JP2010157916A - Image reader, and wrinkle region determination method in the same, and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To attain an image reading technology capable of detecting a wrinkle region from a read image in a colorless document. <P>SOLUTION: This image reader has: a reading means for reading the image from the document; a saturation detection means for detecting the saturation value of each pixel from image data read by the reading means; a determination means for determining whether or not each pixel is included in the wrinkle region on the basis of the saturation value detected by the saturation detection means; and a correction means for correcting data about the pixel determined to be included in the wrinkle region by the determination means, wherein the determination means determines, when the saturation value detected by the saturation detection means satisfies a predetermined condition for the colorless document, that the pixel with the saturation value is included in the wrinkle region. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a technique for determining the presence or absence of a wrinkle region from an image read from a document.

  Conventionally, an image reading apparatus that reads image information in a document and outputs the read image information has been put into practical use. It is desired that image information to be read is displayed and stored in a high quality state. Furthermore, in recent years, image reading processing such as OCR that optically reads printed characters and recognizes the characters has been frequently used, and further improvement in image reading accuracy and quality is desired.

  By the way, recently, in many companies, in order to reduce the space for storing manuscripts and to improve the efficiency of business, so-called paperless printing, in which documents are stored as electronic information instead of manuscripts (hard copy), has progressed. Yes. As a result, there are increasing opportunities to read all originals, including color originals and old achromatic originals that had only monochrome printers.

  In particular, old manuscripts and the like are often damaged and wrinkled because time has passed. When such a wrinkled document is read by a scanner or the like, there is a disadvantage that light and dark shadows at a wrinkled portion in the document are reflected in the read image.

  In general, in an inexpensive scanner, a reading unit that reads a document includes a single light source and a light receiving unit, and the light source is arranged on either the upstream side or the downstream side in the transport direction with respect to the light receiving unit. Light is irradiated obliquely from one side to the document surface, and the light receiving section reads the reflected light from a direction perpendicular to the document surface.

  In such a scanner that irradiates light from one side, it is difficult for light to reach the back of the wrinkled portion of the document. Therefore, a shadow due to the wrinkle is generated in the document, and the read image includes an unnecessary shadow.

  In order to avoid such inconvenience, the reading unit is provided with two light sources, two light sources are arranged on both sides so as to sandwich the light receiving unit, and upstream and downstream in the transport direction with respect to the document. It is conceivable to irradiate light from both sides so as not to cause shadows due to wrinkles. However, since at least two light sources are required, the cost increases accordingly.

For example, Patent Document 1 describes a technique for reducing the influence of wrinkles formed in a document. According to Patent Document 1, a document is pressed by a reference surface extending in the width direction of the document conveyance path and a pressing member facing the reference surface, and wrinkles formed on the document surface are corrected. Then, by reading the original surface with the wrinkles corrected, the influence of wrinkles on the image is reduced, and the quality of the image is improved.
Japanese Patent No. 3912917

  However, the technique described in Patent Document 1 requires a member for pressing the document, and incurs high cost in exchange for realizing high image quality.

  Further, in order to reduce the influence of wrinkles in a document at a low cost, it is necessary to detect a wrinkle area from the read image and perform some image processing on the detected wrinkle area. No technology that focuses on this point has been found at present.

  The present invention provides at least one of realizing an image reading apparatus capable of detecting a wrinkle area from a read image in an achromatic document, and realizing an image reading apparatus capable of effectively correcting pixels of the detected wrinkle area. For one purpose.

  In order to solve the above problems, an image reading apparatus of the present invention includes a reading unit that reads an image from a document, a saturation detection unit that detects a saturation value of each pixel from image data read by the reading unit, Determination means for determining whether each pixel is included in the wrinkle area based on the saturation value detected by the saturation detection means, and correcting the data of the pixel determined to be included in the wrinkle area by the determination means A correction unit, and when the saturation value detected by the saturation detection unit satisfies a predetermined condition for a pixel of an achromatic document, the determination unit includes the pixel in the wrinkle region. Is determined.

  Further, the wrinkle region determination method of the present invention is a wrinkle region determination method in an image reading apparatus that reads an image from a document, and includes a saturation detection step of detecting a saturation value of each pixel from the read image data, A determination step of determining whether each pixel is included in the wrinkle region based on the detected saturation value, and a correction step of correcting data of the pixel determined to be included in the wrinkle region, In the determination step, when the detected saturation value satisfies a predetermined condition for a pixel of an achromatic document, it is determined that the pixel is included in the wrinkle region.

  According to the present invention, a wrinkled region can be detected from a read image in an achromatic original. Further, since the pixel data of the detected wrinkle region can be corrected, a high quality image can be obtained at a low cost.

  The best mode for carrying out the present invention will be described below in detail with reference to the accompanying drawings. The following embodiments are examples as means for realizing the present invention, and should be appropriately modified or changed depending on the configuration of the apparatus to which the present invention is applied and various conditions without departing from the spirit of the present invention. The present invention is not limited to the following embodiments.

[Configuration of Image Reading Apparatus]
The configuration of the image reading apparatus according to the embodiment of the present invention will be described.

  FIG. 1 is a schematic view illustrating the configuration of an image reading apparatus according to an embodiment of the invention. In addition, the structure of illustration is schematic and this invention is not limited to this structure.

  As shown in FIG. 1, the image reading apparatus 1 includes a pickup roller 2 that picks up a document D, a feeding roller 3 that feeds the document D picked up by the pickup roller 2, and a picked-up document D. And a separation roller 4 for separating the sheets one by one. Further, the image reading apparatus 1 is located on the downstream side of the reading unit 8, a registration roller pair 5 disposed in pairs for conveying the document D, a reading unit 8 for reading image information on the document D, and the like. A pair of conveyance rollers 7 and a registration sensor 10 that detects the document D are provided.

  The image reading apparatus 1 includes an upper frame 81 and a lower frame 82, and the upper frame 81 is rotatable about a rotation shaft 81a. In order to remove the document staying in the apparatus, the apparatus can be manually opened and closed. The reading unit 8 is fixed to the upper frame 81. The reading unit 8 includes a line image sensor 200 and a light source 201.

In this image reading apparatus, the original D is illuminated by the light source 201 and the original image is read by the line image sensor 200. However, since the light amount of the light source 201 and the sensitivity of the line image sensor 200 are uneven, the white color reference member is read. Need to be corrected.
For this reason, shading correction is performed when executing a light amount adjustment process for optimizing the light emission amount of the light source 201 and a gain adjustment process for optimizing the amplification factor for the image signal output from the line image sensor 200. This shading correction is a process of correcting the light amount unevenness of the light source 201 and the sensitivity unevenness of the line image sensor 200 for each pixel cell of the line image sensor 200.

  In the present embodiment, a correction process for the line image sensor 200 to uniformly read a document image including the light amount adjustment process and the gain adjustment process is referred to as “shading correction”. Here, the color of the facing member 9 arranged facing the line image sensor 200 and the light source 201 so as to sandwich the document D is white, and the facing member 9 is read to perform shading correction.

  The image reading apparatus 1 configured as described above performs an image reading operation of the document D described below.

  First, as will be described later, the reading unit 8 reads the facing member 9 by the line image sensor 200, generates correction data for shading correction, and stores it for each pixel. Thereafter, the document D is fed into the apparatus by the pickup roller 2 and the feeding roller 3 and separated one by one by the separation roller 4. The document D is sandwiched between the registration roller pair 5 and the conveyance roller pair 7 and is conveyed in the sub-scanning direction, and the image on the surface is read by the reading unit 8 in the main scanning direction (a direction perpendicular to the sub-scanning direction). .

  Note that the image data generated from the image signal of the line image sensor 200 of the reading unit 8 is subjected to shading correction with reference to the correction data described above.

  After the image is read, the document D is ejected out of the apparatus while being held and conveyed by the conveyance roller pair 7. The timing for reading the image is set so that the reading starts after the leading end of the document D passes through the registration sensor 10 and ends after the document D has passed. Since the registration sensor 10 that detects the document D is located upstream of the line image sensor 200, the document D is read after a predetermined time has elapsed after the leading edge of the document D passes over the registration sensor 10. Start. Further, the reading is finished after a lapse of a fixed time after the trailing edge of the document D passes over the registration sensor 10. Thereby, the leading edge resist and trailing edge resist of the read image are adjusted.

  FIG. 2 is a block diagram showing an electrical configuration of the image reading apparatus according to the present embodiment.

  In FIG. 2, the image reading unit 102 includes a light source 201, a line image sensor 200, and an A / D conversion unit. The light reflected from the document D by irradiating the document D with the light source 201 is decomposed into pixels with a predetermined resolution by the line image sensor 200 and subjected to photoelectric conversion, and then the A / D conversion unit has a predetermined color depth. Output as image data.

  The image processing unit 103 includes a shading correction unit and a binarization unit (not shown), and performs image processing on the image data read by the image reading unit 102. The shading correction unit performs shading correction using a known method. The binarization unit will be described later.

  The saturation detection unit 104 detects the saturation value of each pixel constituting the image read by the image reading unit 102. The detection method here will be described later.

  The wrinkle region determination unit 105 determines whether or not the target pixel is included in the wrinkle region based on whether or not the saturation value detected by the saturation detection unit 104 satisfies a predetermined condition. The determination method here will be described later.

  The data correction unit 106 corrects to another data when each pixel constituting the image read by the image reading unit 102 is determined to be a pixel included in the wrinkle region by the wrinkle region determination unit 105. The correction method here will be described later.

  The control unit 109 includes a CPU, a ROM, and a RAM (not shown). Various programs such as a basic processing program as an image reading device are stored in the ROM, and are necessary for executing these programs. Various data are stored. Then, a CPU (not shown) uses the RAM as a work memory based on a program in the ROM, and controls each part of the apparatus 1 to execute basic processing as an image reading apparatus.

  The output unit 107 functions as a recording unit that records and outputs an image on recording paper when the image reading apparatus 1 is applied to a copying machine or the like, and when applied to a facsimile or a scanner, the output unit 107 is a telephone line or a PC. It functions as a communication unit connected to the external host device.

  The storage unit 108 includes, for example, a RAM, a hard disk, a flash memory, and the like, and image information and image data are written and read under the control of the control unit 109.

  Next, a saturation detection method performed by the saturation detection unit 104 will be described with reference to the flow of FIG.

  In FIG. 4, first, the image size is acquired from the image information stored in the storage unit 108, and the number of pixels calculated based on this size is stored in the variable I (step S401). Next, a memory necessary for storing the saturation value S for each pixel is secured (step S402). Next, it is determined whether there is a next pixel based on whether I is 1 or more (step S403). If there is a next pixel, I is first decremented (step S404), and the R value, G value, and B value as pixel data of the pixel of interest stored in the storage unit 108 are read (step S405).

  By the way, the method of converting from RGB (red, green, blue) to HSV (hue, saturation, lightness) is performed by a generally known conversion method described below.

Hue H = 60 * (GB) / (MAX-MIN) +0 (when MAX = R)
Hue H = 60 * (BR) / (MAX-MIN) +120 (when MAX = G)
Hue H = 60 * (RG) / (MAX-MIN) +240 (when MAX = B)
Saturation S = (MAX−MIN) / MAX (1)
Lightness V = MAX
MAX is the maximum value among the R, G, and B values, and MIN is the minimum value among the R, G, and B values.

  In accordance with the conversion method, first, the maximum value among the R value, G value, and B value of the read pixel data is substituted into the variable MAX (step S406), and similarly, the minimum value is substituted into the variable MIN (step S407). . Further, the saturation value S of the pixel is calculated according to the above equation 1 using MAX and MIN (step S408). Next, the saturation value S is stored in the secured memory (step S409). For example, when the pixel data is (R, G, B) = (200, 150, 100), MAX = 200, MIN = 100, and saturation S = (200−100) /200=0.5. become.

  After storing the saturation value S, the process returns to step S403 again, and this process is repeated until there is no next pixel.

  Next, the 105 determination method by the wrinkle region determination unit will be described. The reason why the color tone is generated when an achromatic original having a wrinkle is read in color will be described with reference to FIG.

  Originally, when an achromatic original is read in color, the read image data should have a saturation value S close to 0, but when a wrinkled achromatic original is read, the read image data There is a color.

  FIG. 3A shows a case where an achromatic document without wrinkles is read, and the incident angle of light that the light source 201 irradiates the document D is θ0. When the original D is not wrinkled, the incident angle is θ0 no matter which part of the original D is irradiated. When the light source 201 is turned on in the order of R, G, and B, the line sensor 200 receives light in the order of the R component, the G component, and the B component. For this reason, a time difference occurs in the light receiving time. Since the document D is being conveyed even during light reception, the document position differs by this time difference with respect to reception of the R light, G light, and B light. However, since it is a wrinkle-free document, the same incident angle θ0 is applied regardless of the position, and the received light intensity is the same for R light, G light, and B light.

  On the other hand, when reading a wrinkled achromatic color original, if the original position is slightly different, the incident angles of R, G, and B are different as shown in FIG. , G light, and B light are different, and the R value, G value, and B value are not equal. As a result, image data having a hue / tint different from the image information of the document D is formed. For example, if the document D is a white document, the image data is chromatic color with low saturation.

  For the reasons described above, when a wrinkled achromatic original is read in color, a slight color tone is generated in the wrinkled region.

  However, there are other causes of color when reading an achromatic original. As described above, when the light source is turned on in the order of R, G, and B, the line image sensor 200 causes a time difference to receive light in the order of R, G, and B values. Slightly different. As a result, for example, when a fine line on the document D is read, color misregistration may occur. In this case, since it is not a chromatic color with low saturation but a chromatic color with high saturation, it can be distinguished from the occurrence of color due to wrinkles.

  From the above, the wrinkle region determination unit 105 determines that the saturation value S of the target pixel is equal to or greater than a predetermined second value (saturation threshold Ts2, here 0 based on the saturation value S detected by the saturation detection unit 104). .5), the pixel is determined to have a color shift.

  When the saturation value S is less than the predetermined first value (saturation threshold Ts1, here 0.1), it is determined that the pixel is not included in the wrinkle region because no color is generated. To do.

  When the saturation value S is greater than or equal to the first value (saturation threshold value Ts1 or more) and less than the second value (less than the saturation threshold value Ts2), a pixel in which color is generated, judge. Incidentally, it can be seen from the above equation 1 that the saturation value S has a minimum value of 0 and a maximum value of 1 and takes values from 0 to 1 (FIG. 5).

  Here, the saturation threshold Ts1 is 0.1 and the saturation threshold Ts2 is 0.5, but other values may be used.

  Next, a correction method by the data correction unit 106 will be described with reference to FIGS.

  The data correction unit 106 replaces the R, G, and B data of the pixels determined as the pixels included in the wrinkle region by the wrinkle region determination unit 105 described above with data corresponding to the background brightness. As the flow of the correction process, scanning is performed while changing the target pixel from the upper left end of the image as the start point and the lower right end as the end point, and if the target pixel is included in the wrinkle region, the data corresponding to the background lightness It becomes the flow of replacing with.

  In FIG. 6, first, an image size is acquired from the image information stored in the storage unit 108, and the number of pixels calculated based on this size is stored in a variable I (step S601). Next, a lightness histogram is created from the image data stored in the storage unit 108, and a background lightness Vb and a character lightness Vt are obtained (step S602). Here, a method for creating a lightness histogram, a method for obtaining background lightness, and character lightness will be described later. Here, as an example, a case where the background lightness (first lightness) Vb = 200 and the character lightness (second lightness) Vt = 50 will be described.

  Next, whether or not there is a next pixel is determined based on whether or not I is 1 or more (step S603). If there is a next pixel, I is first decremented (step S604), and the saturation value S (I) of the pixel of interest stored in the storage unit 108 is read (step S605). Next, the wrinkle region determination unit 105 determines whether the pixel of interest is a color-shifted pixel. If it is determined that the pixel is a color-shifted pixel (YES in step S606), the R, G, and B data of the pixel of interest are The data corresponding to the character brightness Vt is replaced with 50 (S607). On the other hand, if the pixel is not a color shift pixel, the wrinkle region determination unit 105 determines whether the target pixel is included in the wrinkle region (step S608). As a result, if it is determined that the pixel is included in the wrinkle region (YES in step S608), the R, G, and B data of the target pixel are replaced with data 200 corresponding to the background lightness Vb, respectively ( Step S609).

  On the other hand, if NO in step S608, the wrinkle region determination unit 105 determines that the pixel of interest is not a color misregistration pixel or a pixel included in the wrinkle region, and returns to S603 without performing the process. This process is repeated until there are no more pixels.

  FIG. 7 exemplifies the result of the data correction processing according to FIG. 6, (a) is the pixel data before correction, (b) is the saturation value detected from the pixel data, and (c) is the pixel data after correction. Each is shown.

  In the present embodiment, the pixel data included in the wrinkle region is replaced with pixel data having a brightness equal to the background brightness, but may be replaced with pixel data having a brightness (255) brighter than the background, for example, other than the background brightness. .

  Next, a lightness histogram creation method will be described with reference to the flow of FIG.

  In FIG. 10, first, the memory for the brightness histogram is initialized. Here, as an example, a memory capable of counting the number of appearances of lightness in 256 stages from 0 to 255 is secured (S1000). Further, it is assumed that the saturation value is calculated and stored from the pixel data composed of the R value, the G value, and the B value by the above-described method.

  The image size is acquired from the image information stored in the storage unit 108, and the number of pixels calculated based on this size is stored in the variable I (step S1001). It is determined whether there is a next pixel based on whether I is 1 or more (step S1002). If there is a next pixel, I is first decremented (step S1003), and the saturation value S (I) of the target pixel stored in the storage unit 108 is read (step S1004).

  Next, it is determined whether or not the saturation value S (I) of the target pixel is 0.1 or less (step S1005). If it is less than 0.1, the data of the pixel of interest is read (step S1006), the brightness is obtained, and then the brightness value counter is incremented (step S1007). Thereafter, the process returns to step S1002, and this process is repeated until there is no next pixel. On the other hand, if the saturation value is 0.1 or more in step S1005, the process returns to step S1002.

  Next, how to obtain the background lightness and the character lightness (lightness detection method) will be described with reference to FIG. FIG. 11 exemplifies the lightness histogram created as described above, and the lightness histogram of an achromatic color document generally increases the number of appearances of background lightness and character lightness. Therefore, the lightness value of the first peak from the lightness 0 to 255 direction is the character lightness, and the lightness value of the first peak from the lightness 255 to the 0 direction is the background lightness. Here, the lightness value 50 of the first peak in FIG. 11 is the character lightness, and the lightness value 200 of the last peak value is the background lightness.

  Next, the binarization method will be described with reference to the flow of FIG.

  In FIG. 8, the image size is acquired from the image information stored in the storage unit 108, and the number of pixels calculated based on this size is stored in the variable I (step S801). It is determined whether there is a next pixel based on whether I is 1 or more (step S802). If there is a next pixel, I is first decremented (step S803), and the data of the pixel of interest stored in the storage unit 108 is read (step S804). It is assumed that the brightness value is calculated from the target pixel data composed of the R value, the G value, and the B value by the method exemplified above.

  Next, it is determined whether all of the R value, G value, and B value of the target pixel are equal to or higher than the binarization threshold value 180 (step S805). Alternatively, the brightness value (MAX value) of the target pixel calculated by the above-described method may be determined. If the determination is 180 or more, the target pixel is set to white (step S806), and if it is less than 180, the target pixel is set to black (step S807). Thereafter, the process returns to step S802, and this process is repeated until there is no next pixel. Although the binarization threshold is 180 here, other values may be used. Moreover, although it was determined whether all of the R value, the G value, and the B value are equal to or greater than the binarization threshold value 180, the average value or the mean square value of the R value, the G value, and the B value may be used for the determination. Good.

  FIG. 9 illustrates the binarized data according to FIG. 8. FIG. 9A shows a case where it is assumed that the data before brightness correction is binarized as it is for comparison, and the pixels in the shaded area are included in the wrinkled region. Since it is a pixel corresponding to a shaded shadow, if it is binarized, it will remain as a black pixel. On the other hand, (b) shows the case where the pixel data of the pixel corresponding to the shadow according to the present invention is replaced with the pixel data having the same brightness as the background portion, and the data is binarized, and corresponds to the shadow shown in (a). There are no black pixels, and the binarization result is good.

  Finally, an image reading operation by the image reading apparatus according to the present embodiment will be described with reference to the flowchart of FIG.

  The control unit 109 waits for the user to press a start button (not shown) of the image reading apparatus 1 (step S1200). If the control unit 109 detects that the start button is pressed, the document is placed on the document table (not shown). It is determined whether or not there is (step S1201). If there is no original, the process returns to step S1200. If there is an original, correction data for shading correction that is performed when reading image information described later is created (step S1202).

  After creating the correction data, the control unit 109 conveys the document to a predetermined position, reads the image information by the image reading unit 102 (step S1203), creates a brightness histogram, and calculates the background brightness Vb and the text brightness Vt. Obtained (step S1204). Next, the saturation detection unit 104 detects the saturation value of each pixel (step S1205).

  Then, the pixel data determined to be included in the wrinkle region by the wrinkle region determination unit 105 is replaced with pixel data having lightness equal to the background portion by the data correction unit 106 (step S1206). Thereafter, binarization processing is performed by the image processing unit 103 (step S1207), and the binarized data is transferred to an external device (not shown) (step S1208). Thereafter, the process returns to step S1201, and this process is repeated until there is no next pixel.

  According to the above-described embodiment, a wrinkle region can be detected from a read image and pixel data of the detected wrinkle region can be corrected in an achromatic document, so that a high-quality image can be obtained at a low cost. In the above-described embodiment, the image data of the achromatic document is handled as pixel data composed of R value, G value, and B value until just before binarization, but before that, grayscale pixel data is processed. The data correction unit 106 may replace the grayscale pixel data with the same brightness as that of the background portion.

The present invention can also be applied to a program for causing a computer to execute the processing according to each flow described above, and a computer-readable storage medium storing the program.
In this case, a storage medium storing a computer program for executing the processing according to each flow described above is supplied to the computer of the image reading apparatus, and the computer reads the program code stored in the storage medium and executes the above processing. To do. In addition, a part or all of the processing according to each flow of the present invention may be replaced with processing by hardware. Further, the processing of the present invention may be performed in a host device such as a PC connected to the image reading device. In this case, an image reading system including the image reading device and the host device corresponds to the image reading device of the present invention.

1 is a schematic diagram illustrating a mechanical configuration of an image reading apparatus according to an embodiment of the present invention. 1 is a block diagram illustrating an electrical configuration of an image reading apparatus according to an embodiment. It is a figure explaining the principle which a color generate | occur | produces in a wrinkle area | region. It is a flowchart which shows the saturation detection method. It is a figure explaining a wrinkle area | region detection method. It is a flowchart which shows a data correction method. It is a figure which illustrates the pixel data before and behind data correction. It is a flowchart which shows a binarization process. It is a figure which illustrates the binarized data before and behind data correction. It is a flowchart which shows the histogram preparation method. It is a figure explaining the detection method of background lightness and character lightness. It is a flowchart which shows operation | movement of the whole apparatus.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1,100 Image reading apparatus 2 Pickup roller 3 Feeding roller 4 Separating roller 5 Registration roller pair 7 Conveying roller 8 Reading unit 9 Opposing member 10 Registration sensor 81 Upper frame 82 Lower frame 102 Image reading unit 103 Image processing unit 104 Saturation detection Unit 105 wrinkle region determination unit 106 data correction unit 107 output unit 108 storage unit 109 control unit 110 bus 200 line image sensor 201 light source

Claims (6)

Reading means for reading an image from a document;
Saturation detecting means for detecting the saturation value of each pixel from the image data read by the reading means;
Determination means for determining whether each pixel is included in the wrinkle region based on the saturation value detected by the saturation detection means;
Correction means for correcting data of pixels determined to be included in the wrinkle region by the determination means,
The determination unit determines that a pixel of an achromatic document is included in the wrinkle region when the saturation value detected by the saturation detection unit satisfies a predetermined condition. An image reading apparatus.   The image reading apparatus according to claim 1, wherein the saturation detection unit detects a saturation value based on a difference between a maximum value and a minimum value of R, G, and B values of each pixel. A histogram is created by calculating the brightness from data of pixels whose saturation value is less than a predetermined first value, and a background brightness that is a predetermined first brightness and a predetermined second brightness from the generated histogram. Lightness detecting means for detecting the character lightness
The correcting unit replaces data of pixels having a saturation value equal to or greater than a predetermined second value with data corresponding to the character brightness, and the saturation value is equal to or greater than the predetermined first value. The image reading apparatus according to claim 1, wherein pixel data less than a value is replaced with data corresponding to the background brightness.   4. The image reading apparatus according to claim 1, further comprising a binarizing unit that binarizes the image data corrected by the correcting unit. A wrinkle region determination method in an image reading apparatus for reading an image from a document,
A saturation detection step of detecting a saturation value of each pixel from the read image data;
A determination step of determining whether each pixel is included in the wrinkle region based on the detected saturation value;
A correction step of correcting data of pixels determined to be included in the wrinkle region,
In the determination step, if the detected saturation value satisfies a predetermined condition for a pixel of an achromatic color document, it is determined that the pixel is included in the wrinkle region. .   A program for causing a computer of an image reading apparatus to execute the wrinkle region determination method according to claim 5.

Images