JP6852618B2 - Computer programs and image processing equipment - Google Patents

Description

The present specification relates to a technique for determining whether or not the color of a part of an image should be corrected.

Conventionally, image data indicating a document has been generated by using an image reading device such as a scanner. Further, a technique has been proposed in which a part of the image data showing a defect such as a cut portion of a document is masked by correcting the color.

Japanese Unexamined Patent Publication No. 2001-169081

By the way, as the image data, in addition to the original, image data indicating an image including a margin arranged outside the original may be used. When processing image data indicating an image including margins in this way, there is room for ingenuity in determining whether or not to correct the color of a part of the image.

The present specification discloses a technique capable of appropriately determining whether or not to correct the color of a part of an image including a manuscript and a margin arranged outside the manuscript.

The present specification discloses, for example, the following application examples.

[Application Example 1] A program, which is a program and has an acquisition function of acquiring the scanned image data indicating a scanned image including a document and a margin arranged outside the document, which is generated by optically scanning the document. A side identification function for identifying four sides of a rectangular document area obtained by dividing a portion of the scanned image including the document into a rectangular area by analyzing the scanned image data, and a side identification function of the four sides. A candidate area identification function for specifying a candidate area that is a candidate for an area that is not the original and is a region in the rectangular original area that touches any of the sides, and whether or not the color of the candidate area should be corrected. The first determination function for determination and the partial margin area which is the area indicating the margin and constitutes at least a part of the margin area which is the area outside the rectangular document area, and which are mutual of the four sides. The second judgment function for determining whether or not to correct the color for each of the one or more partial margin areas in contact with different sides, the result of the judgment by the first judgment function for the candidate area, and the one or more parts. Using the result of the judgment by the second judgment function for each of the margin areas, the selection correction processing, which is the processing for correcting the color of the area where it is determined that the color should be corrected, is executed, and the selection correction is performed. A computer is realized with an image generation function for generating output image data indicating an output image including each of the processed rectangular original area and the one or more partial margin areas after the selection correction processing, and the second. The judgment function is an area that constitutes an area having a predetermined continuous relationship with the attention area margin area, and the color should not be corrected for at least one area of the partial margin area and the candidate area. When it is determined, the condition for determining that the color of the attention portion margin area should not be corrected and determining that the color of the attention portion margin region should be corrected by the second determination function is as described above. The region constituting the region having a predetermined continuous relationship with the attention portion margin region of the one or more partial margin regions and the candidate region includes an region where it is determined that the color should not be corrected. Computer programs, including not.

According to this configuration, when it is determined that the color should not be corrected for the area having a predetermined continuous relationship with the attention area margin area, it is determined that the color of the attention area margin area should not be corrected. To. Then, the condition for determining that the color of the attention portion margin region should be corrected is that the partial margin region and the candidate region constituting the region having a predetermined continuous relationship with the attention portion margin region correct the color. Includes not including areas that should not be included. As a result, it is possible to prevent the region where the color is corrected from coming into contact with the region where the color is not modified. As a result, the noticeable color difference between the color-corrected area and the color-uncorrected area is suppressed.

[Application Example 2] In the computer program according to the application example 1, the condition for the first determination function to determine that the color of the candidate area should not be corrected is the condition in which the candidate area is in contact with the candidate area. A computer program including that the length of the candidate region from the side is equal to or greater than the first threshold.

If the color of a large candidate area is corrected, the area where the color is corrected is large, so that the area where the color is corrected may look unnatural. According to the above configuration, it is determined that the color should not be corrected for the large candidate area, so that it is possible to suppress that the color-corrected area looks unnatural.

[Application Example 3] The computer program according to Application Example 1 or 2, wherein the determination function of determining the width of each of the one or more partial margin areas in the output image is performed according to a user's instruction. The condition for the second determination function to determine that the color of the partial margin area should not be corrected by a computer is that the width of the partial margin area determined according to the user's instruction is the first. A computer program that includes being greater than or equal to two thresholds.

If the color of the large partial margin area is corrected, the color-corrected area may look unnatural because the color-corrected area is large. According to the above configuration, it is determined that the color should not be corrected for the large partial margin area, so that it is possible to prevent the color-corrected area from appearing unnatural.

[Application Example 4] In the computer program according to any one of Application Examples 1 to 3, in the second determination function, (A) the attention portion margin area should correct the color of the partial margin region. It is determined whether or not the non-target tentative condition for tentatively determining that the color is not satisfied, and (B) if the attention portion margin area does not satisfy the non-target tentative condition, a candidate in contact with the attention portion margin area. It is determined whether or not zero or more adjacent candidate regions, which are regions, include a non-target candidate region, which is a candidate region for which it is determined that the color of the candidate region should not be corrected, and the adjacent candidate region is said to be said. When it is determined that the color of the attention portion margin area should not be corrected when the non-target candidate region is included, (C) the adjacent candidate when the attention portion margin area satisfies the non-target provisional condition. A computer program that determines that the color of the area of interest should not be modified without determining whether the area includes the non-target candidate area.

According to this configuration, even if the attention portion margin area does not satisfy the non-target provisional condition, that is, even if it can be determined that the color of the attention portion margin area should be corrected, the adjacent candidate area is the non-target candidate area. In the case of including, since it is determined that the color of the margin area of interest should not be corrected, it is suppressed that the candidate area where the color is not corrected is adjacent to the margin where the color is corrected. As a result, it is suppressed that the candidate area where the color is not corrected is conspicuous. In addition, when the attention area margin area satisfies the non-target provisional condition, it is determined that the color of the attention area margin area should not be determined without determining whether or not the adjacent candidate area includes the non-target candidate area. Therefore, it is possible to make an appropriate judgment while suppressing a decrease in processing speed.

[Application Example 5] In the computer program according to any one of Application Examples 1 to 4, the second determination function determines whether or not each color of the partial margin area of 1 or more should be corrected. If it is tentatively determined independently of the partial margin area and it is determined that the color of the attention partial margin area should be corrected, the partial margin area adjacent to the attention portion margin area and the width larger than the reference width is in contact with the attention portion margin area. It is tentatively determined that at least one of the opposed portion margin region having a width larger than the reference width, which is in contact with the adjacent partial margin region and is located opposite to the attention portion margin region, should not be corrected in color. If it is determined whether or not the color should be corrected for at least one of the adjacent partial margin area and the opposite partial margin area, the color of the attention partial margin area should be corrected. A computer program that determines that it is not.

According to this configuration, even if it can be determined that the color of the partial margin area should be corrected, when it is determined that the color of the other partial margin area in contact with the partial margin area of interest should not be corrected. Since it is determined that the color of the attention portion margin region should not be corrected, the contact between the partial margin region where the color is corrected and the partial margin region where the color is not corrected is suppressed. As a result, it is suppressed that the color difference is conspicuous due to the contact between the partial margin area where the color is corrected and the partial margin area where the color is not corrected.

[Application Example 6] In the computer program according to any one of Application Examples 1 to 5, the candidate area specifying function uses the rectangular original area without using the margin area of the scanned image. A computer program that identifies the candidate area.

According to this configuration, it is possible to make an appropriate judgment while suppressing a decrease in processing speed.

The techniques disclosed in the present specification can be realized in various aspects, for example, an image processing method and an image processing device, a computer program for realizing the functions of those methods or devices, and a computer thereof. It can be realized in the form of a recording medium on which the program is recorded (for example, a recording medium that is not temporary).

It is a figure which shows the structure of the image processing system as one Example. It is a flowchart which shows the example of image processing. It is a figure which shows an example of the image used in image processing. It is a flowchart which shows the example of the process of the determination of a candidate area. It is a flowchart which shows the example of the repair process. It is a flowchart which shows the example of the process of the provisional determination of a partial margin area. It is a flowchart which shows the example of the processing of the final determination of a partial margin area. It is explanatory drawing which shows the processing example of another image. It is explanatory drawing which shows the processing example of another image.

A. First Example:
A-1. Configuration of Image Processing System FIG. 1 is a diagram showing a configuration of an image processing system as an embodiment. This image processing system includes an image processing device 800 and a scanner 900. The image processing device 800 and the scanner 900 are connected to the network NT and can communicate with each other.

The image processing device 800 is, for example, a personal computer (for example, a desktop computer or a tablet computer). The image processing device 800 includes a CPU 810 as a controller of the image processing device 800, a storage device 815, a display unit 840 for displaying an image, an operation unit 850 for accepting an operation by a user, and an interface 890. .. The storage device 815 includes a volatile storage device 820 and a non-volatile storage device 830. These elements are connected to each other via a bus.

The CPU 810 is an arithmetic unit (processor) that processes data. The volatile storage device 820 is, for example, a DRAM, and the non-volatile storage device 830 is, for example, a flash memory. The non-volatile storage device 830 stores the program 832. By executing the program 832, the CPU 810 causes the scanner 900 to read the document and executes a process of generating output image data indicating the scanned document (details will be described later). Program 832 may be, for example, a scanner driver for controlling the scanner 900. The CPU 810 temporarily stores various intermediate data used for executing the program 832 in the storage device 815 (for example, either the volatile storage device 820 or the non-volatile storage device 830). Program 832 is provided, for example, by the manufacturer of Scanner 900.

The display unit 840 is a device for displaying an image, for example, a liquid crystal display. Instead of this, other types of devices that display images, such as LED displays and organic EL displays, may be employed. The operation unit 850 is a device that receives an operation by the user, and is, for example, a touch panel that is superposed on the display unit 840. Alternatively, other types of devices operated by the user, such as buttons and levers, may be employed. The user can input various instructions to the image processing device 800 by operating the operation unit 850.

Interface 890 is an interface for communicating with other devices (eg, USB interface, wired LAN interface, IEEE 802.11 wireless interface). In this embodiment, the interface 890 is a wired or wireless network interface and is connected to the network NT.

FIG. 1 shows a perspective view of the scanner 900. In the figure, the first direction Dp1 and the second direction Dp2 indicate a horizontal direction, and the third direction Dp3 indicates a vertically upward direction. The first direction Dp1 and the second direction Dp2 are perpendicular to each other. Further, the third direction Dp3 is also referred to as an upward Dp3.

The scanner 900 is a so-called flatbed type image reading device. The scanner 900 includes a main body 990 and a cover 950 attached to the upper Dp3 side of the main body 990 so as to be openable and closable. FIG. 1 shows a scanner 900 with a cover 950 opened toward Dp3 in the upward direction.

The main body 990 includes a control unit 910, an image sensor 920 that optically reads a document, a moving device 930 that moves the image sensor 920 in parallel with the first direction Dp1, and a document stand 940.

The platen 940 is provided on the upward Dp3 side of the main body 990 (FIG. 1). The platen 940 appears by opening the cover 950 upward Dp3. The document table 940 is a substantially rectangular table surrounded by two sides parallel to the first direction Dp1 and two sides parallel to the second direction Dp2, and is configured by using a transparent plate (for example, a glass plate). There is. The surface of the platen 940 on the third direction Dp3 side is the mounting surface Us on which the document to be read is placed.

The image sensor 920 is arranged below the platen 940 (opposite the third direction Dp3), that is, below the platen 940. The image sensor 920 is a one-dimensional image sensor that optically reads a document, and has a configuration in which a plurality of photoelectric conversion elements (simply also referred to as optical elements) such as a CCD or CMOS are arranged side by side in the second direction Dp2. Have. The image sensor 920 optically reads the document on the platen 940 to output a signal indicating the scanned document.

The mobile device 930 includes a power source (eg, an electric motor). The moving device 930 uses the power source to move the image sensor 920 in a direction along the mounting surface Us of the platen 940 (a direction parallel to the first direction Dp1 in FIG. 1).

The control unit 910 is, for example, a computer including a CPU 911 that performs data processing, a storage device 915, and an interface 919. The storage device 915 includes a volatile storage device 912 (for example, DRAM) and a non-volatile storage device 913 (for example, flash memory). Each element of the control unit 910 is connected to each other via a bus. The non-volatile storage device 913 stores the program 914 in advance. The CPU 911 controls the image sensor 920 and the mobile device 930 by executing the program 914. Interface 919 is an interface for communicating with other devices (eg, USB interface, wired LAN interface, IEEE 802.11 wireless interface). In this embodiment, the interface 919 is a wired or wireless network interface and is connected to the network NT.

The CPU 911 controls the moving device 930 to move the image sensor 920 along the platen 940 from the position of the end of the platen 940 opposite to the first direction Dp1 to the position of the end of the platen 940 on the first direction Dp1 side. To move. The CPU 911 controls the image sensor 920 while moving the image sensor 920 to optically read the document placed on the platen 940. The CPU 911 generates scanned image data indicating the scanned image based on the signal output from the image sensor 920. The CPU 911 transmits the generated scanned image data to the image processing device 800.

A-2. Image processing:
FIG. 2 is a flowchart showing an example of image processing. In this embodiment, the CPU 810 of the image processing apparatus 800 executes image processing as a scanner driver. In this image processing, scanned image data is acquired by causing the scanner 900 to scan the original, and the acquired scanned image data is used to generate output image data indicating an output image in which a defect has been repaired. As will be described later, the output image includes a document and a margin arranged outside the document.

In S100, the user inputs an instruction to start image processing by operating the operation unit 850. Further, in this embodiment, the user inputs the width of the margin. The user can specify the width of the margins to be provided on each of the four sides of the rectangular document. The width of the margin may be selected by the user from a plurality of settings prepared in advance. Alternatively, the user may enter a numerical value indicating the width of the margin (for example, a numerical value in millimeters). The CPU 810 determines the width of the margin to the input value in response to the input instruction. Then, the CPU 810 starts image processing in response to the start instruction.

In S105, the CPU 810 acquires the read image data. Specifically, the CPU 810 transmits an instruction to read the document to the scanner 900. The CPU 911 of the control unit 910 of the scanner 900 generates scanned image data by reading the document placed on the platen 940 in response to an instruction from the image processing device 800, and obtains the generated scanned image data as an image. It is transmitted to the processing device 800. The CPU 810 acquires the scanned image data transmitted from the scanner 900. The data format of the scanned image data may be various formats. In this embodiment, the scanned image data is RGB image data including RGB values of a plurality of pixels, or monochrome image data including brightness values of a plurality of pixels. The RGB value of one pixel indicates the color of that pixel, and for example, the three component values of red (R), green (G), and blue (B) (hereinafter, R value, G value, and B value). Also called). In this embodiment, the number of gradations of each component value is 256 gradations. The luminance value is a value indicating the luminance of the pixel, for example, as a value of 256 gradations. The data format of the scanned image data is selected according to the user's instruction.

FIG. 3 is a diagram showing an example of an image used in image processing. FIG. 3A shows an example of the scanned image. The shape of the scanned image 110 is a rectangular shape surrounded by a straight line parallel to the first direction D1 and a straight line parallel to the second direction D2. The plurality of pixels showing the scanned image 110 are arranged in a grid pattern along these directions D1 and D2.

The scanned image 110 is an image generated by scanning a rectangular original. The scanned image 110 includes a manuscript image 21 showing a manuscript and an outer image 31 which is an image outside the manuscript image 21. The outer image 31 shows a region other than the original document outside the original image 21. The outer image 31 is an image located between the outer image of the original image 21, that is, the outer edge of the original image 21 and the outer edges (four sides) of the scanned image 110. The outer image 31 shows the facing surface Bs of the cover 950 (FIG. 1) facing the platen 940 in this embodiment. In this embodiment, the facing surfaces Bs are painted in gray, which is darker than white and lighter than black. Therefore, the outer image 31 is a gray, substantially monochromatic image.

The shape of the original image 21 is an incomplete substantially rectangular shape including the tear 211. The tear 211 is a missing portion extending inward from the outer edge of the original image 21. Further, the manuscript image 21 includes an object Ob such as characters and a background Bg. The background Bg is a region of the ground color of the document.

In S110 (FIG. 2), the CPU 810 identifies four sides of a rectangular region indicating the original in the scanned image. FIG. 3B is an explanatory diagram showing an example of four sides 411 to 414 identified from the scanned image 110. In the figure, the same scanned image 110 as in FIG. 3A is shown. The sides 411 to 414 form a rectangle indicating the outer edge of the original image 21. Hereinafter, the rectangular area surrounded by the sides 411 to 414 is referred to as a rectangular document area 210. The rectangular contour 410 of the rectangular document area 210 is composed of four sides 411 to 414. Further, the area 310 outside the rectangular document area 210 in the scanned image 110 is referred to as a margin area 310. The margin area 310 indicates the outer margin of the original image 21. The tear 211 is included in the rectangular document area 210.

Various methods can be adopted as a method for specifying the four sides 411 to 414 of the rectangular document area 210. For example, the CPU 810 executes the following processing. The CPU 810 executes a reduction process on the scanned image data to generate reduced image data indicating the reduced image which is the reduced scanned image. The reduction process is a process for reducing the pixel density, and may be various known processes. For example, a process of thinning out some pixels may be adopted. Further, a process of calculating the color value of each of a plurality of pixels arranged at a low pixel density on the scanned image by interpolation using the color values of the plurality of pixels of the scanned image may be adopted.

The CPU 810 executes an edge extraction process for extracting edge pixels in the reduced image. The edge extraction process is a process for extracting edge pixels indicating edges in an image, and may be various known processes. For example, the edge strength of each pixel is calculated, and pixels having an edge strength equal to or higher than a threshold value may be extracted as edge pixels. Various edge detection operators such as a sobel operator and a prewit operator can be used to calculate the edge strength. In the example of FIG. 3B, in addition to the plurality of pixels indicating the outer edge (that is, the contour) of the original image 21, various pixels such as the plurality of pixels indicating the outer edge of the object Ob are extracted as edge pixels. Can be done.

The CPU 810 executes a Hough transform using the extracted plurality of edge pixels, and identifies a candidate for a straight line indicating the outer edge of the original image 21. Since the Hough transform is a known process, its description will be omitted. As candidates for the straight line, in addition to the straight line indicating the outer edge of the original image 21, various straight lines such as a straight line indicating the edge of the tear 211 and a straight line indicating the outer edge of the object Ob are specified.
The CPU 810 selects four candidate straight lines forming a rectangular shape from the specified candidate straight lines as edge straight lines that are straight lines indicating the outer edge of the original image 21. Various methods may be used for selecting four edge straight lines indicating the outer edges of the original image 21 from the plurality of candidate straight lines. For example, four candidate straight lines forming a rectangular shape are selected as the four edge straight lines. The four candidate straight lines selected correspond to the four sides of the rectangle, respectively. When a plurality of combinations of the four candidate straight lines form a rectangular shape, the four candidate straight lines forming the largest rectangular shape may be selected.

The four edge lines selected indicate the outline of the original image 21 on the reduced image. The CPU 810 positions the four straight lines corresponding to the four edge straight lines in the reduced image in the scanned image 110 (that is, in the scanned image 110 at the same positions as the four edge straight lines in the reduced image). ), Identify the four straight lines. As a result, the four sides of the rectangular document area (for example, the four sides 411 to 414 of FIG. 3B) are specified. As described above, the CPU 810 specifies the four sides 411 to 414 of the rectangular document area 210 obtained by dividing the portion including the document in the scanned image 110 into a rectangular area. In this embodiment, the rectangular document area 210 is the smallest rectangular area including the document.

The edge straight line may be specified by using a scanned image instead of using a reduced image. However, when a reduced image is used, the number of pixels used to identify the edge straight line is small, so that the processing load can be reduced.

In S120 (FIG. 2), the CPU 810 identifies a candidate area that is a candidate area within the rectangular document area and not the document. In the example of FIG. 3B, the area 213 showing the tear 211 is an area within the rectangular document area 210, not a document. Various methods may be used to identify such a candidate region. In this embodiment, the CPU 810 specifies a candidate area by binarizing the rectangular document area. Specifically, the CPU 810 has a plurality of pixels in a region corresponding to a rectangular original region in the reduced image, a first-class pixel having a brightness within a specific luminance range, and a first-class pixel having a luminance outside the specific luminance range. The binarization process of dividing into two types of pixels is executed. The specific luminance range is a predetermined luminance range, and is a range including the luminance of the color of the facing surface Bs of the cover 950 (FIG. 1). The first-class pixels show a color similar to the color of the facing surface Bs of the cover 950.

The CPU 810 selects, as a candidate region, a region in contact with the edge straight line among the regions in the reduced image in which the first-class pixels are continuous. Objects in the manuscript may include a portion of color similar to the color of the facing surface Bs of the cover 950. In this case, that part of the object is also indicated by the first-class pixels. Normally, the objects in the manuscript are located inside the outer edge of the manuscript. Therefore, the region in which the first-class pixels are continuous and in contact with the edge straight line is likely to indicate a missing portion of the document, such as region 213 of the tear 211.

The identified candidate area is an area on the reduced image. The CPU 810 specifies an area in the scanned image 110 corresponding to the candidate area in the reduced image (that is, an area in the scanned image 110 located at the same position as the candidate area in the reduced image). As a result, the candidate area in the rectangular document area is specified.

FIG. 3C shows a rectangular document area 210. In the figure, the identified candidate regions are indicated by hatching. As shown, the region 213 showing the tear 211 is specified as a candidate region. It should be noted that a plurality of tears may be formed in the manuscript. Therefore, a plurality of candidate regions corresponding to a plurality of breaks can be identified. Also, if no tears are formed in the manuscript, the total number of candidate regions identified can be zero.

The candidate region may be specified by using a scanned image instead of using a reduced image. However, when a reduced image is used, the number of pixels used to identify the candidate area is small, so that the processing load can be reduced.

In S130 (FIG. 2), the CPU 810 determines whether or not the candidate area is the target of repair. The CPU 810 determines that the candidate area is not the target of repair when the length of the candidate area from the side in contact with the candidate area (specifically, the side of the rectangular original area) is equal to or greater than the first threshold value.

FIG. 4 is a flowchart showing an example of the process of determining the candidate region. In S200, the CPU 810 selects one candidate area that has not been processed in the process of FIG. 4 among the candidate areas specified in S120 (FIG. 2) as a candidate area to be determined (referred to as a candidate area of interest). In S210, the CPU 810 determines whether or not the length of the candidate area of interest (specifically, the length from the side in contact with the candidate area of interest in the direction perpendicular to that side) is equal to or greater than the first threshold Th1. to decide. In this embodiment, the first threshold Th1 is predetermined and is greater than zero. FIG. 3D shows a processing example of the scanned image 110. The length L11 in the figure is the length from the side 413 of the candidate region 213. Hereinafter, it will be described that the length L11 is less than the first threshold value Th1.

When the length of the attention candidate region is less than the first threshold Th1 (S210: No), in S220, the CPU 810 selects the attention candidate region as the repair target. That is, the CPU 810 determines that the candidate region of interest should be repaired. It is determined that the candidate area 213 of FIG. 3D should be repaired. Then, the CPU 810 shifts to S240.

When the length of the attention candidate region is equal to or greater than the first threshold Th1 (S210: Yes), in S230, the CPU 810 excludes the attention candidate region from the repair target. That is, the CPU 810 determines that the candidate region of interest should not be repaired. Then, the CPU 810 shifts to S240.

In this way, the reason for determining that the candidate region should not be repaired when the length of the candidate region is equal to or greater than the first threshold Th1 is when the color of the long candidate region is corrected by the repair process described later. This is because the color-corrected area may look unnatural.

In S240, the CPU 810 determines whether or not the processing of all the candidate areas has been completed. When the unprocessed candidate area remains (S240: No), the CPU 810 shifts to S200 and processes the unprocessed candidate area. When the processing of all the candidate areas is completed (S240: Yes), the CPU 810 ends the processing of FIG. 4 (and by extension, S130 (FIG. 2)).

In S135 (FIG. 2), the CPU 810 specifies a partial margin area. FIG. 3 (D) shows an example of the specified partial margin region (partial margin region 511 to 514). As described above, in S100, the width of each margin on each side of the rectangular document is specified by the user. The CPU 810 specifies a partial margin area 511-514 of a designated width W21-S24 that contacts the outside of the sides 411-414 of the rectangular document area 210 (FIG. 3D).

Specifically, the CPU 810 has a rectangular contour 111s composed of four sides 411x to 414x located outside the four sides 411 to 414 of the rectangular document area 210 by the widths W21 to W24 specified by the user. To identify. The outer sides 411x to 414x and the inner sides 411 to 414 are parallel to each other. The distances between the outer sides 411x to 414x and the inner sides 411 to 414 are the widths W21 to W24 specified by the user, respectively. Then, the CPU 810 divides the area 510 between the rectangular contour 111s and the contour 410 of the rectangular original region 210 into four partial margin areas 511 to 514 that are in contact with the four sides 411 to 414, respectively. The partial margin areas 511 to 514 are trapezoidal areas. The upper base and the lower base of the partial margin regions 511 to 514 are inner sides 411 to 414 and outer sides 411x to 414x.

For example, the upper and lower bases of the partial margin area 511 in contact with the left side 411 of the rectangular document area 210 are the inner side 411 and the outer side 411x located outside the side 411 by the width W21. (The sides 411 and 411x are parallel, and the distance between the sides 411 and 411x is the width W21).

Of the scanned image 110, the area 111 surrounded by the outer sides 411x to 414x, that is, the area 111 composed of the rectangular document area 210 and the four partial margin areas 511 to 514 is the output image as described later. It is an area included in (referred to as an output area 111).

In S140 (FIG. 2), the CPU 810 tentatively determines whether or not the partial margin area is the target of repair. In S140, the provisional determination of each partial margin area is performed independently of the determination of the other partial margin areas. In this embodiment, in the CPU 810, the partial margin area is the target of repair when the width of the partial margin area is equal to or larger than the second threshold value and when the partial margin area is in contact with a candidate area which is not the target of repair. Judge that it is not. In other cases, the partial margin area is determined to be the target of repair. In the example of FIG. 3D, the widths of the partial margin areas 511 to 514 are widths W21 to W24, respectively. These widths W21 to W24 are greater than zero and less than the second threshold. Then, the partial margin areas 511 to 514 are not in contact with the candidate areas that are not the targets of repair. Therefore, each of the partial margin areas 511 to 514 is determined to be the target of repair. The details of the processing of S140 will be described later.

In S150 (FIG. 2), the CPU 810 finally determines whether or not the partial margin area is the target of repair. In S150, the final judgment result of each partial margin area can be changed in consideration of the judgment result of the other partial margin area. When the continuous area composed of at least one partial margin area and zero or more candidate areas includes an area that is tentatively determined not to be repaired, the CPU 810 repairs the entire continuous area. Judge that it should not be done. In the example of FIG. 3D, the partial margin areas 511 to 514 and the candidate area 213 form a continuous area. In S130, the candidate area 213 is determined to be the target of repair, and in S140, all of the partial margin areas 511 to 514 are determined to be the target of repair. Therefore, in S150, the partial margin areas 511 to 514 and the candidate areas 213 are finally determined to be the targets of repair. The details of the processing of S150 will be described later.

In S160 (FIG. 2), the CPU 810 executes the repair process of the area to be repaired. FIG. 5 is a flowchart showing an example of the repair process. In S500, the CPU 810 selects one unprocessed partial margin area in the process of FIG. 5 from the partial margin areas specified in S135 (FIG. 2) as the partial margin area to be processed (attention partial margin area). Called). In S510, the CPU 810 determines whether or not the attention portion margin area is the target of repair.

When the attention portion margin area is the target of repair (S510: Yes), in S520, the CPU 810 repairs the attention portion margin area. Specifically, the color of the margin area of interest is corrected. In this embodiment, the CPU 810 corrects the color values of all the pixels in the margin area of interest to the color values indicating the background Bg of the original image 21 (FIG. 3A). The method for specifying the color value of the background Bg may be various methods. For example, the mode of each of the histograms of the color components of the plurality of pixels in the rectangular document area 210 may be adopted as the value indicating the color of the background Bg. Further, the mode may be specified by using a plurality of pixels at the edge portion of the remaining region excluding the candidate region (for example, the candidate region 213 of FIG. 3C) from the rectangular original region 210.

FIG. 3 (E) shows an example of the image 112 obtained by the repair process. This image 112 is an image obtained by performing a repair process on the image of the output region 111 of FIG. 3D (also referred to as an output image 112). Regions 210x, 511x to 514x show images obtained by performing repair processing on regions 210 and 511 to 514 in FIG. 3D, respectively. When the partial margin region 513 (FIG. 3 (D)) is the attention portion margin region, the color of the plurality of pixels in the attention portion margin region 513 is corrected to the color of the background Bg. In the repaired image 112 (FIG. 3 (E)), the color difference between the background Bg of the rectangular original area 210x and the partial margin area 513x becomes small. As a result, the boundaries of the regions 210x and 513x (here, sides 413) become inconspicuous.

In S530 (FIG. 5), the CPU 810 repairs the candidate area to be repaired in contact with the attention portion margin area. Specifically, the color of the candidate area to be repaired is corrected. In this embodiment, the CPU 810 corrects the colors of all the pixels in the candidate area to be repaired to the color of the background Bg of the original image 21 (FIG. 3 (A)). The color of the background Bg is the same as the color specified in S520. When the partial margin area 513 (FIG. 3 (D)) is the attention partial margin area, the color of the plurality of pixels of the candidate area 213 to be repaired is corrected to the color of the background Bg. In the repaired image 112 (FIG. 3 (E)), the candidate region 213x shows the repaired image of the candidate region 213 (FIG. 3 (D)). The repair process reduces the color difference between the background Bg of the rectangular original region 210x and the candidate region 213x. As a result, the boundary between the background Bg of the region 210x and the candidate region 213x becomes inconspicuous.

As will be described later, the width of the partial margin area can be zero. In this embodiment, even when the width of the partial margin region is zero, it can be determined that the color of the partial margin region should be corrected by the processing of S140 and S150 of FIG. Then, in the process of FIG. 5, even when the width of the attention portion margin area is zero, if it is determined that the color of the attention portion margin region should be corrected, the determination result of S510 is Yes. Yes, in S530, the color of the candidate area to be repaired in contact with the margin area of interest is corrected. When the width of the attention portion margin region is zero, the attention portion margin region is not actually formed. Therefore, the color correction in S520 is omitted.

After repairing the candidate area of interest and the candidate area (S520, S530), the CPU 810 shifts to S540. When the attention portion margin area is not the target of repair (S510: No), the CPU 810 skips S520 and S530 and shifts to S540. In S540, the CPU 810 determines whether or not the processing of all the partial margin areas is completed. When the unprocessed partial margin area remains (S540: No), the CPU 810 shifts to S500 and processes the unprocessed partial margin area. In the example of FIG. 3D, all of the partial margin areas 511 to 514 are the targets of repair. As a result, in the repaired image 112 (FIG. 3 (E)), all of the partial margin areas 511x to 514x are repaired. As a result, the color difference between the background Bg of the rectangular original area 210x and the partial margin areas 511x to 514x becomes small. As a result, the boundary between the rectangular original area 210x and the partial margin areas 511x to 514x (here, sides 411 to 414) becomes inconspicuous.

When the processing of all the partial margin areas is completed (FIG. 5: S540: Yes), the CPU 810 ends the processing of FIG. 5 (by extension, S160 (FIG. 2)).

In S170 (FIG. 2), the CPU 810 generates output image data showing the repaired image (for example, the output image 112 of FIG. 3 (E)). The data format of the output image data may be arbitrary. For example, output image data in JPEG format may be generated.

In S180, the CPU 810 outputs the output image data. The output destination device may be any device. For example, the output destination may be an internal storage device 815 (for example, a non-volatile storage device 830) provided in the image processing device 800. In this case, the CPU 810 stores the output image data in the non-volatile storage device 830. The user may use the output image data stored in the non-volatile storage device 830 for any purpose (for example, printing or display). Further, the output destination device may be an external storage device (for example, a USB memory) connected to the image processing device 800 (not shown). In this case, the CPU 810 stores the output image data in an external storage device. Further, the output destination device may be a printer (not shown) connected to the image processing device 800. In this case, the CPU 810 may print the output image (that is, the repaired image) on the printer by outputting the output image data to the printer. Upon completion of S180, the CPU 810 ends the process of FIG.

A-3. Temporary judgment processing of partial margin area:
FIG. 6 is a flowchart showing an example of a provisional determination process (FIG. 2: S140) of the partial margin area. In S300, the CPU 810 selects one unprocessed partial margin area in the process of FIG. 6 among the partial margin areas specified in S135 (FIG. 2) as the partial margin area to be determined (attention partial margin area). Called). In S310, the CPU 810 tentatively selects the attention portion margin area as a repair target. In S320, the CPU 810 determines that the width of the attention portion margin area (specifically, the width in the direction perpendicular to the side from the side in contact with the attention portion margin area among the four sides of the rectangular document area). It is determined whether or not the second threshold value is Th2 or more. In this embodiment, the second threshold Th2 is predetermined and is greater than zero. In the example of FIG. 3D, the widths of the partial margin areas 511 to 514 are widths W21 to W24, respectively. Hereinafter, it will be described that these widths W21 to W24 are larger than zero and less than the threshold value Th2.

When the width of the attention portion margin region is equal to or larger than the second threshold Th2 (S320: Yes), in S330, the CPU 810 excludes the attention portion margin region from the repair target. That is, the CPU 810 tentatively determines that the margin area of interest should not be repaired. Then, the CPU 810 shifts to S340.

As described above, when the width of the partial margin region is equal to or larger than the second threshold value Th2, it is tentatively determined that the partial margin region should not be repaired. The reason for this is as follows. When the color of the large partial margin area is corrected, the color-corrected area may look unnatural because the color-corrected area is large. In this embodiment, when the width of the partial margin region is equal to or greater than the second threshold value Th2, it is tentatively determined that the partial margin region should not be repaired. Can be suppressed.

When the width of the attention portion margin area is less than the second threshold value Th2 (S320: No), the CPU 810 executes the processes of S350 to S390. As a result, when the non-target candidate area that is not the target of repair is in contact with the attention area margin area, the attention area margin area is excluded from the repair target.

Specifically, in S350, the CPU 810 determines whether or not the width of the attention portion margin region is larger than zero. As described above, when the width of the margin specified by the user is zero, the width of the attention portion margin area is zero. When the width of the attention portion margin region is zero (S350), the CPU 810 skips S355 to S390 and shifts to S340 without excluding the attention portion margin region from the repair target.

When the width of the attention portion margin region is larger than zero (S350: Yes), in S355, the CPU 810 determines whether or not there is a candidate region in contact with the attention portion margin region. When there is no candidate area in contact with the attention portion margin region (S355: No), the CPU 810 skips S360 to S390 and shifts to S340 without excluding the attention portion margin region from the repair target.

For example, the candidate region does not touch the partial margin regions 511, 512, and 514 in FIG. 3 (D). Therefore, when these partial margin regions 511, 512, and 514 are the partial margin regions of interest, the judgment result of S355 is No. As a result, the tentative determination (S310) that the partial margin areas 511, 512, and 514 should be repaired without being excluded from the repair target is maintained.

When there is a candidate area in contact with the attention area margin area (S355: Yes), in S360, the CPU 810 selects one undetermined candidate area as the candidate area to be processed from the candidate areas in contact with the attention area margin area. (Called a candidate area of interest). In S370, the CPU 810 determines whether or not the candidate region of interest is not subject to repair. When the candidate region of interest is not the target of repair, that is, when the candidate region of interest is not the target of repair (S370: Yes), in S380, the CPU 810 excludes the region of interest from the repair target. That is, the CPU 810 determines that the attention portion margin area should not be repaired. Then, the CPU 810 shifts to S390.

When the candidate area of interest is the target of repair, that is, when the candidate area of interest is the target of repair (S370: No), the CPU 810 skips S380 and shifts to S390.

For example, when the partial margin area 513 of FIG. 3D is the attention partial margin area, the candidate area 213 may be the attention candidate area. Since the candidate area 213 is the target of repair, the judgment result of S370 is No. As a result, the tentative determination (S310) that the partial margin region 513 should be repaired without being excluded from the repair target is maintained.

In S390, the CPU 810 determines whether or not the processing of all the candidate areas in contact with the attention portion margin area is completed. When the unprocessed candidate area remains (S390: No), the CPU 810 shifts to S360 and processes the unprocessed candidate area. When the processing of all the candidate areas is completed (S390: Yes), the CPU 810 shifts to S340.

In S340, the CPU 810 determines whether or not the provisional determination process of all the partial margin areas has been completed. When the unprocessed partial margin area remains (S340: No), the CPU 810 shifts to S300 and processes the unprocessed partial margin area. When the processing of all the partial margin areas is completed (S340: Yes), the CPU 810 ends the processing of FIG. 6 (and by extension, S140 (FIG. 2)).

A-4. Final judgment processing of partial margin area:
FIG. 7 is a flowchart showing an example of the final determination process (FIG. 2: S150) of the partial margin area. In S400, the CPU 810 selects one unprocessed partial margin area in the process of FIG. 7 among the partial margin areas specified in S135 (FIG. 2) as the partial margin area to be determined (attention partial margin area). Called). In S410, the CPU 810 determines whether or not the tentative determination result in S140 (FIG. 2) of the attention portion margin area is "should be repaired (that is, is the target of repair)". When the attention portion margin area is not the target of repair (S410: No), the CPU 810 shifts to S480 without changing the determination result (not the repair target) of the attention portion margin area.

When the attention portion margin area is the target of repair (S410: Yes), in S420, the CPU 810 determines whether or not the width of the attention portion margin area is larger than zero. When the width of the attention portion margin region is zero (S420: No), the CPU 810 maintains the determination result (the target of repair) of the attention portion margin region without changing, and then shifts to S480.

When the width of the attention portion margin area is larger than zero (S420: Yes), in S430, the CPU 810 determines that the partial margin area adjacent to one of the attention portion margin areas is "the width is larger than zero" and "the object to be repaired". It is judged whether or not the condition of "not (not subject to repair)" is satisfied. When the judgment result of S430 is No, in S440, the CPU 810 states that the partial margin area adjacent to the other of the attention portion margin area is "the width is larger than zero" and "is not the target of repair (not the target of repair). It is judged whether or not the condition of "is)" is satisfied.

For example, when the partial margin area 513 of FIG. 3D is the attention portion margin region, in S430, a determination is made regarding the portion margin region 514 adjacent to the attention portion margin region 513 in the clockwise direction, and in S440, attention is paid. A determination is made regarding the partial margin area 512 adjacent to the partial margin area 513 in the counterclockwise direction. Since the width W24 of the partial margin region 514 is larger than zero and the partial margin region 514 is the target of repair, the judgment result of S430 is No. Further, since the width W22 of the partial margin region 512 is larger than zero and the partial margin region 512 is the target of repair, the judgment result of S440 is No.

A specific example of the figure will be described later, but for at least one of the adjacent partial margin areas, the width of the partial margin area is larger than zero and the partial margin area is not the target of repair. In the case (S430: Yes, or S440: Yes), in S470, the CPU 810 removes the attention portion margin area from the repair target and shifts to S480. As described above, the attention portion margin region having a width larger than zero and adjacent to the partial margin region that is not the target of repair is excluded from the repair target. The reason for this is that when a partial margin area that is not the target of repair is arranged next to the partial margin area of interest that is the target of repair, the color difference is easily noticeable at the boundary where those areas are in contact. When the width of the adjacent partial margin region is zero, the adjacent partial margin region is not actually formed in the output image, so that the boundary that makes the color difference conspicuous is not formed. Therefore, in this embodiment, when the width of the adjacent partial margin area is zero, the judgment results of S430 and S440 are set to No.

When the judgment results of S430 and S440 are No, in S450, the CPU 810 has a partial margin area (referred to as an opposite partial margin area) opposite to the attention portion margin region, which is "the width is larger than zero" and "the target of repair". It is judged whether or not the condition of "not (not subject to repair)" is satisfied. If the determination result of S450 is No, the CPU 810 shifts to S480 and maintains a tentative determination that the attention portion margin area should be repaired without being excluded from the repair target. For example, when the partial margin region 513 of FIG. 3D is the attention portion margin region, the opposite portion margin region 511 opposite the attention portion margin region 513 is the target of repair, and its width W21 is larger than zero. .. Therefore, the judgment result of S450 is No. When the determination result of S450 is No, both the attention portion margin region and the facing portion margin region may be the target of repair, and the width of the facing portion margin region may be zero. In this case, it is suppressed that the color difference after the repair treatment is conspicuous between the attention portion margin region and the opposite portion margin region. For example, when the partial margin area 513 of FIG. 3D is the attention portion margin region, both the attention portion margin region 513 and the opposite portion margin region 511 are the targets of repair (S450: No). When both the attention portion margin region and the opposite portion margin region are repaired, the conspicuous color difference after the repair treatment is suppressed between these regions. Therefore, the CPU 810 maintains a tentative determination that the attention portion margin area should be repaired without being excluded from the repair target.

When the determination result of S450 is Yes, in S460, the CPU 810 determines whether or not the width of at least one adjacent partial margin region of the attention portion margin region is larger than zero.

When the determination result of S460 is Yes, the CPU 810 shifts to S470, removes the attention portion margin area from the repair target, and shifts to S480. A specific example of the figure will be described later, but when the judgment result of S450 and S460 is Yes, the attention portion margin area to be repaired and the opposite portion margin area not to be repaired are larger than zero. It is continuous through the adjacent partial margin area having a width. As a result, the color difference after the repair treatment can be large between the continuous attention portion margin region and the opposite portion margin region. Therefore, in the present embodiment, the attention portion margin region is excluded from the repair target in accordance with the facing portion margin region.

If the determination result of S460 is No, the CPU 810 shifts to S480 and maintains a tentative determination that the attention portion margin area should be repaired without being excluded from the repair target. When the judgment result of S460 is No, the attention portion margin region and the opposite portion margin region are not continuous. Therefore, it is suppressed that the color difference after the repair treatment is conspicuous between the attention portion margin region and the opposite portion margin region. Therefore, the CPU 810 maintains a tentative determination that the attention portion margin area should be repaired without being excluded from the repair target.

In S480, the CPU 810 determines whether or not the processing for determining all the partial margin areas has been completed. When the unprocessed partial margin area remains (S480: No), the CPU 810 shifts to S400 and processes the unprocessed partial margin area. When the processing of all the partial margin areas is completed (S480: Yes), the CPU 810 ends the processing of FIG. 7 (and by extension, S150 (FIG. 2)).

As described above, in the processing of S130, S140, and S150 of FIG. 2, the condition for determining that the color of the attention portion margin region should be corrected is the partial margin region constituting the region continuous with the attention portion margin region. And the candidate area include not including the area where it is judged that the color should not be corrected. Therefore, it is possible to prevent the region where the color is modified from coming into contact with the region where the color is not modified. As a result, the noticeable color difference between the color-corrected area and the color-uncorrected area is suppressed.

A-5. Another image processing example:
FIG. 8 is an explanatory diagram showing an example of processing another image. The explanatory views of FIGS. 8 (A) to 8 (E) correspond to the explanatory views of FIGS. 3 (A) to 3 (E), respectively. FIG. 8A shows the scanned image 120. The only difference from the scanned image 110 in FIG. 3 (A) is that the tear 221 is long. The portion of the original image 22 and the outer image 32 other than the tear 221 is the same as the corresponding portion of the original image 21 and the outer image 32 in FIG. 3 (A).

8 (B) shows sides 421 to 424 identified in S110 of FIG. In S110 of FIG. 2, the sides 421 to 424 showing the outline of the original image 22 are specified as in the sides 411 to 414 of FIG. 3 (B). The rectangular document area 220 is a rectangular area surrounded by the contour 420 formed by the sides 421 to 424. The margin area 320, which is an area outside the rectangular document area 220, indicates the outside margin of the document image 22. The area 223 showing the tear 221 is included in the rectangular document area 220.

FIG. 8C shows a candidate region identified in S120 of FIG. As shown, the region 223 showing the tear 221 is specified as a candidate region. The candidate area 223 is an area tangent to the side 423.

FIG. 8D shows a processing example of the scanned image 120. The length L21 in the figure is the length of the candidate region 223 from the side 423 in contact with the candidate region 223 (here, the length in the direction perpendicular to the side 423). In S130 of FIG. 2 (and by extension, the process of FIG. 4), it is determined whether or not the candidate region 223 should be repaired according to the length L21. In this embodiment, the length L21 is equal to or greater than the first threshold value Th1. In this case, since the determination result of S210 in FIG. 4 is Yes, the candidate region 223 is excluded from the repair target (S230).

Further, FIG. 8D shows a partial margin region 521 to 524 specified in S135 of FIG. In this embodiment, the widths W21 to W24 specified by the user are the same as the widths W21 to W24 in FIG. 3 (D), respectively. Then, as in the embodiment of FIG. 3D, the four sides 421x to 424x located outside the four sides 421 to 424 of the rectangular document area 220 by the widths W21 to W24 specified by the user. The rectangular contour 121s to be constructed is specified. Then, the region 520 between the rectangular contour 121s and the contour 420 of the rectangular original region 220 is divided into four partial margin regions 521 to 524 that are in contact with the four sides 421 to 424, respectively. The partial margin areas 521 to 524 are trapezoidal areas having inner sides 421 to 424 and outer sides 421x to 424x as upper and lower bases. The area 121 composed of the rectangular document area 220 and the four partial margin areas 521 to 524 is an output area included in the output image (referred to as an output area 121).

In S140 of FIG. 2 (and by extension, the process of FIG. 6), a tentative determination is made as to whether or not the partial margin areas 521 to 524 (FIG. 8 (D)) should be repaired. The widths W21 to W24 of the partial margin regions 521 to 524 are less than the second threshold Th2 (FIG. 6: S320). Therefore, these partial margin areas 521 to 524 are not excluded from the repair target at this stage (that is, it is tentatively determined that they should be repaired (S320: No)). The candidate regions do not touch the three partial margin regions 521, 522, and 524 on the left side, the upper side, and the lower side (S355: No). Therefore, the tentative judgment result that the three partial margin areas 521, 522, and 524 should be repaired is maintained. The candidate area 223 is in contact with the partial margin area 523 on the right side (S355: Yes). This candidate area 223 is not subject to repair (S370: Yes). Therefore, the partial margin area 523 is excluded from the repair target (S380).

In S150 of FIG. 2 (and by extension, the process of FIG. 7), a final determination is made as to whether or not the partial margin areas 521 to 524 (FIG. 8 (D)) should be repaired. When the left partial margin region 521 is the attention portion margin region, the attention portion margin region 521 is the target of repair (S410: Yes), and the width W21 is larger than zero (S420: Yes). The partial margin areas 522 and 524 on both sides are the targets of repair (S430: No, S440: No). The facing portion margin area 523 is not subject to repair, and its width W23 is larger than zero (S450: Yes). The widths W22 and W24 of the adjacent partial margin areas 522 and 524 are larger than zero (S460: Yes). As a result, the partial margin area 521 is excluded from the repair target (S470).

When the upper partial margin region 522 is the attention portion margin region, the attention portion margin region 522 is the target of repair (S410: Yes), and the width W22 is larger than zero (S420: Yes). The adjacent partial margin area 523 is not subject to repair, and the width W23 is greater than zero (S430: Yes). As a result, the partial margin area 522 is excluded from the repair target (S470).

When the lower partial margin region 524 is the attention portion margin region, the process proceeds in the same manner as when the upper partial margin region 522 is the attention portion margin region. Then, the partial margin area 524 is excluded from the repair target (S470).

When the partial margin area 523 on the right side is the partial margin area of interest, the partial margin area 523 is not the target of repair (S410: No). Therefore, the tentative determination that the partial margin area 523 should not be repaired is maintained.

As described above, according to S130, S140, and S150 of FIG. 2, it is determined that all of the partial margin areas 521 to 524 and the candidate area 223 should not be repaired. Then, in S160 of FIG. 2 (and by extension, the process of FIG. 5), the repair process is performed according to these determination results.

FIG. 8E shows an example of the output image 122 obtained by the repair process. This image 122 is an image obtained by performing a repair process on the image of the output region 121 of FIG. 8 (D). As described above, it is determined that all of the partial margin areas 521 to 524 and the candidate area 223 should not be repaired. Therefore, the images of these regions 521 to 524 and 223 are maintained as they are without being repaired (FIG. 5: S510: No).

As described above, in the process of FIG. 4, when the length L21 of the candidate region 223 is equal to or larger than the first threshold value Th1, it is determined that the candidate region 223 should not be repaired (S210: Yes). If the color of a large candidate area is corrected by the repair process, the color-corrected area may look unnatural because the color-corrected area is large. According to the above configuration, it is determined that the color should not be corrected for the large candidate area, so that it is possible to suppress that the color-corrected area looks unnatural. Also, if the candidate area is large, the candidate area is likely to indicate a deliberately cut portion rather than an unintended tear. Since the correction of the color of the intentionally formed portion is suppressed, it is possible to suppress the output image from appearing unnatural.

Further, in the process of FIG. 6, when the right partial margin area 523 is the attention partial margin region, in S320, it is tentatively determined that the attention partial margin region 523 is the target of repair. That is, the attention portion margin area 523 does not satisfy the non-target tentative condition (S320), which is a condition for tentatively determining that the repair should not be performed. In this case, in S355 to S390, it is determined whether or not zero or more adjacent candidate regions, which are candidate regions in contact with the attention portion margin region 523, include non-target candidate regions that are not the targets of repair. In the example of FIG. 8D, the candidate area 223 in contact with the attention portion margin area 523 is a non-target candidate area. In this way, when the adjacent candidate region includes the non-target candidate region (S370: Yes), the attention portion margin region 523 is excluded from the repair target (S380). As a result, it is possible to prevent the candidate area where the color is not corrected from contacting the partial margin area where the color is corrected. As a result, it is suppressed that the candidate area where the color is not corrected is conspicuous.

FIG. 8F shows an example of an image 122x generated when the candidate region 223 is not repaired and the partial margin regions 521 to 524 are repaired. As shown in the figure, color-corrected partial margin areas 521x to 524x are arranged outside the rectangular document area 220. In particular, the repaired partial margin area 523x is in contact with the candidate area 223. As a result, in the image 122x, the candidate region 223 whose color is not corrected is shown as an isolated island surrounded by the background Bg of the rectangular original region 220 and the partial margin region 523x. As a result, the candidate region 223 can be unintentionally noticeable. In this embodiment, it is suppressed that the candidate region 223 is unintentionally conspicuous in this way.

Further, in the process of FIG. 6, when the left side, upper side, and lower side partial margin areas 521, 522, and 524 are the attention part margin areas, it is assumed that the attention part margin areas 521, 522, and 524 are the targets of repair. It is determined (S310, S320: No, S355: No). Then, in the process of FIG. 7, when the upper and lower partial margin areas 522 and 524 are the attention partial margin areas, in S430 and S440, the adjacent partial margin areas in contact with the attention partial margin areas 522 and 524 are repaired. It is judged whether or not it is not a target of the above, that is, whether or not it is judged that it should not be repaired. In the example of FIG. 8D, the adjacent partial margin area 523 is not subject to repair and its width W23 is greater than zero. Therefore, the determination result of at least one of S430 and S440 is Yes. In this case, the attention portion margin areas 522 and 524 are excluded from the repair target (S470).

Further, in the process of FIG. 7, when the left partial margin area 521 is the attention partial margin area, in S430 and S440, the adjacent partial margin areas 522 and 524 in contact with the attention portion margin area 521 are not subject to repair. It is determined whether or not there is, that is, whether or not it is determined that the repair should not be performed. Since the partial margin areas 522 and 524 are tentatively determined to be the target of repair in S140 of FIG. 2, the determination results of S430 and S440 are No. In this case, in S450 and S460, whether or not the opposite partial margin region 523 continuous to the attention partial margin region 521 via the adjacent partial margin regions 522 and 524 is not subject to repair, that is, should be repaired. It is judged whether or not it is judged not to be. In the example of FIG. 8D, the facing portion margin area 523 is not subject to repair (S450: Yes). The widths W22 and W24 of the adjacent partial margin areas 522 and 524 are larger than zero (S460: Yes). In this case, the attention portion margin area 521 is excluded from the repair target (S470).

In this way, when it is determined that at least one of the adjacent partial margin area in contact with the attention partial margin area and the opposite partial margin area in contact with the adjacent partial margin area should not be corrected in color, attention is paid. It is determined that the color of the partial margin area should not be modified. In this way, when it is determined that the color of the other partial margin area continuous with the attention portion margin area should not be corrected, it is determined that the color of the attention portion margin area should not be corrected. It is suppressed that the partial margin area where the color is corrected and the partial margin area where the color is not corrected are continuous. As a result, it is suppressed that the color difference is conspicuous due to the continuity of the partial margin area where the color is corrected and the partial margin area where the color is not corrected.

As described above, in the processing of S130, S140, and S150 of FIG. 2, the region constitutes a region continuous with the attention portion margin region of one or more partial margin regions and the candidate region, and is referred to as the partial margin region. When it is determined that the color should not be modified with respect to at least one of the candidate regions, it is determined that the color of the attention portion margin region should not be modified. Therefore, it is suppressed that the area where the color is not corrected is adjacent to the area where the color is corrected. As a result, the noticeable color difference between the color-corrected area and the color-uncorrected area is suppressed.

A-6. Another image processing example:
FIG. 9 is an explanatory diagram showing an example of processing another image. The explanatory views of FIGS. 9 (A) to 9 (E) correspond to the explanatory views of FIGS. 3 (A) to 3 (E), respectively. FIG. 9A shows the scanned image 130. The scanned image 130 includes a manuscript image 23 showing a manuscript and an outer image 33 which is an image outside the manuscript image 23. Unlike the scanned image 110 of FIG. 3A, two tears 231 and 232 are formed in the original image 23. Further, the width of the original image 23 is smaller than the width of the original image 21 of FIG. 3 (A).

9 (B) shows sides 431 to 434 identified in S110 of FIG. In S110 of FIG. 2, the sides 431 to 434 showing the outline of the original image 23 are specified as in the sides 411 to 414 of FIG. 3 (B). The rectangular document area 230 is a rectangular area surrounded by the contour 430 formed by the sides 431 to 434. The margin area 330, which is an area outside the rectangular document area 230, indicates the outside margin of the document image 23. Areas 233 and 234 showing tears 231 and 232 are included in the rectangular document area 230.

FIG. 9C shows a candidate region identified in S120 of FIG. As shown, the regions 233 and 234 showing the tears 231 and 232 are specified as candidate regions. The candidate area 233 on the right side is an area in contact with the side 433 on the right side, and the candidate area 234 on the left side is an area in contact with the side 431 on the left side.

FIG. 9D shows a processing example of the scanned image 130. The length L31 in the figure is the length of the candidate region 233 in the direction perpendicular to the side 433 in contact with the candidate region 233. The length L32 is the length of the candidate region 234 in the direction perpendicular to the side 431 in contact with the candidate region 234. In S130 of FIG. 2 (and by extension, the process of FIG. 4), it is determined whether or not the candidate regions 233 and 234 should be repaired according to the lengths L31 and L32. In this embodiment, the lengths L31 and L32 are each less than the first threshold Th1. In this case, since the determination result of S210 in FIG. 4 is No, all of the candidate regions 233 and 234 are selected as targets for repair (S220).

Further, FIG. 8D shows a partial margin region 513 to 534 specified in S135 of FIG. In this embodiment, the left width W21 is greater than zero and less than the second threshold Th2 (FIG. 6), the upper and lower widths W22 and W24 are zero, and the right width W23 is the second. The threshold is Th2 or higher. From the four sides 431 to 434 of the rectangular document area 230, the rectangular contour 131s composed of the four sides 431x to 434x located outside by the widths W21 to W24 specified by the user is specified. Then, the area 530 between the rectangular contour 131s and the contour 430 of the rectangular document area 230 is divided into partial margin areas 531 to 534. The partial margin region 513 to 534 is a trapezoidal region having an inner side 431 to 434 and an outer side 431x to 434x as an upper base and a lower base. The upper and lower sides 432x and 434x overlap the original sides 432 and 434. The upper and lower partial margin areas 532 and 534 are areas having a width of zero. Regions 532, 534 with zero width are not actually formed. Therefore, the left partial margin region 531 and the right partial margin region 533 are not continuous and are separated from each other outside the rectangular original region 230. The area 131 composed of the rectangular document area 230 and the partial margin areas 531 and 533 having a width larger than zero is an output area included in the output image (referred to as an output area 131).

In S140 of FIG. 2 (and by extension, the process of FIG. 6), a tentative determination is made as to whether or not the partial margin area 531 to 534 (FIG. 9 (D)) should be repaired.

The width W21 of the left partial margin region 531 is less than the second threshold Th2 (FIG. 6: S320: No). Therefore, it is tentatively determined that the partial margin area 531 should be repaired at this stage. The candidate region 234 in contact with the partial margin region 531 is the target of repair (S370: No). Therefore, the tentative determination that the partial margin region 531 should be repaired is maintained.

The width W23 of the right partial margin region 533 is equal to or greater than the second threshold value Th2 (S320: Yes). Therefore, in S330, the partial margin area 533 is excluded from the repair target.

The widths W22 and W24 of the upper and lower partial margin regions 532 and 534 are zero, that is, less than the second threshold Th2 (S320: No). Therefore, it is tentatively determined that the partial margin areas 532 and 534 should be repaired at this stage. Further, the widths W22 and W24 of these partial margin regions 532 and 534 are zero (S350: No). Therefore, the tentative determination that the partial margin areas 532 and 534 should be repaired is maintained.

In S150 of FIG. 2 (and by extension, the process of FIG. 7), a final determination is made as to whether or not the partial margin area 531 to 534 (FIG. 9 (D)) should be repaired. When the left partial margin region 531 is the attention portion margin region, the attention portion margin region 531 is the target of repair (S410: Yes), and the width W21 is larger than zero (S420: Yes). With respect to the partial margin areas 522 and 524 on both sides, the widths W22 and W24 are zero (S430: No, S440: No). The opposite partial margin area 533 is not subject to repair, its width W23 is larger than zero (S450: Yes), and the widths W22 and W24 of the adjacent partial margin areas 532 and 534 are zero (S460: Yes). No). As a result, the tentative judgment result that the partial margin area 521 should be repaired is maintained.

In this way, even when the opposite portion margin region 533 of the attention portion margin region 531 is not the target of repair, the attention portion margin region 531 and the opposite portion margin region 533 have a common partial margin having a width larger than zero. When not in contact with the region, the tentative determination result that the attention portion margin region 531 should be repaired is maintained. The reason for this is that when the attention portion margin area 531 and the facing portion margin region 533 are separated from each other outside the rectangular original region 230 without being continuous, the attention portion margin region 531 and the facing portion margin area 533 are separated from each other. This is because the conspicuous color difference after the repair treatment is suppressed.

With respect to the upper and lower partial margin areas 532 and 534, since the widths W22 and W24 are zero (S420: No), the tentative judgment that the partial margin areas 532 and 534 should be repaired is maintained. .. Regarding the partial margin area 533 on the right side, since the partial margin area 533 is not the target of repair (S410: No), the tentative determination result that the partial margin area 533 should not be repaired is maintained.

In S160 of FIG. 2 (and by extension, the process of FIG. 5), the repair process is performed according to these determination results.

FIG. 9E shows an example of the output image 132 obtained by the repair process. This image 132 is an image obtained by performing a repair process on the image of the output region 131 of FIG. 9 (D). The regions 230x, 533x, and 234x show images obtained by performing repair processing on the regions 230x, 533x, and 234x in FIG. 9 (D), respectively.

As described above, it is determined that the left partial margin area 531 and the candidate area 234 should be repaired. Therefore, the partial margin region 531 is repaired (S510: Yes, S520), and the candidate region 234 in contact with the partial margin region 531 is also repaired (S530). In the repaired image 132 (FIG. 9E), the boundary between the background Bg of the rectangular document area 230x and the candidate area 234x and the boundary between the background Bg of the rectangular document area 230x and the partial margin area 531x become inconspicuous. ..

It has been determined that the right partial margin area 533 should not be repaired. Therefore, the partial margin region 533 is not repaired (FIG. 5: S510: No), and the candidate region 233 in contact with the partial margin region 533 is also not repaired.

As described above, when the width of the partial margin region is equal to or larger than the second threshold value Th2 (FIG. 6: S320: Yes), it is determined that the partial margin region should not be repaired (FIG. 6: S330, FIG. 7: S410). : No). Therefore, since the large partial margin area provided according to the user's instruction is excluded from the repair target, it is possible to prevent the color-corrected area from appearing unnatural.

Further, when it is tentatively determined in the process of FIG. 6 that the partial margin area should not be repaired (S320: Yes, S330, S370: Yes, S380), in the process of FIG. 7, the candidate area in contact with the partial margin area is tentatively determined. The tentative judgment result that the partial margin area should not be repaired is adopted as the final judgment result without performing the process (S355-S390) for determining whether or not includes the non-target candidate area for repair. (S410: No). Therefore, it is possible to make an appropriate judgment while suppressing a decrease in processing speed.

B. Modification example:
(1) In S210 of FIG. 4, the conditions for determining that the color of the candidate region should not be corrected may be various conditions. This condition may include, for example, that the length of the candidate region in the direction parallel to the side tangent to the candidate region is equal to or greater than the threshold value, and the area of the candidate region (for example, the number of pixels) is equal to or greater than the threshold value. It may include that there is. In general, various conditions indicating that the candidate region is large may be used.

(2) In S320 of FIG. 6, the conditions for tentatively determining that the color of the partial margin region should not be corrected may be various conditions. This condition may include, for example, that the area of the partial margin region (for example, the number of pixels) is equal to or larger than the threshold value. In general, various conditions indicating that the partial margin area is large may be used.

Further, in the process of FIG. 6, the condition for tentatively determining that the color of the attention portion margin region should not be corrected is the condition of using S320, S355, and S370, that is, "the width of the attention portion margin region is the second. Instead of the threshold Th2 or more (S320: Yes), or the candidate area to be repaired is in contact with the attention portion margin area (S355: Yes, and S370: Yes) ”, under various other conditions. It may be there. The condition for tentatively determining that the color of the attention area margin area should not be corrected is, for example, that the difference between the color of the attention area margin area and the background Bg color of the rectangular original area is less than the threshold value. May include that.

Generally, in the process of FIG. 6, whether or not the color of the attention portion margin region should be corrected may be determined independently of the other partial margin regions. The result of the judgment made independently of the other partial margin area may be used as a tentative judgment result. Then, as in the process of FIG. 7, the final determination result of the attention portion margin region so that the partial margin region where the color is corrected and the partial margin region where the color is not corrected are not continuous outside the rectangular original region. May be adjusted in consideration of the tentative determination result of the other partial margin area.

The process of adjusting the determination result may be various other processes instead of the process of FIG. 7. In general, the condition for determining that the color of the attention portion margin area should be corrected is that the region constituting the region continuous with the attention portion margin region among one or more partial margin regions and the candidate region , Various conditions may be included, including not including a region where it is determined that the color should not be modified. Further, the condition for determining that the color of the attention portion margin region should not be corrected is an region constituting a region continuous with the attention portion margin region of one or more partial margin regions and the candidate region. Therefore, various conditions may be used, including that it is determined that the color should not be corrected with respect to at least one region of the partial margin region and the candidate region.

As shown in FIG. 9D, the width of the partial margin region can be zero. The partial margin area having a width of zero in this way is not an area actually formed in the output image, but a virtual area. Therefore, when the width of at least one of the two adjacent partial margin regions is zero, it can be said that the two partial margin regions do not form a continuous region.

(3) Even when the width of the partial margin area is larger than zero, if the width is small, it may be difficult for the user to visually recognize the partial margin area. For example, when the width of the partial margin area with respect to the total size of the output image is small, the user who observes the entire output image may not be able to recognize the small width partial margin area. In this case, even if the partial margin area is in contact with another small width partial margin area, the user can recognize that the partial margin area is continuous with the small width partial margin area. , Can be difficult.

When two large partial margin areas are connected via such a small width partial margin area, the user can recognize that the two large partial margin areas are separated from each other. Therefore, in the processing of FIGS. 6 and 7, the small-width partial margin region may be treated as a region that does not form a continuous region with the other partial margin region. For example, under the conditions of S350 in FIG. 6 and S420, S430, S440, S450, and S460 in FIG. 7, "width is larger than zero" may be replaced with "width is larger than the reference width". Here, the reference width may be zero and may be a value larger than zero. The reference width may be determined so that the user can visually recognize the partial margin area. For example, the reference width is preferably 1/20 or less, particularly preferably 1/50 or less, and 1/100 or less of the shorter length of the output image. Is more preferable, and most preferably zero.

In any case, in the processing of S130, S140, and S150 of FIG. 2, the condition for determining that the color of the attention portion margin region should be corrected is the attention portion of one or more partial margin regions and the candidate region. It may be various conditions including that the region constituting the region having a predetermined continuous relationship with the margin region does not include the region where it is determined that the color should not be corrected. Here, the "predetermined continuous relationship" is the following relationship. That is, when a plurality of partial margin areas are connected in order and the widths of all the partial margin areas are larger than the reference width, the plurality of partial margin areas have a predetermined continuous relationship. Further, when the candidate area is in contact with the partial margin area and the width of the partial margin area is larger than the reference width, the partial margin area and the candidate area have a predetermined continuous relationship. When the candidate area is in contact with one of the plurality of partial margin areas having a predetermined continuous relationship, the plurality of partial margin areas and the candidate area are continuously determined in advance. There is a relationship.

Further, in the processing of S130, S140, and S150 of FIG. 2, it is a region constituting a region having a predetermined continuous relationship with the attention portion margin region of one or more partial margin regions and the candidate region, and is a portion. When it is determined that the color should not be modified with respect to at least one of the margin region and the candidate region, it may be determined that the color of the attention portion margin region should not be modified.

(4) The method of specifying a candidate area that is a candidate for an area that is not a manuscript but is an area in the rectangular manuscript area is different from the method of the above embodiment, and various other methods that can specify a non-manuscript area It may be. For example, color components other than luminance may be utilized (hue, saturation, etc.). In general, a candidate region may be specified by using a marginal white range, which is a range of one or more color components and is a color range indicating a margin outside the original. When each color value of one or more color components of the pixel of interest is within the marginal white range of the corresponding color component, the pixel of interest is classified as a pixel that does not indicate the original. When the color value of at least one color component of the pixel of interest is outside the marginal white range of that color component, the pixel of interest is classified as a pixel indicating a document. Then, a region in which a plurality of pixels that do not indicate the original are continuous and is in contact with the side (that is, the outer edge) of the rectangular original region may be specified as a candidate region.

Further, in the above embodiment, in the process of specifying the candidate area (FIG. 2: S120), the candidate area is specified by using the rectangular original area without using the margin area outside the rectangular original area. However, a candidate area may be specified by using a margin area in addition to the rectangular document area. For example, the CPU 810 may determine the margin white range used for identifying the pixels showing the original and the pixels not showing the original by analyzing the margin area instead of the predetermined range. For example, a color range having a predetermined width centered on the mode of each of the histograms of each color component of a plurality of pixels in the margin region may be used as the margin white range.

(5) The process of correcting the color of the region determined to be corrected may be various processes instead of the process described with reference to FIG. For example, in the process of FIG. 5, when the candidate area to be repaired touches a partial margin area having a width of zero (more generally, a partial margin area having a width equal to or less than the above reference width), the candidate area is the candidate. The color of the area may not be modified. Further, the color of the candidate area to be repaired may be corrected regardless of whether or not the partial margin area in contact with the candidate area is the target of repair.

Further, the width of the margin area in the scanned image may be smaller than the width of the partial margin area specified by the user. For example, in the image example of FIG. 3D, the upper edge 118 of the scanned image 110 may be located inside the side 412x located outside the upper side 412 of the rectangular document area 210 by the width W22. is there. That is, a part of the output area 111 may protrude outside the scanned image 110. In such a case, in the repair process (S160 of FIG. 2), the CPU 810 may execute a process of repairing (that is, a process of adding) a portion of the output area that extends outside the scanned image. For example, the CPU 810 may modify the color value of the pixel of the protruding portion to the same color value as the color value of the partial margin area including the protruding portion. When the protruding portion is included in the partial margin area to be repaired, the color value of the pixel of the protruding portion is corrected to the same color value as the color value of the pixel of the repaired partial margin area. When the protruding portion is included in the non-repaired partial margin area, the color value of the pixel of the protruding portion is corrected to the same color value as the color value of the pixel of the unrepaired partial margin area. However, the CPU 810 may delete the portion of the output area that extends outside the scanned image from the output area instead of repairing (adding it here). That is, the portion of the output region that overlaps the scanned image may be used as the final output region.

(6) The image processing may be various other processing instead of the above processing. For example, the original image can be tilted with respect to the scanned image. In this case, the CPU 810 may perform tilt correction to correct the tilt of the original image. Tilt correction may be performed at any stage of image processing. For example, the CPU 810 may perform tilt correction between S110 and S120 in FIG. 2 to correct the tilt of the original image with respect to the scanned image according to the side specified in S110. Then, the CPU 810 may execute the processing after S120 using the image data representing the tilt-corrected read image. Further, the process of specifying the side of the rectangular document area may be various other processes instead of the above process. For example, the CPU 810 may specify a line segment that approximates the arrangement of a plurality of edge pixels by using the least squares method, and adopt the specified line segment as an edge.

Further, in S100 of FIG. 2, the CPU 810 has a width of each of the four partial margin areas arranged on all four sides of the rectangular document area (for example, the width of each of the four partial margin areas 511 to 514 of FIG. 3D). W21 to W24) are individually determined according to the user's instruction. Instead, the CPU 810 may determine one width common to the four partial margin areas according to the user's instruction. Further, the width of the partial margin area may be predetermined instead of being determined according to the instruction of the user.

(7) The image processing device of FIG. 1 may be a device of a type different from that of a personal computer (for example, a digital camera, a scanner, a smartphone). Further, the image processing device may be a part of the scanner 900. Further, a plurality of devices (for example, a computer) capable of communicating with each other via a network may partially share the image processing function of the image processing device and provide the image processing function as a whole (for example). A system equipped with these devices corresponds to an image processing device).

Further, the scanning device for generating the scanned image data indicating the scanned image including the document and the margins arranged outside the document by optically scanning the document is different from the scanner 900 of FIG. 1 in various other scanning devices. It may be the device of. For example, the scanned image data generated by a digital camera (for example, a digital camera incorporated in a smartphone) may be used to generate the output image data. Here, the reading device and the image processing device may be incorporated into one device (for example, a scanner, a smartphone, etc.), and the reading device and the image processing device may be different devices.

In each of the above embodiments, a part of the configuration realized by the hardware may be replaced with software, and conversely, a part or all of the configuration realized by the software may be replaced with the hardware. May be good. For example, at least a part of the processing of S100 to S180 in FIG. 2 may be realized by a dedicated hardware circuit.

In addition, when a part or all of the functions of the present invention are realized by a computer program, the program is provided in a form stored in a computer-readable recording medium (for example, a non-temporary recording medium). be able to. The program may be used while being stored on the same or different recording medium (computer-readable recording medium) as it was provided. The "computer-readable recording medium" is not limited to a portable recording medium such as a memory card or a CD-ROM, but is connected to an internal storage device in the computer such as various ROMs or a computer such as a hard disk drive. It may also include an external storage device.

Although the present invention has been described above based on Examples and Modifications, the above-described embodiments of the invention are for facilitating the understanding of the present invention and do not limit the present invention. The present invention may be modified or improved without departing from the spirit and claims, and the present invention includes an equivalent thereof.

21-23 ... Original image, 31-33 ... Outer image, 110, 120, 130 ... Scanned image, 111, 121, 131 ... Output area, 111s, 121s, 131s ... Rectangular contour, 112, 122, 132 ... Output image, 122x ... image, 118 ... edge, 210, 210x, 220, 230, 230x ... rectangular original area, 213, 213x, 223, 233, 234, 234x ... candidate area, 310, 320, 330 ... margin area, 410, 420, 430 ... Contours 411, 411x, 421, 421x, 413, 413x, 414, 414x, 421, 421x, 422, 422x, 423, 423x, 424, 424x, 431, 431x, 432, 432x, 433, 433x, 434, 434x ... Sides, 510, 520, 530 ... Areas, 511, 511x, 512, 512x, 513, 513x, 514, 514x, 521, 521x, 522, 522x, 523, 523x, 524, 524x, 531, 513x, 532, 533 ... Partial margin area, 800 ... Image processing device, 810 ... CPU, 815 ... Storage device, 820 ... Volatile storage device, 830 ... Non-volatile storage device, 832 ... Program, 840 ... Display unit, 850 ... Operation unit , 890 ... interface, 900 ... scanner, 910 ... control unit, 911 ... CPU, 912 ... volatile storage device, 913 ... non-volatile storage device, 914 ... program, 915 ... storage device, 919 ... interface, 920 ... image sensor, 930 ... moving device, 940 ... platen, 950 ... cover, 990 ... main body, D1 ... first direction, D2 ... second direction, NT ... network, Ob ... object, Bg ... background, Us ... mounting surface, Bs ... Opposing surface, W21 to W24 ... Width, Th1 ... 1st threshold, Th2 ... 2nd threshold, Dp1 ... 1st direction, Dp2 ... 2nd direction, Dp3 ... 3rd direction (upward)

Claims (7)

It ’s a program
An acquisition function for acquiring the scanned image data indicating the scanned image including the document and the margins arranged outside the document, which is generated by optically scanning the document, and the acquisition function.
A side identification function for identifying four sides of a rectangular document area obtained by dividing a portion of the scanned image including the document into a rectangular area by analyzing the scanned image data, and
A candidate area specifying function that identifies a candidate area that is a candidate for an area that is not the manuscript but is a region in the rectangular manuscript area that is in contact with any one of the four sides.
The first judgment function for judging whether or not the color of the candidate area should be corrected, and
A partial margin area that is a region indicating the margin and constitutes at least a part of a margin area that is an area outside the rectangular original region, and is one or more portions that are in contact with different sides of the four sides. A second judgment function that determines whether or not to correct the color for each of the margin areas,
It is determined that the color should be corrected by using the result of the judgment by the first judgment function regarding the candidate area and the result of the judgment by the second judgment function regarding each of the one or more partial margin areas. A selection correction process, which is a process of correcting the color of the selected area, is executed, and an output image including each of the rectangular original area after the selection correction processing and the one or more partial margin areas after the selection correction processing is shown. Image generation function to generate output image data and
To the computer,
The second determination function is an area that constitutes a region having a predetermined continuous relationship with the attention portion margin region, and the color should be corrected with respect to at least one region of the partial margin region and the candidate region. If it is determined that this is not the case, it is determined that the color of the margin area of interest should not be corrected.
The condition for the second determination function to determine that the color of the attention portion margin region should be corrected is determined in advance as the attention portion margin region of the one or more partial margin regions and the candidate region. A computer program that includes that the areas that make up the contiguous areas do not include areas that are determined not to be color-corrected. The computer program according to claim 1.
The condition for the first determination function to determine that the color of the candidate region should not be modified is that the length of the candidate region from the side in contact with the candidate region is equal to or greater than the first threshold value. including,
Computer program. The computer program according to claim 1 or 2.
The computer is realized with a determination function of determining the width of each of the one or more partial margin areas in the output image in response to a user's instruction.
The condition for the second determination function to determine that the color of the partial margin region should not be modified is that the width of the partial margin region determined according to the user's instruction is equal to or greater than the second threshold value. Including that
Computer program. The computer program according to any one of claims 1 to 3.
The second judgment function is
(A) It is determined whether or not the attention portion margin area satisfies the non-target provisional condition for tentatively determining that the color of the partial margin area should not be corrected.
(B) When the attention portion margin area does not satisfy the non-target tentative condition,
It is determined whether or not zero or more adjacent candidate regions, which are candidate regions in contact with the attention portion margin region, include non-target candidate regions, which are candidate regions for which it is determined that the color of the candidate region should not be corrected. And
When the adjacent candidate region includes the non-target candidate region, it is determined that the color of the attention portion margin region should not be corrected.
(C) When the attention portion margin area satisfies the non-target provisional condition, the color of the attention portion margin region is changed without determining whether or not the adjacent candidate region includes the non-target candidate region. Judge that it should not be fixed,
Computer program. The computer program according to any one of claims 1 to 4.
The second judgment function is
Whether or not each color of the one or more partial margin areas should be corrected is tentatively determined independently of the other partial margin areas.
If it is determined that the color of the attention portion margin area should be corrected, the color of the attention portion margin region is in contact with the adjacent partial margin region having a width larger than the reference width, and the adjacent partial margin region is in contact with the attention portion margin region. It is determined whether or not at least one of the opposite portion margin region having a width larger than the reference width, which is located opposite the attention portion margin region, is tentatively determined that the color should not be corrected.
If it is tentatively determined that at least one of the adjacent partial margin area and the opposite partial margin area should not be corrected in color, it is determined that the color of the attention partial margin area should not be corrected.
Computer program. The computer program according to any one of claims 1 to 5.
The candidate area identification function identifies the candidate area by using the rectangular original area without using the margin area of the scanned image.
Computer program. It is an image processing device
An acquisition unit that acquires the scanned image data, which is generated by optically scanning the original and shows the scanned image including the original and the margins arranged outside the original.
By analyzing the scanned image data, a side specifying portion for specifying four sides of a rectangular document area obtained by dividing a portion of the scanned image including the document into a rectangular area, and
A candidate area specifying unit that specifies a candidate area that is a candidate for an area that is not the manuscript but is a region in the rectangular manuscript area that is in contact with any one of the four sides.
The first judgment unit that determines whether or not the color of the candidate area should be corrected, and
A partial margin area that is a region indicating the margin and constitutes at least a part of a margin area that is an area outside the rectangular original region, and is one or more portions that are in contact with different sides of the four sides. A second judgment unit that determines whether or not to correct the color for each of the margin areas,
It is determined that the color should be corrected by using the result of the judgment by the first judgment unit regarding the candidate area and the result of the judgment by the second judgment unit regarding each of the one or more partial margin areas. A selection correction process, which is a process of correcting the color of the selected area, is executed, and an output image including each of the rectangular original area after the selection correction processing and the one or more partial margin areas after the selection correction processing is shown. An image generator that generates output image data and
With
The second determination unit is an area that constitutes a region having a predetermined continuous relationship with the attention portion margin region, and the color should be corrected with respect to at least one region of the partial margin region and the candidate region. If it is determined that this is not the case, it is determined that the color of the margin area of interest should not be corrected.
The conditions for the second determination unit to determine that the color of the attention portion margin region should be corrected are determined in advance with the attention portion margin region of the one or more partial margin regions and the candidate region. Includes that the regions that make up the contiguous regions do not include regions where it is determined that the color should not be modified.
Image processing device.

Images