit 41 receives the moving average data and the second derivative data for each of the plurality of samples from the second differentiation processing unit 31 and the moving average generation processing unit 32, Based on this, the first and second positions where these are in a predetermined relationship are detected and sent to the detected coordinate storage unit 42.
- the first and second positions are the edges on both sides of the sheet.
- the edge detection processing unit 41 determines that the point at which the second derivative data is the maximum and which is larger than the moving average data is the first position ⁇ ⁇ and the second position 0 Set to 0. This is called an outside point.
- the position on the side where the pixel value sharply increases is referred to as a first position ⁇
- the position on the side where the pixel value sharply decreases is the second position ⁇ .
- the second derivative data is always maximum and larger than the moving average data. Therefore, the position where the second derivative data is maximal and larger than the moving average data can be considered to be the edge of the paper.
- the edge detection processing unit 41 inverts the polarity of the value of the moving average data at the point where the secondary differential data is minimal and the secondary differential data is maximal. Points that are smaller than the values are defined as a first position ⁇ n and a second position] 3 n. This is called the inside point (the point inside the outside point). At the position where the pixel value suddenly rises or falls, the value of the second derivative data is always minimum and the value of the moving average data at the point where the second derivative data is the maximum is inverted. Become smaller.
- the position where the value of the moving average data at the point where the second derivative data is minimum and the value of the second derivative data is maximum becomes smaller than the value obtained by inverting the polarity of the moving average data is also considered to be the edge of the paper. Good. It should be noted that only the outer point may be obtained and the inner point may not be obtained, or conversely, only the inner point may be obtained and the outer point may not be obtained.
- the detected coordinate storage unit 42 creates a detected coordinate table 4 21 as shown in FIG. 7 (A).
- the detected coordinate table 42 1 stores a unique number assigned to each of a plurality of samples, and outer and inner points detected from the edge detection processing unit 41 for the sample.
- the detected coordinate storage unit 42 stores the outer point and the inner point for all of the plurality of samples, the detected coordinate storage unit 42 notifies the parallel area determination unit 5 of the stored outer and inner points.
- the parallel region determination unit 5 determines a parallel region based on the first and second positions detected for each of the plurality of samples, and as a result, (Position coordinates) to the inclination detection unit 6.
- the parallel area determination unit 5 refers to the detection coordinate table 4 21 and subtracts the first position 0 (the value of the coordinate) from the second position (the value of the coordinate) of the outer point. In this way, the distance between the first and second positions (see FIG. 6) is calculated. Alternatively, the distance between the first and second positions is calculated by subtracting the first position ⁇ ⁇ (the value of the coordinates) from the second position 0 ⁇ (the value of the coordinates) of the inner point. The value of the distance between the first and second positions when the distance becomes substantially constant corresponds to the width of the sheet.
- the width of the paper tends to be calculated wider using the outer point, and the width of the paper tends to be calculated smaller using the inner point. Therefore, the average of the distance between the first and second positions of the outer point and the distance between the first and second positions of the inner point is calculated as the average of the first and second positions of the sample. The distance between them may be used. Which of these is to be used is determined, for example, by a user inputting an instruction from outside the image reading apparatus.
- the parallel region determination unit 5 obtains a distribution (histogram) of the distance between the first and second positions.
- FIG. 8 shows the distribution of the distance between the first and second positions for a plurality of samples in the X direction (lateral direction of reading). In this example, since the distance of many samples is about 238, the distance is distributed around the distance corresponding to about 238 pixels.
- FIG. 9 shows the distribution of the distance between the first and second positions for a plurality of samples in the y-direction (vertical direction of reading). In the case of this example, since the distances of many samples are at positions of about 168, it can be seen that the distances are distributed around the distance corresponding to about 168 pixels.
- the histogram of the distance between the first and second positions usually has a shape that is distributed with a certain width as shown in FIG. 7 (B). Therefore, the parallel area determination unit 5 sets the width of the distribution as the parallel recognition area P. That is, the parallel area is determined.
- the width of the distribution is a width obtained by adding and subtracting a predetermined value to and from the center value of the distribution.
- the parallel region determination unit 5 determines the parallel region in the vertical direction of reading by setting the width of the distribution as the parallel recognition region P based on the distribution. Further, the parallel region determination unit 5 determines the parallel region in the horizontal direction of reading by setting the width of the distribution as the parallel recognition region P based on the distribution.
- the inclination detection unit 6 Upon receiving the determined parallel region from the parallel region determination unit 5, the inclination detection unit 6 calculates the inclination of the four sides of the input image based on the received parallel region.
- the inclination detection unit 6 includes a linear processing unit 61 1 for processing in the y direction, a linear processing unit 62 for processing in the X direction, an intersection coordinate calculation processing unit 63, and an angle calculation processing unit. Consists of six and four.
- the straight line processing unit 61 receives the parallel region in FIG. 7 (C). As shown in (2), a straight line equation for the two sides (left side and right side) in the y direction of the image is obtained.
- the linear processing unit 61 refers to the detection coordinate table 421, and determines in the y direction that the distance between the first and second positions is within the range of the parallel region in the y direction. Extract multiple samples (only). Then, the linear equation processing unit 61 uses the coordinates of the first position of the plurality of samples to obtain a linear equation by a well-known least square method. This is the straight line equation on the left side. In addition, the linear equation processing unit 61 obtains a linear equation using the coordinates of the second positions of the plurality of samples by a well-known least square method. This is the linear equation on the right side.
- the linear expression processing unit 62 converts the linear expression of the two sides (upper side and lower side) in the X direction of the image as shown in FIG. 7 (C).
- the linear processing unit 61 extracts a plurality of samples in the X direction in which the distance between the first and second positions is within the range of the parallel region in the X direction.
- a linear equation on the upper side and a linear equation on the lower side are obtained by the least square method.
- the intersection coordinate calculation processing unit 63 is inclined from the intersection (indicated by a white circle) using the four-sided linear expression from the linear expression processing units 61 and 62. Then, find the four vertices of the image. These can be obtained by solving each simultaneous equation as can be seen from Fig. 7 (C).
- the intersection coordinate calculation processing unit 63 notifies the obtained four vertices to the angle calculation processing unit 64 and the image output unit 8.
- the angle calculation processing unit 64 obtains the distances of the four sides of the image based on the above four vertices, and calculates the inclination correction unit 7, and Although not shown, it is sent to the image output unit 8.
- the slope 0 can be obtained, for example, by obtaining tan 1 ⁇ for the triangle ⁇ .
- Tan- L 0 is obtained by solving each simultaneous equation from the linear equation shown by the dotted line in FIG. 10 (A).
- the straight line equation indicated by the dotted line is obtained from the coordinates of the two vertices included in the triangle T. The same applies to other inclinations.
- the inclination correction unit 7 Upon receiving the detected inclination from the angle calculation processing unit 64, the inclination correction unit 7 corrects the inclination of the input image 100 based on the received inclination, and corrects the inclination as shown in FIG. 10 (B). Obtain the positive image 200. For this reason, although not specifically shown, the tilt correction unit 7 Receives the input image 10 ° before conversion from the data converter 1 and stores it. The inclination of the input image 100 can be corrected by various processes. For example, a well-known rotation process may be used, or a process shown in the above-mentioned Japanese Patent Application Laid-Open No. 2002-142804. The corrected image 200 is stored in a predetermined storage area (not shown).
- FIG. 11 is an image skew correction processing flow, showing the image skew correction processing in the image reading apparatus of the present invention.
- the image data converter 1 checks the image type (Step S 2). If the image type is a color image or a binary image, the input image 100 is converted into multi-valued image data (step S3), and the process proceeds to step S4. If the image type is a multi-valued image, step S3 is omitted.
- the sample extracting unit 2 calculates the following in the vertical direction (y direction) and the horizontal direction (X direction) of reading from the multi-valued image data according to the detection ratio (extraction ratio). Extract a plurality of samples (step S4).
- the data calculation unit 3 calculates second derivative data and moving average data for each of the plurality of samples in the vertical and horizontal directions as shown in FIGS. 4 and 5 (step S5).
- the position detecting section 4 creates a detection coordinate table 4 21 (step S 6), takes out one sample (step S 7), and returns to FIG.
- an outer point (first position ⁇ 0 and second position] 30) where the second derivative data is maximum and larger than the moving average data is detected (step S 8).
- the second derivative data is obtained as shown in FIG. Is smaller than the value obtained by inverting the polarity of the value of the moving average data at the point where the second derivative data is local maximum (the first position
- step S10 0 ct n and the second position] 3 n are detected. Thereafter, the position detector 4 checks whether or not the sample is the last sample (step S11). If it is not the last sample, repeat step S7 and subsequent steps.
- the detection process is started from both the beginning and end of the data string as the sample in step S8, The point at which the secondary differential data is maximal is detected, and both inner points are detected at step S10.
- the detection process is started from the beginning of the sample, the outer point ⁇ is detected, and after step S8, the inner point ⁇ is detected in step S1 ⁇ , and the inner point ⁇ is detected.
- the detection process from the direction is stopped, the detection process is started from the end of the sample, the outer point / 30 is detected, and after the step S8, the inner point / 3 ⁇ is obtained at the step S10. Is detected.
- the parallel region determination unit 5 calculates the distribution (histogram) of the distance between the first and second positions for each of the plurality of samples as shown in FIGS. Then, based on this, a parallel area (parallel recognition area) is determined as shown in FIG. 7 (() (step S12).
- the inclination detection unit 6 calculates a straight line expression on two sides in the y direction (left side and right side) and two sides in the X direction (upper side and lower side) based on the parallel region, as shown in FIG. (Step S13), and using these four-sided linear equations, the four vertices of the image inclined from the intersection are obtained (step S14). Based on the peak of, the inclinations of the four sides of the image are obtained (step S15).
- the inclination of the input image 100 is corrected based on the inclination, as shown in FIG. 10 (A), and the corrected image is corrected as shown in FIG. 10 (B).
- Get 200 step S 16
- the image output unit 8 obtains the four vertices after the capture based on the four vertices and the inclination of the inclined image (step S17), and as shown in FIG. 10 (B).
- a rectangular image determined by the four vertices after the correction is cut out from the corrected image 200, and this is output as the output image 300 (step S18).
- a parallel region is determined using a plurality of samples composed of multi-valued data, and based on the determined parallel region, inclinations of four sides of the image are determined.
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Facsimile Scanning Arrangements (AREA)
- Image Input (AREA)
- Editing Of Facsimile Originals (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
Description
Claims
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| EP03748597A EP1549042A4 (en) | 2002-10-04 | 2003-09-26 | IMAGE READING DEVICE |
| US10/527,984 US7415168B2 (en) | 2002-10-04 | 2003-09-26 | Image reading device |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP2002/292007 | 2002-10-04 | ||
| JP2002292007A JP2004129022A (ja) | 2002-10-04 | 2002-10-04 | 画像読取装置 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| WO2004032482A1 true WO2004032482A1 (ja) | 2004-04-15 |
Family
ID=32063908
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| PCT/JP2003/012313 Ceased WO2004032482A1 (ja) | 2002-10-04 | 2003-09-26 | 画像読取装置 |
Country Status (4)
| Country | Link |
|---|---|
| US (1) | US7415168B2 (ja) |
| EP (1) | EP1549042A4 (ja) |
| JP (1) | JP2004129022A (ja) |
| WO (1) | WO2004032482A1 (ja) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100384210C (zh) * | 2001-09-12 | 2008-04-23 | 精工爱普生株式会社 | 复合打印机及扫描图像复制方法 |
| US7742198B2 (en) * | 2001-09-12 | 2010-06-22 | Seiko Epson Corporation | Image processing apparatus and method |
| WO2006087791A1 (ja) * | 2005-02-17 | 2006-08-24 | Fujitsu Limited | 画像処理方法、画像処理システム、画像処理装置及びコンピュータプログラム |
| JP4784500B2 (ja) * | 2006-12-08 | 2011-10-05 | 日本電気株式会社 | 画像傾き補正装置及び画像傾き補正方法 |
| JP2008252862A (ja) * | 2007-03-05 | 2008-10-16 | Ricoh Co Ltd | 画像処理装置、画像処理方法及び画像処理プログラム |
| US8463074B2 (en) * | 2009-11-11 | 2013-06-11 | General Dynamics Advanced Information Systems | System and method for rotating images |
| JP5567963B2 (ja) * | 2010-09-29 | 2014-08-06 | 富士フイルム株式会社 | 画像処理装置、放射線画像システム、画像処理方法およびプログラム |
| JP2020052916A (ja) * | 2018-09-28 | 2020-04-02 | 日本電産サンキョー株式会社 | 画像処理装置、イメージスキャナ、及び画像処理方法 |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05344318A (ja) * | 1992-06-10 | 1993-12-24 | Canon Inc | 画像入力装置 |
| JPH11252351A (ja) * | 1998-03-02 | 1999-09-17 | Konica Corp | 画像読取装置 |
| JP2000261653A (ja) * | 1999-03-09 | 2000-09-22 | Hitachi Ltd | 画像処理装置 |
| JP2000341501A (ja) * | 1999-03-23 | 2000-12-08 | Minolta Co Ltd | 画像処理装置および画像処理方法、ならびに画像処理プログラムを記録した記録媒体 |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US3920889A (en) * | 1974-12-05 | 1975-11-18 | Bell Telephone Labor Inc | Method and apparatus for crispening video signals by the use of temporal filters |
| JPS63284686A (ja) * | 1987-05-18 | 1988-11-21 | Oki Electric Ind Co Ltd | 画像の境界線検出方式 |
| US5142592A (en) * | 1990-12-17 | 1992-08-25 | Moler Keith E | Method and apparatus for detection of parallel edges in image processing |
| DE4318526C2 (de) | 1992-06-10 | 1999-11-25 | Canon Kk | Bildeingabevorrichtung |
| JPH0737103A (ja) * | 1993-07-23 | 1995-02-07 | Olympus Optical Co Ltd | 傾き角度検出装置 |
| US6384414B1 (en) * | 1997-11-25 | 2002-05-07 | Board Of Regents, The University Of Texas System | Method and apparatus for detecting the presence of an object |
| KR100607018B1 (ko) * | 1998-06-23 | 2006-08-01 | 샤프 가부시키가이샤 | 화상 처리 장치, 화상 처리 방법 및 화상 처리 프로그램을기록한 매체 |
| JP3670571B2 (ja) | 2000-10-31 | 2005-07-13 | 株式会社Pfu | 画像読取装置 |
-
2002
- 2002-10-04 JP JP2002292007A patent/JP2004129022A/ja not_active Withdrawn
-
2003
- 2003-09-26 WO PCT/JP2003/012313 patent/WO2004032482A1/ja not_active Ceased
- 2003-09-26 US US10/527,984 patent/US7415168B2/en not_active Expired - Fee Related
- 2003-09-26 EP EP03748597A patent/EP1549042A4/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH05344318A (ja) * | 1992-06-10 | 1993-12-24 | Canon Inc | 画像入力装置 |
| JPH11252351A (ja) * | 1998-03-02 | 1999-09-17 | Konica Corp | 画像読取装置 |
| JP2000261653A (ja) * | 1999-03-09 | 2000-09-22 | Hitachi Ltd | 画像処理装置 |
| JP2000341501A (ja) * | 1999-03-23 | 2000-12-08 | Minolta Co Ltd | 画像処理装置および画像処理方法、ならびに画像処理プログラムを記録した記録媒体 |
Non-Patent Citations (1)
| Title |
|---|
| See also references of EP1549042A4 * |
Also Published As
| Publication number | Publication date |
|---|---|
| JP2004129022A (ja) | 2004-04-22 |
| US20060044575A1 (en) | 2006-03-02 |
| EP1549042A1 (en) | 2005-06-29 |
| US7415168B2 (en) | 2008-08-19 |
| EP1549042A4 (en) | 2008-05-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4219542B2 (ja) | 画像処理装置、画像処理方法および画像処理プログラムが格納された記録媒体 | |
| JP2595158B2 (ja) | 画像情報の絵/文字自動分離装置及びその方式 | |
| WO1999067943A1 (en) | Image processor, image processing method, and medium on which image processing program is recorded | |
| US7542608B2 (en) | Method for automatically cropping image objects | |
| US6771842B1 (en) | Document image skew detection method | |
| CN107800922B (zh) | 图像处理装置及其控制方法和计算机可读存储介质 | |
| JP3886727B2 (ja) | 画像処理装置 | |
| US20030160760A1 (en) | Image comining apparatus and method | |
| JP2008147976A (ja) | 画像傾き補正装置及び画像傾き補正方法 | |
| JP2004129022A (ja) | 画像読取装置 | |
| CN111178356A (zh) | 纸张轮廓的歪斜纠偏方法 | |
| JP2616386B2 (ja) | 画像処理装置 | |
| JP3310744B2 (ja) | 解像度変換装置 | |
| JP3697828B2 (ja) | 原稿角度補正方法及び原稿角度補正装置 | |
| JP2009284190A (ja) | 画像読み取り装置および画像読み取りシステム | |
| JPH11288453A (ja) | 再生用のスキャン環境における原稿画像のスキュ―角度および黒い境界線を検出する方法およびシステム | |
| JP2000261653A (ja) | 画像処理装置 | |
| WO1993017518A1 (fr) | Numeriseur d'image | |
| JP3915974B2 (ja) | 画像処理装置、画像処理方法、プログラム及び記録媒体 | |
| JPH05344330A (ja) | 画像領域識別装置 | |
| JPH0676108A (ja) | 文書画像の傾き検出方法 | |
| JP2003203205A (ja) | 文字認識装置、文字認識方法、およびその方法をコンピュータに実行させるプログラム、並びにそのプログラムを記録したコンピュータ読み取り可能な記録媒体 | |
| JP2002262074A (ja) | 画像処理装置、画像処理方法、該方法を実行するプログラムおよび該プログラムを記録した記録媒体 | |
| JP2004032765A (ja) | 媒体を処理する画像形成装置のための方法、及びその方法に従って構成された画像形成装置 | |
| JP3274063B2 (ja) | 画像傾き検出装置 |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| AK | Designated states |
Kind code of ref document: A1 Designated state(s): US |
|
| AL | Designated countries for regional patents |
Kind code of ref document: A1 |
|
| 121 | Ep: the epo has been informed by wipo that ep was designated in this application | ||
| ENP | Entry into the national phase |
Ref document number: 2006044575 Country of ref document: US Kind code of ref document: A1 |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 10527984 Country of ref document: US |
|
| WWE | Wipo information: entry into national phase |
Ref document number: 2003748597 Country of ref document: EP |
|
| WWP | Wipo information: published in national office |
Ref document number: 2003748597 Country of ref document: EP |
|
| WWP | Wipo information: published in national office |
Ref document number: 10527984 Country of ref document: US |