JP2014192636A - Image processing device - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce deterioration of image quality due to stripe removal.SOLUTION: In a stripe detection unit 31, a stripe extending in the sub-scanning direction is detected in an original image, and a stripe range in the main-scanning direction of the stripe is specified. In a correction processing unit 32, a pixel value in the stripe range is corrected in the sub-scanning direction in order to remove the stripe in the original image. Then, in a correction stop determination unit 33, a final end of the strip is detected on the basis of the pixel value in the strip strange, and when the final end of the strip is detected, correction of the pixel value in the stripe range due to a correction processing unit 32 is stopped.

Description

  The present invention relates to an image processing apparatus.

  For example, in an image reading apparatus having an automatic document feeder, if dust adheres to contact glass or the like, the light to be incident on the document is blocked by the dust, so that the document image output from the image reading apparatus is not related to the document. Black streaks and other streaks occur.

  In a certain image processing apparatus, the pixel value in the black stripe is interpolated with the values of the peripheral pixels of such a black stripe to remove the black stripe in the image (see, for example, Patent Documents 1 and 2).

JP 2007-142671 A JP 2011-023920 A

  When the black streak is removed by interpolation as described above, as the black streak becomes wider, there is a higher possibility that the image quality of the portion where the black streak has deteriorated. For example, when the original image is a repetitive image such as a halftone dot, if the width of the black stripe becomes wide, the regularity of the halftone dot is lost at the location where the black stripe is present, so the black stripe is removed. The image quality will be low and will be noticeable.

  Therefore, it is preferable not to perform the interpolation process for black stripe removal except at the black stripe portion. However, in the above-described image processing apparatus, once a black streak is detected, interpolation processing is continuously performed on the black streak portion. Therefore, even if the adhering dust disappears and the black streak disappears from the middle, it continues. There is a possibility that the interpolation process is performed at other points and the interpolation process is performed at a portion other than the black streak portion, and the image quality is deteriorated.

  The present invention has been made in view of the above problems, and an object of the present invention is to obtain an image processing apparatus that reduces image quality degradation caused by streak removal.

  An image processing apparatus according to the present invention detects a streak extending in a sub-scanning direction in a document image and specifies a streak range in the main scanning direction of the streak, and removes the streak in the document image. A correction processing unit for correcting a pixel value in the streak range along the sub-scanning direction, and detecting the end of the streak based on the value of the pixel in the streak range, and detecting the end of the streak, A correction cancellation determination unit that cancels correction of the pixel values within the stripe range by the correction processing unit.

  According to the present invention, it is possible to obtain an image processing apparatus that reduces the deterioration in image quality caused by streak removal.

FIG. 1 is a side view showing an internal configuration of an image processing apparatus according to an embodiment of the present invention. FIG. 2 is a block diagram showing an electrical configuration of the image processing apparatus according to the embodiment of the present invention. FIG. 3 is a diagram for explaining the streak detection by the streak detection unit 31 in FIG. FIG. 4 is a flowchart for explaining the operation of the correction cancellation determination unit 33 in the first embodiment. FIG. 5 is a diagram illustrating an example of correction cancellation by the correction cancellation determination unit 33 according to the first embodiment. FIG. 6 is a diagram for explaining another example of correction cancellation by the correction cancellation determination unit 33 in the first embodiment. FIG. 7 is a flowchart for explaining the operation of the correction cancellation determination unit 33 according to the second embodiment. FIG. 8 is a diagram for explaining an example of correction cancellation by the correction cancellation determination unit 33 according to the second embodiment. FIG. 9 is a diagram for explaining another example of correction cancellation by the correction cancellation determination unit 33 according to the second embodiment.

  Hereinafter, embodiments of the present invention will be described with reference to the drawings.

Embodiment 1 FIG.

  FIG. 1 is a side view showing an internal configuration of an image processing apparatus according to an embodiment of the present invention. The image processing apparatus shown in FIG. 1 is an apparatus such as a scanner, a copier, a facsimile machine, or a multifunction machine.

  The image processing apparatus shown in FIG. 1 includes contact glasses 1 a and 1 b, carriages 2 and 3, an imaging lens 4, an image sensor 5, a white reference patch 6, and a document cover 7.

  The contact glass 1 a is installed on the upper surface of the image processing apparatus main body, and is used to place an original when reading an image without using an automatic document feeder (ADF) of the original cover 7.

  Further, the contact glass 1b is installed on the upper surface of the image processing apparatus main body, and when the image is read while the document is automatically conveyed by the ADF of the document cover 7, the document passes therethrough.

  The ADF described above passes the document so as to pass over the contact glass 1b, and the image reading unit 21 reads the image of the document passing over the contact glass 1b.

  In the image reading unit 21, the carriage 2 is installed so as to be movable in the sub-scanning direction by a drive source (not shown). The carriage 2 has a light source 11 and a mirror 12. The light source 11 is arranged along the main scanning direction, and emits light with, for example, a plurality of light emitting diodes arranged. The light emitted from the light source 11 is reflected by an original placed on the contact glass 1a, an original passing through the contact glass 1b, or the like according to the position of the carriage 2. The mirror 12 reflects reflected light from a document or the like. When the image of a document is read using the ADF of the document cover 7, the carriage 2 is fixedly disposed below the contact glass 1b.

  The carriage 3 is installed so as to be movable in the sub-scanning direction together with the carriage 2 by a drive source (not shown). The carriage 3 has mirrors 13 and 14. The mirrors 13 and 14 reflect the light from the mirror 12 of the carriage 2 and emit it along the sub-scanning direction.

  The imaging lens 4 focuses the light from the mirror 14 on the image sensor 5. The image sensor 5 is a one-dimensional image sensor having light receiving elements with a predetermined number of pixels arranged in the main scanning direction, and outputs an electrical signal corresponding to the amount of light received for the pixels with the number of pixels for each line. For example, a CCD (Charge Coupled Device) is used as the image sensor 5.

  The white reference patch 6 is a plate-like member that is disposed on the top surface inside the apparatus and is used to acquire white reference data.

  The document cover 7 is a member that can be brought into surface contact with the contact glass 1a and is rotatably mounted. The document cover 7 closely contacts the document with the contact glass 1a, and ambient light is incident on the inside of the apparatus from the contact glass 1 during image reading. To prevent. Further, the document cover 7 has an ADF, and the documents placed on the document tray 7a are conveyed one by one by the conveyance roller 7b and passed over the contact glass 1b.

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

  As shown in FIG. 2, the image data of the original image obtained by the image reading unit 21 is supplied to the line correction unit 22.

  The streak correction unit 22 includes a streak detection unit 31, a correction processing unit 32, a correction stop determination unit 33, and a storage unit 34. The streak correction unit 22 may be realized as hardware such as an ASIC (Application Specific Integrated Circuit) or may be realized as software by executing a program on a computer.

  The streak detection unit 31 detects a streak extending in the sub-scanning direction in the document image and specifies a streak range in the main scanning direction of the streak.

  FIG. 3 is a diagram for explaining the streak detection by the streak detection unit 31 in FIG.

  For example, the streak detection unit 31 specifies a range in which the pixel value is equal to or less than a predetermined threshold among a plurality of predetermined lines L1 to LN in the document image, and is common to the lines L1 to LN among the ranges. The part is detected as a streak range.

  In addition, the streak detection unit 31 generates streak range data that designates a streak range in the main scanning direction for each detected one or more streaks. For example, the stripe range data has a pixel position PS at the start position of the stripe range in the main scanning direction and a width W of the stripe range.

  The streak detection unit 31 may perform streak detection for each of the RGB color planes, or the streak detection unit 31 specifies a luminance value from the RGB value of each pixel, and the luminance A streak may be detected using the value as a pixel value.

  The correction processing unit 32 corrects the pixel values in the streak range along the sub-scanning direction in order to remove the streaks in the document image. For example, the correction processing unit 32 changes the pixel value in the stripe range to the pixel value obtained by interpolation based on the pixel values around the stripe range.

  The correction processing unit 32 sequentially selects one line of the document image as a target line, and corrects the pixel value in one or a plurality of line ranges specified by the line range data in the target line.

  When the streak detection is performed for each of the RGB color planes, the correction processing unit 32 performs along the sub-scanning direction to remove the streaks in the document image for each of the RGB color planes. Correct the pixel value within the streak range.

  The correction cancellation determination unit 33 detects the end of the streak in the sub-scanning direction based on the value of the pixel within the streak range. When the end of the streak is detected, the correction processing unit 32 corrects the pixel value within the streak range. To cancel. In other words, pixel values are not corrected for pixels within the streak range after the position where the correction cancellation determination unit 33 cancels in the sub-scanning direction.

  In the first embodiment, the correction cancellation determination unit 33 determines whether or not the pixel value at the pixel position is a value determined as a streak for each pixel position within the streak range along the sub-scanning direction (a). (B) for each pixel position along the sub-scanning direction, the pixels determined to be not the value determined to be a streak are counted, and (c) for all the pixel positions within the streak range When the number of counted pixels becomes equal to or greater than a predetermined threshold, the correction processing unit 32 stops the correction of the pixel value within the stripe range.

  The “value determined as a streak” is a color value of a streak detected by the streak detection unit 31. Hereinafter, the color of “value determined to be a streak” is referred to as a streak color. For example, the streak detection unit 31 identifies a range in which the pixel value is equal to or less than a predetermined threshold among a plurality of predetermined lines L1 to LN in the document image, and is common to those lines L1 to LN in the range. When a portion is detected as a streak range, the “value determined to be a streak” is a value equal to or less than the predetermined threshold.

  When the correction processing unit 32 corrects the pixel value in the streak range along the sub-scanning direction in order to remove the streaks in the original image for each of the RGB color planes, the correction cancellation determination unit 33 When the end of the streak is detected based on the value of the pixel in the streak range and the end of the streak is detected in all the color planes, the correction processing unit 32 corrects the pixel value in the streak range for all the color planes. Let's stop about.

  When the correction processing unit 32 corrects the pixel value in the streak range along the sub-scanning direction in order to remove the streaks in the original image for each of the RGB color planes, the correction stop determination unit 33 For each plane, the end of the streak is detected based on the value of the pixel in the streak range, and when the end of the streak is detected in any one color plane, the correction processing unit 32 corrects the pixel value in the streak range. You may make it cancel about all the color planes.

  The storage unit 34 is a storage device such as a memory that holds the above-described stripe range data. The streak detector 31 writes streak range data specifying one or a plurality of streak ranges in the storage unit 34. The correction processing unit 32 reads the line range data stored in the storage unit 34 for each line, specifies the line range, and performs the above-described correction process on the line range. The correction cancellation determination unit 33 reads the streak range data stored in the storage unit 34, identifies the streak range, and determines whether or not to cancel the correction process for the streak range as described above.

  The streak detection unit 31 detects a streak in the original image of the first page, and performs correction processing by the correction processing unit 32 and determination by the correction stop determination unit 33 on the original image of the second page and thereafter. Alternatively, the streak detection unit 31 detects a streak in a predetermined portion of the original image of the first page, and the correction processing by the correction processing unit 32 and the correction stop determination unit 33 for the original image after the predetermined portion. You may make it perform determination.

  Next, the operation of the image processing apparatus according to the first embodiment will be described.

  FIG. 4 is a flowchart for explaining the operation of the correction cancellation determination unit 33 in the first embodiment.

  When dust or the like adheres to the contact glass 1b and a streak occurs in the original image, the streak detection unit 31 detects the streak, and the pixel value within the streak range is corrected by the correction processing unit 32.

  When the correction processing by the correction processing unit 32 is started, the correction cancellation determination unit 33 first acquires the line range data from the storage unit 34 (Step S1), specifies one or a plurality of line ranges, and sets each line range. The following processing is performed for (that is, each stripe).

  First, the correction cancellation determination unit 33 sets the initial value 0 to the counter data corresponding to each pixel position within one stripe range.

  The correction cancellation determination unit 33 determines whether the pixel at each pixel position within the streak range is a streak color, with the line where the correction process has been started as the target line (step S2).

  The correction cancellation determination unit 33 increases the value of the counter data corresponding to the pixel position that is not determined to be the streak color (that is, the pixel position of the pixel that is not the streak color) by 1 (step S3).

  Then, the correction cancellation determination unit 33 determines whether or not all the values of the counter data corresponding to the pixel positions within the stripe range are equal to or greater than a predetermined cancellation threshold (for example, 4) (step S4).

  When at least one of the values of the counter data corresponding to the pixel position within the streak range is less than the predetermined stop threshold, the correction stop determination unit 33 sets the next line as the attention line (step S5), and steps S2 to S2. The process of S4 is executed.

  On the other hand, when the values of the counter data corresponding to the pixel positions in the streak range are all equal to or greater than the predetermined stop threshold, the correction stop determination unit 33 determines that the streak is over, and the correction processing unit 32 corrects the streak. Is stopped (step S6). Specifically, the correction cancellation determination unit 33 deletes the line range data for the line from the storage unit 34. As a result, the correction processing unit 32 does not perform correction processing for the streak.

  FIG. 5 is a diagram illustrating an example of correction cancellation by the correction cancellation determination unit 33 according to the first embodiment. Note that hatched pixels in the figure are streak-colored pixels, white-brown pixels are pixels that are not streaked, and the numbers in the white-browned pixels are the count values of the counter data described above.

  In the example shown in FIG. 5, the stop threshold is set to 4, the value of the counter data corresponding to the pixel position X4 is 4 on the line Y20, and the values of the counter data corresponding to all the pixel positions X1 to X6 are Since it is 4 or more, the correction cancellation determination unit 33 stops the correction processing by the correction processing unit 32 for the line Y21 and subsequent lines. Note that even if ruled lines are present in the document image as indicated by lines 16 and Y17 shown in FIG. 5, the end of the stripe can be detected appropriately.

  FIG. 6 is a diagram for explaining another example of correction cancellation by the correction cancellation determination unit 33 in the first embodiment. Note that hatched pixels in the figure are streak-colored pixels, and whitened pixels are pixels that are not streaked. In the example shown in FIG. 5, the streak disappears from both ends of the streak range, but in the example shown in FIG. 6, the streak disappears from the center of the streak range. In the example illustrated in FIG. 6, the stop threshold is set to 4, and the correction stop determination unit 33 sets the counter data value corresponding to the pixel position X1 to 4 in the line Y19, and sets all the pixel positions X1 to X6. Since the corresponding counter data value is 4 or more, the correction cancellation determination unit 33 stops the correction processing by the correction processing unit 32 for the line Y20 and subsequent lines.

  As described above, according to the first embodiment, the streak detection unit 31 detects a streak extending in the sub-scanning direction in the document image, specifies a streak range in the main scanning direction, and the correction processing unit 32 In order to remove streaks in the original image, the pixel values in the streaks are corrected along the sub-scanning direction. Then, the correction cancellation determination unit 33 detects the end of the stripe based on the value of the pixel in the streak range, and when the end of the streak is detected, the correction processing unit 32 cancels the correction of the pixel value in the streak range. .

  Thereby, for example, when there is no dust on the contact glass 1b and the streak is finished, the streak removal is stopped, so that the image quality deterioration due to the streak removal is reduced.

Embodiment 2. FIG.

  In the first embodiment, the correction process for the entire stripe range is stopped. In the second embodiment, the correction process is stopped for each pixel position in the stripe range.

  The basic configuration and operation of the image processing apparatus according to the second embodiment are the same as those in the first embodiment, but the correction cancellation determination unit 33 operates as follows.

  In the second embodiment, the correction cancellation determination unit 33 determines whether or not the pixel value at the pixel position is a value determined as a streak for each pixel position within the streak range along the sub-scanning direction (a). (B) Count pixels determined not to be streaks for each pixel position along the sub-scanning direction, and (c) the number of counted pixels is a predetermined value. The correction of the pixel value by the correction processing unit 32 at the pixel position that is equal to or greater than the threshold is stopped.

  In the second embodiment, the correction cancellation determination unit 33 corrects the pixel value by the correction processing unit 32 at the pixel position where the number of counted pixels (that is, the value of the counter data) is equal to or greater than a predetermined threshold. When the original one streak is divided into a plurality of streaks, the streak range data is changed so as to specify the streak ranges of the plurality of streaks.

  Next, the operation of the image processing apparatus according to the second embodiment will be described.

  FIG. 7 is a flowchart for explaining the operation of the correction cancellation determination unit 33 according to the second embodiment.

  When the correction process by the correction processing unit 32 is started, the correction cancellation determination unit 33 first acquires the line range data from the storage unit 34 (step S21), specifies one or a plurality of line ranges, and sets each line range. The following processing is performed for (that is, each stripe).

  First, the correction cancellation determination unit 33 sets the initial value 0 to the counter data corresponding to each pixel position within one stripe range.

  The correction cancellation determination unit 33 determines whether or not the pixel at each pixel position in the streak range is a streak color, with the line where the correction process has been started as the target line (step S22).

  The correction cancellation determination unit 33 increases the value of the counter data corresponding to the pixel position that is not determined to be a streak color (that is, the pixel position of a pixel that is not a streak color) by 1 (step S23).

  Then, the correction cancellation determination unit 33 determines whether or not there is a pixel position within the streak range in which the value of the counter data is equal to or greater than a predetermined cancellation threshold (for example, 4) (step S24).

  When the pixel position where the value of the counter data is equal to or greater than the predetermined stop threshold is not within the streak range, the correction stop determination unit 33 sets the next line as the attention line (step S25), and executes the processes after step S22.

  On the other hand, when there is a pixel position in the streak range where the value of the counter data is equal to or greater than the predetermined stop threshold, the correction stop determination unit 33 updates the streak range data (step S26).

  For example, when the value of the counter data regarding the pixel position at the start position of the streak range is equal to or greater than a predetermined stop threshold, the correction stop determination unit 33 sets the start position PS of the streak range in the streak range data to one pixel. While shifting, the width W of the streak range is reduced by one pixel.

  For example, when the value of the counter data for the pixel position at the end position of the streak range is equal to or greater than a predetermined stop threshold value, the correction stop determination unit 33 sets the width W of the streak range in the streak range data to 1 Make the pixel smaller.

  Further, for example, when the value of the counter data for the pixel position at the center of the streak range becomes equal to or greater than a predetermined stop threshold, the correction stop determination unit 33 starts the width W of the streak range in the streak range data. The number of pixels is changed from the position to the adjacent pixel position (on the start position side) of the pixel position, and the start position PS (the end of the pixel position) of the streak range for the streaks generated separately from the original streak The adjacent pixel position on the position side) and the width W are added to the stripe range data. Note that the added stripe range is similarly processed as one stripe range.

  In this way, pixel positions whose counter data value is equal to or greater than the stop threshold are excluded from the streak range, and correction processing is not performed.

  Then, the correction cancellation determination unit 33 determines whether or not the width W of the streak range after updating the streak range data is zero (step S27), and the width W of the streak range after updating the streak range data is zero. In this case, it is determined that the streak is finished, and the streak range data of the streak range is deleted.

  On the other hand, when the width W of the streak range after the streak range data is updated is not zero, the correction cancellation determination unit 33 sets the next line as the target line (step S25), and executes the processes after step S22.

  FIG. 8 is a diagram for explaining an example of correction cancellation by the correction cancellation determination unit 33 according to the second embodiment. Note that hatched pixels in the figure are streak-colored pixels, white-brown pixels are pixels that are not streaked, and the numbers in the white-browned pixels are the count values of the counter data described above. In the example shown in FIG. 8, the stop threshold is set to 4. In the example shown in FIG. 8, in the initial state, the start position PS of the streak range is X1, and the width W is 6 (6 pixels).

  Then, when the value of the counter data at the pixel position X6 becomes 4 in the line Y12, the width W of the stripe range is changed to 5. That is, the streak range to be corrected at this time is from the pixel position X1 to the pixel position X5.

  Next, on the line Y13, when the value of the counter data at the pixel position X1 becomes 4, the start position PS of the stripe range is changed to X2, and the width W is changed to 4. That is, the streak range to be corrected at this time is from the pixel position X2 to the pixel position X5.

  Thereafter, when the value of the counter data at the pixel position X2 becomes 4 in the line Y15, the start position PS of the streak range is changed to X3 and the width W is changed to 3. That is, the streak range to be corrected at this time is from the pixel position X3 to the pixel position X5.

  Thereafter, when the value of the counter data at the pixel position X5 becomes 4 in the line Y17, the width W of the stripe range is changed to 2. That is, the streak range to be corrected at this time is from the pixel position X3 to the pixel position X4.

  Thereafter, when the value of the counter data at the pixel position X3 becomes 4 on the line Y18, the start position PS of the streak range is changed to X4 and the width W is changed to 1. That is, the streak range to be corrected at this time is only the pixel position X4.

  Thereafter, when the value of the counter data at the pixel position X4 becomes 4 in the line Y20, the width W of the streak area becomes 0, and the correction process for this streak is completely stopped.

  FIG. 9 is a diagram for explaining another example of correction cancellation by the correction cancellation determination unit 33 according to the second embodiment. Note that hatched pixels in the figure are streak-colored pixels, white-brown pixels are pixels that are not streaked, and the numbers in the white-browned pixels are the count values of the counter data described above. In the example shown in FIG. 9, the stop threshold is set to 4. In the example shown in FIG. 9, in the initial state, the start position PS of the streak range is X1, and the width W is 6 (6 pixels).

  Then, when the value of the counter data at the pixel position X6 becomes 4 in the line Y12, the width W of the stripe range is changed to 5. That is, the streak range to be corrected at this time is from the pixel position X1 to the pixel position X5.

  Next, on the line Y14, when the value of the counter data at the pixel position X1 becomes 4, the start position PS of the streak range is changed to X2, and the width W is changed to 4. That is, the streak range to be corrected at this time is from the pixel position X2 to the pixel position X5.

  Thereafter, when the value of the counter data at the pixel position X3 and the pixel position X4 becomes 4 in the line Y17, the width W of the stripe range is first changed to 1. That is, the stripe range to be corrected at this time is only the pixel position X2. Then, since the streak remains at the pixel position X4 in the streak range X2 to X5 at this time, the streak range where the start position PS of the streak range is X4 and the width is 1 for the streak at the pixel position X4. Add data. Note that the value of the counter data at the pixel position X4 is inherited as it is.

  After the line Y18, the stripe range at the pixel position X2 and the stripe range at the pixel position X4 are processed separately.

  With respect to the streak range at the pixel position X4, when the counter data value at the pixel position X4 reaches 4 in the line Y18, the width W of the streak range becomes 0, and the correction processing for this streak is completely stopped. Range streak data is deleted at this point.

  On the other hand, for the line range at the pixel position X2, when the counter data value at the pixel position X2 becomes 4 in the line Y19, the width W of the line range becomes 0, and the correction process for this line is completely stopped. The stripe range data of this stripe range is deleted at this point.

  As described above, according to the second embodiment, the correction is stopped for each pixel position. Therefore, the width of the correction portion is narrowed, and the deterioration in image quality due to the correction by interpolation or the like is reduced. The resulting degradation in image quality is reduced.

  Each embodiment described above is a preferred example of the present invention, but the present invention is not limited to these, and various modifications and changes can be made without departing from the scope of the present invention. It is.

  The present invention can be applied to, for example, an image forming apparatus such as a scanner machine, a facsimile machine, a copier, or a multifunction machine having an image reading function.

1b Contact Glass 21 Image Reading Unit 31 Line Detection Unit 32 Correction Processing Unit 33 Correction Cancellation Determination Unit

Claims (7)

A streak detection unit for detecting streaks extending in the sub-scanning direction in the document image and identifying a streak range in the main scanning direction of the streaks;
A correction processing unit that corrects pixel values in the streak range along the sub-scanning direction in order to remove the streaks in the document image;
A correction stop determination unit that detects the end of the streak based on the value of the pixel in the streak range, and stops the correction of the pixel value in the streak range by the correction processing unit when the end of the streak is detected; ,
An image processing apparatus comprising:   The correction cancellation determination unit determines (a) whether the pixel value at the pixel position is a value determined as the streak for each pixel position within the stripe range along the sub-scanning direction. (B) Counting pixels determined not to be determined as the streak for each pixel position along the sub-scanning direction, and (c) for all pixel positions within the streak range. The image processing apparatus according to claim 1, wherein when the number of the counted pixels exceeds a predetermined threshold, the correction processing unit stops the correction of the pixel value in the stripe range. The correction processing unit corrects the pixel value in the streak range along the sub-scanning direction in order to remove the streaks in the document image for each color plane of RGB,
The correction cancellation determination unit detects the end of the streak based on the value of the pixel within the streak range for each color plane, and detects the end of the streak in all the color planes. Stopping correction of pixel values within the streak range by the unit,
The image processing apparatus according to claim 1, wherein: The correction processing unit corrects the pixel value in the streak range along the sub-scanning direction in order to remove the streaks in the document image for each color plane of RGB,
The correction cancellation determination unit detects, for each color plane, the end of the streak based on the value of a pixel in the streak range, and detects the end of the streak in any one of the color planes. Stopping correction of pixel values in the streak range by the correction processing unit;
The image processing apparatus according to claim 1, wherein:   The correction cancellation determination unit determines (a) whether the pixel value at the pixel position is a value determined as the streak for each pixel position within the stripe range along the sub-scanning direction. (B) Counting pixels determined not to be determined as the streak for each pixel position along the sub-scanning direction, and (c) the number of counted pixels is a predetermined value. The image processing apparatus according to claim 1, wherein the correction of the pixel value by the correction processing unit is stopped at a pixel position that is equal to or greater than a threshold value. The streak detection unit generates streak range data that specifies the streak range in the main scanning direction for each of the detected one or more streaks,
The correction processing unit corrects a pixel value in one or a plurality of the streak ranges specified by the streak range data,
The correction cancellation determination unit, when stopping the correction of the pixel value by the correction processing unit at the pixel position where the counted number of pixels is equal to or greater than a predetermined threshold, The line range data is changed to specify the line range of the plurality of lines,
The image processing apparatus according to claim 5. A contact glass; an automatic document feeder that passes a document so as to pass over the contact glass; and an image reading unit that reads an image of the document that passes over the contact glass;
The streak detection unit detects a streak extending in the sub-scanning direction in the document image by using the image read by the document reading unit as the document image, and specifies a streak range in the main scanning direction of the streak;
The image processing apparatus according to claim 1, wherein:

Images