JP2019092127A - Image processing apparatus, image forming apparatus, image processing method, and image processing program - Google Patents

Abstract

To detect a thick character with high reliability in a simple configuration.SOLUTION: An image processing apparatus comprises: an image data acquisition unit that acquires image data; an image analysis unit that analyzes a plurality of pixels constituting the image data for every reference window, detects edge pixels from the plurality of pixels in the reference window, and determines a line drawing candidate area sandwiched by the edge pixels, the area satisfying a predetermined condition, as a line drawing area; and an image processing unit that executes, on the image data, image processing including first image processing applied to the line drawing area and second image processing applied to an area other than the line drawing area and different from the first image processing.SELECTED DRAWING: Figure 4

Description

  The present invention relates to an image processing apparatus, an image forming apparatus, an image processing method, and an image processing program, and more particularly to a technology for improving the image quality of characters.

  As a basic function of the image forming apparatus, there is a function of copying, that is, processing a read image which is an image read by a scanner and reproducing an image using a color material such as CMYK. A typical image forming apparatus identifies a character area and an image area in a read image, and reproduces an image of the character area with a K color material, while reproducing an image of the image area with a CMY or CMYK color material. Character regions can typically be identified by a contour detection process. However, with regard to bold letters, which are remarkably large letters, it is difficult to determine whether or not they are letter areas because the inside is apart from the outline. For such a problem, for example, Patent Document 1 detects the inside of a black character (inside of a black character edge area) as a candidate pixel area within a character, and binarizes the RGB minimum value with a predetermined threshold. A technique has been proposed for detecting a pixel area higher than the density as black character inside.

Unexamined-Japanese-Patent No. 2007-235583

  However, the inventor has found that there is room for improvement in the bold character detection method.

  The present invention has been made in view of such a situation, and an object thereof is to provide a technology for detecting bold letters with high reliability in a simple configuration.

  The image processing apparatus according to the present invention analyzes an image data acquisition unit for acquiring image data, a plurality of pixels forming the image data for each reference window, and selects edge pixels from among the plurality of pixels in the reference window. An image analysis unit that detects a line drawing candidate area which is detected between the edge pixels and determines a predetermined area as a line drawing area; first image processing applied to the line drawing area; and the line drawing area And an image processing unit that executes image processing including the second image processing different from the first image processing applied to the area of the image data.

  An image forming apparatus according to the present invention includes the image processing apparatus and an image forming unit that forms an image using a CMYK color material, the image processing unit is applied to the line drawing area, and the K color material The first image processing for forming an image using the second image processing, and the second image processing applied to an area other than the line drawing area for forming an image using a CMYK color material; Image processing is performed on the image data.

  The image processing method of the present invention comprises an image data acquisition step of acquiring image data, analyzing a plurality of pixels constituting the image data for each reference window, and edge pixels out of the plurality of pixels in the reference window. An image analysis step of detecting a line drawing candidate area sandwiched between the edge pixels and determining a line drawing area as a line drawing area, a first image processing applied to the line drawing area, and the line drawing area Performing an image process including the second image process different from the first image process applied to the area of the image data on the image data.

  The present invention provides an image processing program for controlling an image processing apparatus. The image processing program analyzes an image data acquisition unit for acquiring image data, a plurality of pixels forming the image data for each reference window, and detects an edge pixel from the plurality of pixels in the reference window. An image analysis unit that determines a line drawing candidate area that is a line drawing candidate area sandwiched between the edge pixels and that satisfies a predetermined condition as a line drawing area; first image processing applied to the line drawing area; and an area other than the line drawing area The image processing apparatus functions as an image processing unit that executes image processing including the first image processing applied to the second image processing different from the first image processing applied to the image data.

  According to the present invention, it is possible to provide a technology for detecting bold characters with high reliability in a simple configuration.

2 is a block diagram showing a functional configuration of an image forming apparatus 100 according to an embodiment of the present invention. 5 is a flowchart showing the contents of a document image copying process according to an embodiment. It is a flowchart which shows the content of the character area | region determination processing which concerns on one Embodiment. It is explanatory drawing which shows the content of the character area | region determination processing which concerns on one Embodiment. It is explanatory drawing which shows the outline extraction filter used by the character area determination process which concerns on one Embodiment. It is explanatory drawing which shows each arrangement | positioning state of the reference window which concerns on one Embodiment. It is a flowchart which shows the content of the image attribute determination processing which concerns on one Embodiment.

  Hereinafter, modes for carrying out the present invention (hereinafter, referred to as “embodiments”) will be described with reference to the drawings.

  FIG. 1 is a block diagram showing a functional configuration of an image forming apparatus 100 according to an embodiment of the present invention. The image forming apparatus 100 includes a control unit 110, an image reading unit 120, an image forming unit 130, a storage unit 140, an automatic document feeder (ADF) 160, and an operation display unit 170. The control unit 110 includes an image analysis unit 111 and an image processing unit 112.

  The control unit 110 includes a main storage unit such as a RAM and a ROM, and a control unit such as an MPU (Micro Processing Unit) and a CPU (Central Processing Unit). The control unit 110 also has a controller function related to interfaces such as various I / Os, USB (Universal Serial Bus), buses, and other hardware, and controls the entire image forming apparatus 100.

  The storage unit 140 is a storage device including a hard disk drive or a flash memory, which is a non-temporary recording medium, and stores control programs (including an image processing program) and data of processing executed by the control unit 110.

  The operation display unit 170 functions as a touch panel, and displays various menus as input screens. The operation display unit 170 further receives user's operation input from various buttons and switches (not shown).

  FIG. 2 is a flowchart showing the contents of the document image copying process according to the embodiment. In step S100, the image reading unit 120 executes a scan process. The scan process is a process of reading an original using an ADF 160 or an original table (not shown) to generate RGB image data. In this example, the image reading unit 120 and the ADF 160 (or the document table) function as an image data acquisition unit that acquires image data.

  In step S200, the image processing unit 112 executes color space conversion processing. The color space conversion process is a process of converting the color space of color image data from the RGB color space to the Lab color space. The Lab color space is a uniform color space that can represent luminance, hue, and saturation numerically, and can be said to be a scale (unit) close to human visual sense. In the Lab color space, the L value represents luminance. The hue angle is determined as the direction of a vector composed of the a value and the b value. The saturation is achromatic when the a and b values are zero, and the saturation becomes higher as their absolute value is larger. The uniform color space is a space of a color solid (corresponding to a color space) in which the distances between colors that appear to be the same color differently in the human visual system (psychological distance) are equalized.

  In step S300, the image analysis unit 111 executes character area determination processing. The character area determination process is a process of determining whether the image is a character area in the image data of the Lab color space. In the present embodiment, character area determination processing is performed on image data in the Lab color space, but the processing is not necessarily limited to execution in the Lab color space.

  FIG. 3 is a flowchart showing the contents of the character area determination process (step S300) according to the embodiment. FIG. 4 is an explanatory view showing the content of the character area determination process according to the embodiment. FIG. 4A shows an example of the so-called border phenomenon. In the border phenomenon, the original image MS represented by the scan data acquired by the image reading unit 120 is subjected to enhancement processing only on the outline portion by image processing, and the density of the edge and the inner area where bordering occurs This is a phenomenon that results in an image MP having a difference.

  Typical image processing can highlight the entire character and adjust it to a clear and easy-to-read image if the character is a normal small character. However, for a bold letter that is a letter that is significantly larger than the letter that the image processing assumes, the enhancement process is not performed in the inner area, so only the outline is emphasized and a bordering phenomenon occurs.

  In step S310, the image analysis unit 111 executes reference window arrangement processing. In reference window arrangement processing, the image analysis unit 111 arranges the reference window W1 at the top of the left end of the image M in the main scanning direction. FIG. 4B shows an example of the arrangement of reference windows used in the contour extraction process on the image M to be processed. At this time, the image analysis unit 111 secures, in a memory (not shown), a buffer area for storing the luminance values of all the pixels of the size of the reference window W1.

  The reference windows W1 to W10 have a length of 96 pixels in the main scanning direction and a width of 3 pixels in the sub scanning direction. The reference window WL is a window provided for the convenience of description and has a length of 330 pixels in the main scanning direction and a width of 3 pixels in the sub scanning direction. These reference windows W1 to W10 and WL assume the use of Sobel filters. The width in the sub scanning direction may be, for example, one pixel in the sub scanning direction, and a differential filter may be used, or a reference window with a larger width may be used, and a filter corresponding thereto may be used.

  FIG. 5 is an explanatory view showing a contour extraction filter used in the character area determination process according to an embodiment. In step S320, the image analysis unit 111 executes contour detection processing. In the outline detection process, the image analysis unit 111 includes a first Sobel filter FM for detecting an outline (also referred to as an edge) in the main scanning direction and a second Sobel filter FS for detecting an outline in the sub scanning direction. Use to detect contours. Thus, the image analysis unit 111 can detect the contours in both the main scanning direction and the sub scanning direction.

  The image analysis unit 111 can detect the contour based on the luminance value of the image data in the Lab color space using the first Sobel filter FM and the second Sobel filter FS. Thus, since edge detection is performed in a uniform color space of a scale close to human visual sense, it is possible to detect an edge as a gradation change on the basis of human visual sense. In this example, a Sobel filter is used to detect the contour, but another contour detection filter such as a Laplacian filter or a differential filter can be used to detect the contour as a step-like gradation change. .

  In step S330, the image analysis unit 111 executes contour count processing. In the contour count process, the image analysis unit 111 counts edge pixels (pixels forming the contour) detected in each reference window.

  FIG. 6 is an explanatory view showing each arrangement state of reference windows according to the embodiment. FIG. 6A shows each pixel by enlarging the state of the pixel in the reference window W1. In the reference window W1, only white pixels are present, and edge pixels are not detected. The white pixel means a pixel which has a high luminance value and is determined to be the background of the document.

  FIG. 6B shows the state of the pixel in the reference window W6. In the reference window W6, white pixels are changed to black pixels in the sub-scanning direction, and edge pixels parallel to the main scanning direction are detected as contours on the black pixel side. Therefore, the second Sobel filter FS can detect all target pixels in the reference window W6 as edge pixels.

  In step S340, the image analysis unit 111 determines whether or not the inside of the pixel of interest is all edge pixels. That is, the image analysis unit 111 determines whether the number of target pixels matches the number of edge pixels. If the number of pixels of interest matches the number of edge pixels, the image analysis unit 111 proceeds to step S 371. If the number of pixels of interest does not match the number of edge pixels, the image analysis unit 111 performs processing Proceed to step S350.

  In step S371, the image analysis unit 111 determines that the area formed of the target pixel in the reference window W6 is an edge area since the number of target pixels in the reference window W6 matches the number of edge pixels. Do. Accordingly, the image analysis unit 111 can determine that the contour parallel to the main scanning direction is a part of the character area as the edge area.

  In step S350, the image analysis unit 111 determines whether a plurality of edge pixels exist. If there are a plurality of edge pixels, the image analysis unit 111 advances the process to step S372, and advances the process to step S360 if there is a single edge pixel or no edge pixel.

  In step S372, the image analysis unit 111 extracts the end area and the area between edge pixels as a line drawing candidate area. When there are a plurality of edge pixels, there are a reference window W3 and a reference window WL (see FIG. 4). The end area is an area sandwiched between edge pixels and end pixels. The end pixel is a pixel disposed at the end of the reference window. The edge inter-pixel area is an area sandwiched by two edge pixels.

  Specifically, as shown in FIG. 6C, the reference window W3 has two end areas Z3 e1 and Z3 e2 and one edge inter-pixel area Z3 m. The end area Z3e1 is an area sandwiched between the end pixel W3e1 and the edge pixel C31. The end area Z3e2 is an area sandwiched between the edge pixel C32 and the end pixel W3e2.

  The reference window WL has two end areas ZLe1 and ZLe2 and three edge inter-pixel areas ZLm1 and ZLm2 and ZLm3 as shown in FIG. 6 (d). The end area ZLe1 is an area sandwiched between the end pixel WLe1 and the edge pixel CL1. The end area ZLe2 is an area sandwiched between the edge pixel CL4 and the end pixel WLe2.

  In step S360, the image analysis unit 111 determines whether only one edge pixel is present alone. If there is only one edge pixel, the image analysis unit 111 proceeds to step S373. If there is no edge pixel, the image analysis unit 111 proceeds to step S374.

  In step S373, the image analysis unit 111 extracts the end region as a line drawing candidate region. When there is one edge pixel, there are a reference window W4 and a reference window W5 (see FIG. 4). The reference window W5 has two end regions Z5e1 and Z5e2 as shown in FIG. 6 (f). The end area Z5e1 is an area sandwiched between the end pixel W5e1 and the edge pixel C51. The end area Z5e2 is an area sandwiched between the edge pixel C51 and the end pixel W5e2.

  In step S 374, the image analysis unit 111 extracts all the target pixels as an intermediate region (an example of a line drawing candidate region). Reference windows W1, W2, W8 and W9 (see FIG. 4) exist as cases where there is no edge pixel. The middle region is a region in which there is no edge pixel in the reference window and is sandwiched by two end pixels.

  FIG. 7 is a flowchart showing the contents of the image attribute determination process (step S380) according to one embodiment. In step S 381, the image analysis unit 111 determines whether each area to be determined is an edge area.

  If the area to be determined is an edge area, for example, as in the area including the pixel of interest in the reference window W6, the image analysis unit 111 advances the process to step S387. In step S387, the image analysis unit 111 determines that the area to be determined is a text area. On the other hand, if the area to be determined is not an edge area, the image analysis unit 111 advances the process to step S382.

  In step S382, the image analysis unit 111 determines whether each area to be determined is an inter-edge pixel area. The image analysis unit 111 advances the process to step S385a if each area to be determined is an inter-edge pixel area, as in the inter-edge pixel area Z3m in the reference window W3, for example. The edge inter-pixel area Z3m is an area sandwiched between two edge pixels C31 and C32 in the reference window W3. On the other hand, if the areas to be determined are not the inter-edge pixel areas, the image analysis unit 111 advances the process to step S383.

  In step S385a, the image analysis unit 111 determines whether the saturation of the pixel value of each area to be determined is less than a predetermined threshold Th. Specifically, the image analysis unit 111 determines, for example, whether or not the sum of the absolute values of the a value and the b value in the Lab color space of each pixel constituting the inter-edge pixel area Z3m is less than the threshold value Th. If the sum of absolute values is less than the threshold Th, the image analysis unit 111 proceeds to step S387. If the sum of absolute values is not less than the threshold Th, the image analysis unit 111 proceeds to step S388.

  In step S387, the image analysis unit 111 determines that the area to be determined is a text area, as in the case of the edge area. On the other hand, in step S388, the image analysis unit 111 determines that the area to be determined is an image area. In the present embodiment, the image area means an area other than black characters. In the present embodiment, the character area is assumed to be a black character, and the determination is made using saturation.

  In step S383, the image analysis unit 111 determines whether each area to be determined is an end area. The image analysis unit 111 advances the process to step S 385 b if the areas to be determined are end areas, such as two end areas Z 5 e 1 and Z 5 e 2 in the reference window W 5. On the other hand, if the areas to be determined are not end areas, the image analysis unit 111 advances the process to step S384.

  In step S385b, the image analysis unit 111 determines whether the saturation of the pixel value of each area to be determined is less than the threshold Th. If the sum of absolute values is less than the threshold Th, the image analysis unit 111 proceeds to step S386a. If the sum of absolute values is not less than the threshold Th, the image analysis unit 111 proceeds to step S388. In this example, it is assumed that the image analysis unit 111 determines that the saturation of the pixel value of the end region Z5e1 is less than the threshold Th.

  In step S386a, the image analysis unit 111 determines whether the saturation of the pixel value of the adjacent area of the end area Z5e1 is less than the threshold Th. The adjacent area of the end area Z5e1 is an end area Z4e2 in the reference window W4. This is because the end pixel W4e2 of the reference window W4 is an adjacent pixel adjacent to the end pixel W5e1 of the reference window W5 (see FIGS. 4 and 6).

  The end area Z4e2 is an area between an edge pixel C41 (also referred to as an adjacent edge pixel) of the reference window W4 and the end pixel W4e2. When the image analysis unit 111 determines that the saturation of the pixel value of the end area Z4e2 is less than the threshold Th (that is, the saturation of both the end area Z5e1 and the adjacent area (end area Z4e2) is the threshold Th If less than the case, the process proceeds to step S387, and it is determined that the saturation of the pixel value of end region Z4e2 is not less than threshold Th (generally, end region Z5e1 and an adjacent region (end region Z4e2) If at least one of the saturations is not smaller than the threshold Th), the process proceeds to step S388.

  In step S387, the image analysis unit 111 determines that the end area Z4e2 and the end area Z5e1 are continuous character areas. On the other hand, in step S388, the image analysis unit 111 determines that the end area Z4e2 and the end area Z5e1 are image areas.

  In step S384, the image analysis unit 111 determines that each area to be determined is an intermediate area. As described above, when the image analysis unit 111 determines that each area to be determined is an intermediate area (no edge pixel is present), as in the reference windows W1, W2, W8, and W9 (see FIG. 4), for example. The process then proceeds to step S385c.

  In step S385c, the image analysis unit 111 determines whether the saturation of the pixel values in both adjacent regions is less than the threshold Th. The two adjacent areas are adjacent to the end pixels at both ends of the intermediate area, and are adjacent to the edge pixels (or the end pixels of the image M) across the adjacent reference windows (or plural adjacent reference windows). Region composed of a plurality of pixel groups.

  Specifically, for the intermediate region in the reference window W8, both adjacent regions are referenced from the pixel group from the end pixel of the reference window W8 to the edge pixel C71 of the reference window W7 and the end pixel of the reference window W8 It is a pixel group up to the edge pixel C10 of the window W10.

  In step S386b, the image analysis unit 111 determines whether the saturation of the pixel values of both adjacent regions is less than the threshold Th. If the image analysis unit 111 determines that the saturation of the pixel values of both adjacent regions is less than the threshold Th, the process proceeds to step S 387, and the saturation of at least one pixel value of both adjacent regions is the threshold Th If it is determined not, the process proceeds to step S388.

  In step S387, the image analysis unit 111 determines that the intermediate region and both adjacent regions configured as a pixel group from the edge pixel C71 to the edge pixel C10 are character regions. On the other hand, in step S388, the image analysis unit 111 determines that the intermediate region and both adjacent regions are image regions.

  The image analysis unit 111 analyzes up to the final pixel of the image M while shifting the reference window, for example while shifting in the main scanning direction (for example, shifting from the reference window W1 to the reference window W2) and the subscanning direction. The determination (steps S310 to S380) is repeatedly performed for each reference window (step S390).

  At this time, the image analysis unit 111 secures a buffer area in a memory (not shown) so that the pixel values of adjacent areas or both adjacent areas can be used for determination, and sequentially releases them when the determination process is completed. be able to. Thereby, the image analysis unit 111 can realize efficient use of the memory. When the process is completed on all the pixels of the image M, the image analysis unit 111 advances the process to step S400 (see FIG. 2).

  In step S400, the image analysis unit 111 determines whether each area of the image M is a text area, advances the process to step S500 for the text area, and step S600 for the image area. Advance to

  In step S500, the image processing unit 112 executes image processing for the text area on the text area, and generates gradation data representing the density of the K color material. The image processing for the character area includes color conversion processing for reproducing with the K color material. In step S600, the image processing unit 112 executes image processing for the image area on the image area, and generates gradation data representing the density of the CMY or CMYK color material. Image processing for the image area includes color conversion processing for reproduction with a CMY or CMYK color material.

  In step S700, the image forming unit 130 forms an image on the print medium based on the CMYK gradation data. The CMYK tone data is generated from the CMYK tone data by halftone processing.

  As described above, according to the image forming apparatus 100 according to the embodiment, a technology for detecting bold characters with high reliability with a simple configuration is provided. As a result, the image forming apparatus 100 can accurately reproduce the gradation of an image such as a natural image while suppressing the so-called border phenomenon and clearly reproducing bold characters.

C. Modification:
The present invention can be implemented not only in the above-described embodiments but also in the following modifications.

  Modification 1: In the above embodiment, as a predetermined condition for determining that the character area is a character area, when the saturation of the area between the edge pixels is low, for example, the direction of the edge is determined. May be specified and used for determination. The direction of the edge is the direction of the change of the pixel value bordering on the edge. Specifically, in the direction of the edge, there are white to black (the decrease direction of the brightness value) and black to white (the increase direction of the brightness value). That is, the character area is present in an area sandwiched by edge pixels in the direction in which the luminance decreases.

  In other words, since the character area is assumed to be a black character, the area sandwiched between the edge pixel having the decreasing direction of the luminance value and the edge pixel having the increasing direction of the luminance value is regarded as the character area. Can. Furthermore, an area between an edge pixel and an end pixel having a decreasing direction of the luminance value may form a character area together with the pixels in the adjacent reference window. Such a method can also be combined with a determination method using saturation.

  For example, in the reference window WL, there are two end areas ZLe1 and ZLe2 and three edge inter-pixel areas ZLm1, ZLm2 and ZLm3 (see FIGS. 4 and 6D). In this case, the image analysis unit divides the edge interpixel region ZLm1 between the edge pixel CL1 (the decrease direction of the brightness value) and the edge pixel CL2 (the increase direction of the brightness value) and the edge pixel CL3 (the decrease direction of the brightness value) It can be easily determined based on the direction of the edge that the inter-edge pixel area ZLm3 between the pixel and the edge pixel CL4 (the direction in which the luminance value increases) is a character area.

  Variation 2: In the above embodiment, the present invention is applied to a character area representing black characters, but the present invention is not necessarily limited to black characters. The present invention may assume a line drawing area including black characters and black line drawings. Thus, the image forming apparatus can suppress the so-called border phenomenon and can reproduce the line drawing area clearly. Furthermore, the present invention provides design freedom and parameter adjustment (or user interface for parameter adjustment) that enables processing suitable for characters and line drawings of various sizes by adjusting the size of the reference window. You can also.

  Modification 3: In the above embodiment, the image processing unit 112 executes image processing (also referred to as first image processing) for the line drawing area on the line drawing area, and indicates the gradation representing the density of the K color material. Data is generated and image processing for the image area is performed on the image area. However, the present invention is not limited to such image processing, and as the image processing for the line drawing area, at least one of filter processing for the line drawing area, color conversion processing, UCR processing and gradation correction processing is other than the line drawing area including the image area. It may be different from the processing for another area (also referred to as second image processing).

  Modification 4: In the above embodiment, the present invention is applied to an image forming apparatus, but may be applied to an image processing apparatus.

100 image forming apparatus 110 control unit 111 image analysis unit 112 image processing unit 120 image reading unit 130 image forming unit 140 storage unit 160 automatic document feeder (ADF)
170 Operation Display

Claims (8)

An image data acquisition unit that acquires image data;
A plurality of pixels constituting the image data are analyzed for each reference window, an edge pixel is detected from among the plurality of pixels in the reference window, and a line drawing candidate region sandwiched by the edge pixels is a predetermined condition An image analysis unit that determines an area to be satisfied as a line drawing area;
Image processing including the first image processing applied to the line drawing area and the second image processing different from the first image processing applied to the area other than the line drawing area on the image data An image processing unit to execute
An image processing apparatus comprising: The image processing apparatus according to claim 1,
The image processing device, wherein the image analysis unit determines the line drawing candidate area as the line drawing area when the saturation of the pixels forming the line drawing candidate area is less than a preset threshold as the predetermined condition. The image processing apparatus according to claim 1 or 2, wherein
The image analysis unit, when the edge pixel is detected alone in the reference window, the edge pixel and an adjacent edge pixel which is an edge pixel detected in another reference window adjacent to the reference window An image processing apparatus for extracting an area sandwiched between the lines as the line drawing candidate area. The image processing apparatus according to any one of claims 1 to 3, wherein
The image analysis unit extracts, in the reference window, an end area which is an area sandwiched between an end pixel which is an end pixel to which the reference window refers and an edge pixel, and An adjacent area is extracted which is an area between an adjacent edge pixel which is an edge pixel detected in another reference window referring to an adjacent pixel which is an adjacent pixel and the adjacent pixel, and the end area and the adjacent area are extracted. The image processing apparatus determines the end area and the adjacent area as the line drawing area when both of the above conditions satisfy the predetermined condition. The image processing apparatus according to any one of claims 1 to 4, wherein
The image processing unit, when detecting the edge pixel, identifies a direction in which the luminance changes, and determines an area sandwiched between the edge pixels in the direction in which the luminance decreases as the line drawing area. An image processing apparatus according to any one of claims 1 to 5,
An image forming unit that forms an image using a CMYK color material;
Equipped with
The image processing unit is applied to the line drawing area, the first image processing for forming an image using a K color material, and is applied to an area other than the line drawing area, and the CMYK color material is applied. An image forming apparatus that executes image processing on the image data, including the second image processing to form an image using the image processing. An image data acquisition step of acquiring image data;
A plurality of pixels constituting the image data are analyzed for each reference window, an edge pixel is detected from among the plurality of pixels in the reference window, and a line drawing candidate region sandwiched by the edge pixels is a predetermined condition An image analysis step of determining a filled area as a line drawing area;
Image processing including the first image processing applied to the line drawing area and the second image processing different from the first image processing applied to the area other than the line drawing area on the image data An image processing process to be performed;
An image processing method comprising: An image processing program for controlling an image processing apparatus, comprising:
Image data acquisition unit for acquiring image data,
A plurality of pixels constituting the image data are analyzed for each reference window, an edge pixel is detected from among the plurality of pixels in the reference window, and a line drawing candidate region sandwiched by the edge pixels is a predetermined condition An image analysis unit that determines a filled area as a line drawing area; a first image processing applied to the line drawing area; and a second image different from the first image processing applied to an area other than the line drawing area An image processing program that causes the image processing apparatus to function as an image processing unit that executes image processing including processing on the image data.