JP4585999B2 - Image processing apparatus, image processing method, and program - Google Patents

Description

  The present invention relates to an image processing apparatus, an image processing method therefor, and a program, and more particularly, to an image processing apparatus that removes isolated point pixels from image data, an image processing method therefor, and a program.

  In an image forming apparatus having an image reading function, unnecessary isolated point pixels that should not originally exist on the read image data used for image formation due to, for example, dust, scratches, or other noise attached to the original at the time of reading the original. May occur. Since the existence of the isolated point pixels leads to a reduction in the quality of the output image, a technique for removing the isolated point pixels generated on such image data before image formation has been studied.

  Examples of such an image processing method include the techniques disclosed in Patent Document 1 and Patent Document 2.

  A method of removing isolated point pixels by the conventional image processing method disclosed in Patent Document 1 will be briefly described. As shown in FIG. 9, in the image processing of binary image data, in the m × n pixel (5 × 5 in FIG. 9) reference pixel region 90, all pixels at the edge thereof are set as the target pixel 91, and the target pixel 91 If no black pixel is present, all pixels in the reference pixel area 90 are output as white pixels. In the case of the conventional technique, when 5 × 5 pixels are used as the reference pixel region 90, and in the case of the patterns 101 and 102 shown in FIG.

The processing method disclosed in Patent Document 2 will be briefly described. First, as shown in FIG. 11, in the image processing of binary image data, among reference pixel regions of m × n pixels (5 × 5 in FIG. 11), at least one line extending in the y direction is used as a target block. The attention block is sequentially shifted in the direction. Hereinafter, this is described as scanning in the x direction. Each time a target block in which the pixel values of the pixels constituting the target block are the same is detected in the scanning process, this pixel value is reset as the reference pixel value, and scanning is continued. Then, among the pixels constituting the block of interest, the pixel values of the pixels at both ends in the y direction are set, and the pixels other than the reference pixel values among the pixels other than both ends in the y direction It is detected whether there is a target block including a pixel that is a value. If the target block exists as a result of this detection, the target block is detected as a removal candidate target block. If the number of removal candidate attention blocks in the m × n pixel reference pixel area is equal to or less than a predetermined number, the pixel values of the pixels constituting the removal candidate attention block are unified to the reference pixel value. In the case of such a conventional technique, when 5 × 5 pixels are used as a reference region, in the case of the patterns 101 to 103 in FIG. 10, isolated point pixels existing inside the reference region are removed. Further, the pattern 104 in FIG. 10 is removed only when the scanning direction is set in the minus direction along the x axis.
JP 2001-119585 A JP 2004-72405 A

  However, in the image processing method of Patent Document 1, in order to find an isolated point pixel, all the edges of the reference pixel area including the isolated point pixel must have the same pixel value. Therefore, if the pattern is as shown in the patterns 104 and 105 in FIG. 10, it is not determined as an isolated point pixel even though the isolated point pixel exists.

  In the processing method disclosed in Patent Document 2, there is a difference in the shape of isolated point pixels that can be removed depending on the scanning direction of the processing. Therefore, in order to reliably remove isolated point pixels such as the pattern 104 in FIG. 10, it is necessary to perform processing in all four types of scanning directions.

  Furthermore, the isolated point pixels of the pattern 105 in FIG. 10 cannot be removed by any processing method, no matter how the settings are changed.

  An object of the present invention is to provide an image processing apparatus, an image processing method thereof, and a program capable of accurately removing isolated point pixels regardless of an image pattern around the isolated point pixels.

In order to achieve the above object, an image processing apparatus according to claim 1 is an image processing apparatus that removes isolated point pixels having a pixel value to be removed from input image data. Reference pixel set extraction means for extracting pixels as a reference pixel set, and non-isolated point pixel detection means for detecting a pixel that has the pixel value to be removed in the reference pixel set and is not isolated as a non-isolated point pixel And an isolated point pixel removing unit that removes a pixel that has the pixel value to be removed in the reference pixel set and is not the non-isolated point pixel as the isolated point pixel , and the non-isolated point pixel detecting unit includes: , Candidate detection means for detecting, as non-isolated point pixel candidates, a set of pixels having the removal target pixel value among pixels included in an edge of the reference pixel set, and included in the non-isolated point pixel candidates Acquisition means for acquiring a set of pixels composed of all pixels having the removal target pixel value among the pixels in the reference pixel set connected to at least one of the pixels, and the non-isolated point pixel candidate Using the replacement means for replacing the non-isolated point pixel candidate with the acquired set of pixels and the replaced non-isolated point pixel candidate when there is a difference between the acquired pixel set and the acquired set of pixels. , When there is no difference between the acquisition repeating unit that repeats the acquisition of the pixel set by the acquisition unit, and the non-isolated point pixel candidate and the acquired pixel set, the acquired pixel set and the Non-isolated point pixel setting means for setting all pixels in any of the non-isolated point pixel candidates as the non-isolated point pixels .

In order to achieve the above object, an image processing method according to claim 7 is an image processing method of an image processing apparatus for removing an isolated point pixel having a removal target pixel value from input image data. A reference pixel set extraction step for extracting pixels in the region as a reference pixel set, and non-isolation for detecting non-isolated pixels having the pixel value to be removed in the reference pixel set and not isolated and the point pixel detection step comprises the removal target pixel value of the reference pixel set in, and a isolated point pixel removal step of removing pixels the non-non-isolated point pixels as the isolated point pixels, wherein the non-isolated point The pixel detection step is a candidate detection step for detecting, as a non-isolated point pixel candidate, a set of pixels having the pixel value to be removed among pixels included in an edge of the reference pixel set. And a set of pixels including all pixels included in the non-isolated point pixel candidate and all pixels having the pixel value to be removed among pixels in the reference pixel set connected to at least one of them. And a replacement step of replacing the non-isolated point pixel candidate with the acquired set of pixels when there is a difference between the non-isolated point pixel candidate and the acquired set of pixels, There is no difference between the acquisition repeating step of repeating the acquisition of the pixel set by the acquisition step using the replaced non-isolated point pixel candidate and the non-isolated point pixel candidate and the acquired set of pixels. when, characterized in that it comprises a non-isolated point pixel setting step for setting one of the all pixels in the non-isolated point pixels of the set and the non-isolated point pixels candidates of the acquired pixel

To achieve the above object, the program according to claim 8 is a program that causes a computer to execute an image processing method of an image processing apparatus that removes isolated point pixels having a pixel value to be removed from input image data. A reference pixel set extraction module that extracts pixels in one region from the image data as a reference pixel set, and a pixel that has the pixel value to be removed and is not isolated in the reference pixel set as a non-isolated point pixel A non-isolated point pixel detecting module for detecting, and an isolated point pixel removing module for removing a pixel that has the pixel value to be removed in the reference pixel set and is not the non-isolated point pixel as the isolated point pixel , The non-isolated pixel detection module is a set of pixels having the removal target pixel value among pixels included in an edge of the reference pixel set. A candidate detection module for detecting as a non-isolated point pixel candidate, all pixels included in the non-isolated point pixel candidate, and the pixel value in the reference pixel set connected to at least one of the pixels. When there is a difference between the acquisition module that acquires a set of pixels including all the pixels and the non-isolated point pixel candidate and the acquired set of pixels, the non-isolated in the acquired set of pixels A replacement module that replaces a point pixel candidate, an acquisition repetition module that repeats acquisition of a set of pixels by the acquisition module using the replaced non-isolated point pixel candidate, and the non-isolated point pixel candidate and the acquired When there is no difference between the set of pixels and all of the acquired set of pixels and the non-isolated point pixel candidates are set as the non-isolated point pixels. Characterized in that it comprises a non-isolated point pixel setting module.

  According to the present invention, pixels in one region are extracted from image data as a reference pixel set, non-isolated point pixels in the reference pixel set are detected, and pixels other than non-isolated point pixels in the reference pixel set are detected. In addition, since the pixel having the removal target pixel value is removed as an isolated point pixel, the isolated point pixel can be accurately removed regardless of the image pattern around the isolated point pixel.

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

  FIG. 1 is a block diagram schematically showing the overall configuration of an image processing apparatus according to an embodiment of the present invention.

  In FIG. 1, the image processing apparatus 1 includes an image input unit 11, an image memory 12, an image processing unit 14, and an image output unit 13.

  The image input unit 11 acquires, for example, binary image data from an image reading device (not shown) such as a scanner, and stores it in the image memory 12.

  The image output unit 13 outputs an image held in the image memory 12.

  As shown in FIG. 2, the image processing unit 14 includes a reference pixel set extraction unit 21, a non-isolated point pixel detection unit 22, and an isolated point pixel removal unit 23.

  The reference pixel set extraction unit 21 extracts m × n (where m and n are integers of 3 or more) reference pixel sets from the images held in the image memory 12. These m and n affect the size of an isolated point that can be removed, and an isolated point having a height of m-2 or less and a width of n-2 or less can be removed using an m × n reference pixel set. Therefore, in order to remove an isolated point having a shape as shown in the pattern 104 of FIG. 10, a reference pixel set size of 5 × 4 or more is required. In this way, the size m × n of the reference pixel set may be set according to the size of the isolated point to be removed.

  As shown in FIG. 3, the non-isolated point pixel detection unit 22 has a pixel value corresponding to a pixel value (“pixel value”) of an isolated point pixel to be removed in the reference pixel set 301 obtained by the reference pixel set extraction unit 21. Hereinafter, non-isolated point pixels having “removal target pixel values”) are detected.

  Specifically, first, a set of pixels that exist at an edge surrounded by a dotted line of the reference pixel set 301 and have a pixel value to be removed is detected as a non-isolated point pixel candidate 303. Next, all the pixels that are connected to at least one pixel in the non-isolated point pixel candidate 303 in the reference pixel set 301 and have a pixel value to be removed (only one pixel of the pixel 304 in FIG. 3). And an expanded non-isolated point pixel candidate that is a set of all pixels in the non-isolated point pixel candidates. Thereafter, it is determined whether there is a difference between the enlarged non-isolated point pixel candidate and the non-isolated point pixel candidate. If there is a difference, the non-isolated point pixel candidate is replaced with the enlarged non-isolated point pixel candidate.

  Until the difference between the non-isolated point pixel candidate and the enlarged non-isolated point pixel candidate is eliminated, the acquisition of the enlarged non-isolated point pixel candidate and the replacement of the non-isolated point pixel candidate are repeated and included in the last replaced non-isolated point pixel candidate All detected pixels are detected as non-isolated point pixels.

  The isolated point pixel removing unit 23 removes isolated point pixels. Specifically, first, pixels other than the non-isolated point pixels detected by the non-isolated point pixel detection unit 22 among the pixels having the removal target pixel value included in the reference pixel set are set as isolated point pixels. Thereafter, the set isolated point pixel is converted into a pixel value different from the removal target pixel value (hereinafter referred to as “non-removal target pixel value”) and output.

  FIG. 4 is a flowchart illustrating a procedure of image processing executed by the image processing unit 14. Here, as an example, the input image is a binary image in which the pixel value of the pixel to be removed is 1, the pixel value of the other pixels is 0, and the reference pixel set is a square area of 5 × 5 pixels. In other words, an isolated point that can be removed has a pixel value of 1 and a size of 3 or less in height and 3 or less in width.

  In FIG. 4, first, an image input to the image input unit 11 is held in the image memory 12 (step S401).

  Next, 5 × 5 pixels located at the upper left reference pixel set extraction position 701 shown in FIG. 7 are extracted from the held image data as a reference pixel set (step S402).

  Next, as shown in FIG. 5, a logical product 503 of the external connection mask 501 composed of 5 × 5 data with only the edge as 1 and the pixel value of the reference pixel set 502 is calculated, and the calculated pixel is calculated. It is determined whether or not the presence of a non-isolated point pixel candidate that is a set of pixel values of 1 is detected (step S403). As a result of this determination, if the presence of a non-isolated point pixel candidate is not detected, it is determined that there is no non-isolated point pixel in the reference pixel set, and the process proceeds to step S407.

  On the other hand, when the presence of the non-isolated point pixel candidate is detected as a result of the determination in step S403, all the pixels in the non-isolated point pixel candidate and all the removal target pixel values connected to at least one of these pixels are detected. An enlarged non-isolated point pixel candidate consisting of pixels is acquired (step S404). The process of step S404 is performed by performing a logical product of pixel values with the reference pixel set 502 after the non-isolated point pixel detection unit 22 performs a process of expanding the non-isolated point pixel candidate by one pixel. The As a result, it is possible to check the connection of all the pixels in the reference pixel set 502 with the non-isolated point pixel candidates in a single process, and the process can be performed at high speed. Specifically, in the above expansion process, as shown in FIG. 6, an image 601 in which the pixel values of all the pixels in the non-isolated point pixel candidates are first set to 1 and the other is set to 0 is shifted to the left by one pixel. An image 602b shifted upward by one pixel, an image 602c shifted rightward by one pixel, and an image 602d shifted downward by one pixel are generated. Next, a logical sum of pixels at the same position is calculated using the generated four images 602 a to 602 d and the image 601, and an image 602 using the logical sum as a pixel value is obtained. Next, an image 603 composed of the logical product of the image 602 and the pixel value of each pixel of the reference pixel set 502 is acquired. A set of pixels having a pixel value of 1 (removal target pixel value) among the pixels of the image 603 is acquired as an enlarged non-isolated point pixel.

In the process of step S404, the pixels adjacent in four directions of up, down, left and right with respect to the non-isolated point pixels candidate has been determined that the pixel being connected to the pixels of the non-isolated point pixels candidate invention is not limited to this. For example, not only pixels that are vertically and horizontally adjacent but also pixels that are adjacent in an oblique direction such as upper right, upper left, lower right, and lower left may be determined as pixels connected to non-isolated point pixel candidates . In this case, as shown in FIG. 8, not only the images 602 a to 602 d in which the non-isolated point pixel candidates are set to the pixel value 1 and the others are set to 0 but shifted by one pixel vertically and horizontally are respectively generated. In addition, images 801a to 801d shifted by one pixel at the lower right and the lower left are also generated, and the logical sum of the pixels at the same position is generated by using these eight images 602a to 602d and 801a to 801d and nine images 601. Calculation is performed to obtain an image 802 using the logical sum as a pixel value. Next, an image 803 composed of a logical product of pixel values for each pixel of the image 802 and the reference pixel set 502 is acquired.

  A set of pixels having a pixel value of 1 (removal target pixel value) among the pixels of the image 803 is acquired as an enlarged non-isolated point pixel candidate.

  In step S405, it is determined whether there is a difference between the enlarged non-isolated point pixel candidate and the non-isolated point pixel candidate. If there is a difference as a result of this determination, the non-isolated point pixel candidate is replaced with the enlarged non-isolated point pixel candidate (step S405a), and the processing from step S404 is performed again. On the other hand, if there is no difference as a result of the determination in step S405, non-isolated point pixels are detected by setting all the pixels in the non-isolated point pixel candidates as non-isolated point pixels (step S406), and the process proceeds to step S407. . At this time, since the enlarged non-isolated point pixel candidate and the non-isolated point pixel candidate are equal, all the pixels in the enlarged non-isolated point pixel candidate may be set as non-isolated point pixels. Through the processes in steps S404 to S406, all the non-isolated point pixels can be reliably detected.

  In step S407, the pixel value of the portion other than the set non-isolated point pixel in the reference pixel set is rewritten to the non-removal target pixel value (here, 0) (step S407).

  Thereafter, it is determined whether or not the extraction position of the reference pixel set is the lower right corner (step S408). If the extraction position is the lower right corner, the process proceeds to step S410. On the other hand, if the result of determination in step S408 is that the extraction position is not the lower right corner, the extraction position of the reference pixel set is changed (step S409), and the processing from step S402 is repeated. Thereby, the isolated point pixel removal process can be reliably performed on the entire image.

  Here, in the process of step S409, as shown in FIG. 7, specifically, scanning is performed while shifting the reference pixel set pixel by pixel in the X direction from the upper left reference pixel set extraction position. Next, when scanning in the X direction is completed, the extraction position of the reference pixel set is returned to the left end, moved one pixel in the Y direction, and similarly scanned one by one in the X direction. This is repeated until the lower right reference pixel set extraction position shown in FIG.

  When the isolated point pixel removal processing is performed on the entire image, the binary image held in the image memory 12 is output by the image output unit 13 (step S410), and this processing ends.

  According to this processing, an area of m × n pixels (where m and n are integers of 3 or more) is extracted from the stored image data as a reference pixel set (step S402), and non-reference pixels in the reference pixel set are extracted. A non-isolated point pixel is set based on the isolated point pixel candidate (steps S403 to S406). Further, the pixel value of the portion other than the set non-isolated point pixel in the reference pixel set is rewritten to the non-removal target pixel value (step S407). Thereby, the isolated point pixel can be accurately removed regardless of the image pattern around the isolated point pixel. Further, when the size of the reference pixel set is m × n pixels, the isolated points having a height of m−2 or less and a width of n−2 or less can be removed in any shape and size.

  Furthermore, when the present image processing method is applied to a binary image as in the present embodiment, the simplest image processing instructions such as shift, AND, and OR are performed on the reference pixel set, It can consist of only one conditional branch (repeated part). Thereby, processing can be performed at high speed.

  Further, according to the present processing, the result of isolated point pixel removal does not change depending on the scanning direction as in the case of extracting a reference pixel set from input image data and searching for isolated point pixels directly in the set. Accordingly, it is not necessary to perform scanning (movement of the reference pixel set) from multiple directions, and it may be performed two-dimensionally sequentially in a predetermined direction.

  In the present embodiment, the image processing method when a binary image is input has been described. However, the present invention may be applied to multi-value images other than binary images. For example, when performing this image processing for a 256-level multi-value image, first, for example, pixel values of 0 to 64 are set as pixel values to be removed. Next, when extracting the reference pixel set, the image is expressed as a binary image of 0 and 1 depending on whether or not the pixel value is a removal target pixel value. Thereafter, processing similar to that of the binary image is performed to obtain non-isolated point pixels. In the reference pixel set, pixels having a removal target pixel value and not non-isolated point pixels, for example, an average value of pixel values of pixels having a pixel value different from the removal target pixel value in the reference pixel set, etc. By overwriting with, isolated point pixels can be removed.

  The reference pixel set is preferably a square area of m × n pixels in image processing, but the shape of the area may be polygonal or substantially circular. The present invention may be applied to image processing performed in the scanner, or may be applied to image processing on image data transferred from the scanner to a host computer such as a PC. The image processing of the present invention can be performed by hardware, but part or all of the image processing may be performed by software.

  The object of the present invention is achieved by executing the following processing. That is, a storage medium that records a program code of software that realizes the functions of the above-described embodiments is supplied to a system or apparatus, and a computer (or CPU, MPU, etc.) of the system or apparatus is stored in the storage medium. This is the process of reading the code.

  In this case, the program code itself read from the storage medium realizes the functions of the above-described embodiments, and the program code and the storage medium storing the program code constitute the present invention.

  Moreover, the following can be used as a storage medium for supplying the program code. For example, floppy (registered trademark) disk, hard disk, magneto-optical disk, CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD + RW, magnetic tape, nonvolatile memory card, ROM or the like. Alternatively, the program code may be downloaded via a network.

  Further, the present invention includes a case where the function of the above-described embodiment is realized by executing the program code read by the computer. In addition, an OS (operating system) running on the computer performs part or all of the actual processing based on an instruction of the program code, and the functions of the above-described embodiments are realized by the processing. Is also included.

  Furthermore, a case where the functions of the above-described embodiment are realized by the following processing is also included in the present invention. That is, the program code read from the storage medium is written in a memory provided in a function expansion board inserted into the computer or a function expansion unit connected to the computer. Thereafter, based on the instruction of the program code, the CPU or the like provided in the function expansion board or function expansion unit performs part or all of the actual processing.

1 is a block diagram schematically showing an overall configuration of an image processing apparatus according to an embodiment of the present invention. FIG. 2 is a block diagram schematically showing a configuration of an image processing unit in FIG. 1. It is a figure used for demonstrating the isolated point pixel removal method performed by the image process part. It is a flowchart which shows the procedure of the image process performed by an image process part. . It is a figure used for demonstrating the acquisition method of the non-isolated point pixel candidate performed by an image process part. It is a figure used for demonstrating the acquisition method of the expansion non-isolation point pixel candidate performed by the image process part. It is a figure used for demonstrating the extraction method of the reference pixel set performed by the image process part. It is a figure used for demonstrating the other acquisition method of the expansion non-isolation point pixel candidate performed by the image process part. It is a figure used for demonstrating the isolated point pixel removal method by the conventional image processing method. It is a figure which shows the various patterns of the isolated point pixel in a reference pixel area. It is a figure used for demonstrating the isolated point pixel removal method by the other conventional image processing method.

Explanation of symbols

DESCRIPTION OF SYMBOLS 11 Image input part 12 Image memory 13 Image output part 14 Image processing part 21 Reference pixel set extraction part 22 Non-isolated point pixel detection part 23 Isolated point pixel removal part

Claims (8)

In an image processing apparatus that removes isolated point pixels having a pixel value to be removed from input image data,
Reference pixel set extraction means for extracting pixels in one region from the image data as a reference pixel set;
Non-isolated point pixel detecting means for detecting pixels that have the pixel value to be removed in the reference pixel set and are not isolated as non-isolated point pixels;
An isolated point pixel removing unit that removes a pixel that has the pixel value to be removed in the reference pixel set and is not the non-isolated point pixel as the isolated point pixel ;
The non-isolated point pixel detecting means includes
Candidate detection means for detecting a set of pixels having the pixel value to be removed among pixels included in an edge of the reference pixel set as non-isolated point pixel candidates;
Acquisition means for acquiring a set of pixels including all pixels included in the non-isolated point pixel candidates and all pixels having the pixel value to be removed among pixels in the reference pixel set connected to at least one of them. When,
A replacement means for replacing the non-isolated point pixel candidate with the acquired set of pixels when there is a difference between the non-isolated point pixel candidate and the acquired set of pixels;
Using the replaced non-isolated point pixel candidate, an acquisition repeating unit that repeats acquisition of a set of pixels by the acquisition unit;
When there is no difference between the non-isolated point pixel candidate and the acquired set of pixels, all the pixels in either the acquired set of pixels and the non-isolated point pixel candidates are converted to the non-isolated point. An image processing apparatus comprising: a non-isolated pixel setting unit for setting a pixel . The one region, claim 1 Symbol mounting image processing apparatus, wherein the lateral vertical is m pixels m and n as an integer of 3 or more is an area of the square n pixels. The acquisition means determines that a pixel adjacent to the pixels in the non-isolated point pixel candidate is a pixel connected to the pixels in the non-isolated point pixel candidate in four directions, up, down, left, and right. The image processing apparatus according to claim 1 , wherein the image processing apparatus is an image processing apparatus. The acquisition unit, the vertical and horizontal with respect to pixels in the non-isolated point pixels candidates, upper left, upper right, lower left and the pixels adjacent in the eight directions of the lower right pixel in the non-isolated point pixels candidate The image processing apparatus according to claim 1 , wherein the image processing apparatus determines that the pixel is connected to the image processing apparatus. The acquisition unit, an image processing apparatus according to any one of claims 1 to 4, characterized in that the expansion process to the non-isolated point pixels candidate. The isolated point pixel removing means is an isolated point pixel setting means for setting a pixel other than the detected non-isolated point pixel among the pixels having the removal target pixel value in the reference pixel set as the isolated point pixel. the image processing apparatus according to any one of claims 1 to 5, characterized in that it comprises a pixel value converting means for converting the set pixel values of isolated point pixels in the non-removed target pixel value. In an image processing method of an image processing apparatus for removing isolated point pixels having a removal target pixel value from input image data,
A reference pixel set extraction step of extracting pixels in one region from the image data as a reference pixel set;
A non-isolated point pixel detecting step of detecting a pixel that has the pixel value to be removed in the reference pixel set and is not isolated as a non-isolated point pixel;
An isolated point pixel removing step that removes a pixel that has the removal target pixel value in the reference pixel set and is not the non-isolated point pixel as the isolated point pixel ,
The non-isolated pixel detection step includes
A candidate detection step of detecting a set of pixels having the pixel value to be removed among pixels included in an edge of the reference pixel set as a non-isolated point pixel candidate;
An acquisition step of acquiring a set of pixels including all pixels included in the non-isolated point pixel candidates and all pixels having the removal target pixel value among pixels in the reference pixel set connected to at least one of them. When,
A substitution step of replacing the non-isolated point pixel candidate with the acquired set of pixels when there is a difference between the non-isolated point pixel candidate and the acquired set of pixels;
Using the replaced non-isolated point pixel candidate, an acquisition repeating step that repeats acquisition of a set of pixels by the acquisition step;
When there is no difference between the non-isolated point pixel candidate and the acquired set of pixels, all the pixels in either the acquired set of pixels and the non-isolated point pixel candidates are converted to the non-isolated point. An image processing method comprising: a non-isolated point pixel setting step for setting a pixel . In a program that causes a computer to execute an image processing method of an image processing apparatus that removes isolated point pixels having a removal target pixel value from input image data,
A reference pixel set extraction module that extracts pixels in one region from the image data as a reference pixel set;
A non-isolated point pixel detection module that detects pixels that have the pixel value to be removed in the reference pixel set and are not isolated as non-isolated point pixels;
An isolated point pixel removal module that removes a pixel that has the pixel value to be removed in the reference pixel set and is not the non-isolated point pixel as the isolated point pixel ;
The non-isolated pixel detection module includes:
A candidate detection module for detecting, as a non-isolated point pixel candidate, a set of pixels having the removal target pixel value among pixels included in an edge of the reference pixel set;
An acquisition module that acquires a set of pixels including all pixels included in the non-isolated point pixel candidates and all pixels having the removal target pixel value among pixels in the reference pixel set connected to at least one of the pixels. When,
A replacement module for replacing the non-isolated point pixel candidate with the acquired set of pixels when there is a difference between the non-isolated point pixel candidate and the acquired set of pixels;
Using the replaced non-isolated point pixel candidate, an acquisition repeating module that repeats acquisition of a set of pixels by the acquisition module;
When there is no difference between the non-isolated point pixel candidate and the acquired set of pixels, all the pixels in either the acquired set of pixels and the non-isolated point pixel candidates are converted to the non-isolated point. A non-isolated point pixel setting module for setting a pixel .

Images