JP2010199767A - Image processing device and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processing device which suppresses influence due to image variation processing for an image subjected to image variation processing, and classifies its pixels. <P>SOLUTION: In the image processing device, a dividing means divides an image into regions, a classification means classifies pixels in the regions divided by the dividing means, and an integration means integrates the classified pixels based on the shapes of pixels classified by the classification means. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to an image processing apparatus and an image processing program.

  When printing an image or the like, an image variation process typified by a screen process is performed for gradation expression of the image. A printed matter on which the image variation processing has been performed is read by a scanner, and the configuration of the image is analyzed.

  As a technique related to this, for example, Patent Document 1 aims to provide an apparatus that cuts out an image formed of a combination of various colors and patterns without setting troublesome cutting conditions. The image data input from the image input means is divided into small block units by the block dividing means, and the color quantized image data grouped for each similar color by the color quantizing means is generated. The image block including the contour portion is designated and selected from the block-divided image data created and displayed on the display means by the contour block setting means, and the contour portion setting means selects using the color quantized image data. The contour is accurately cut out from the block image, and mask data is created by the mask creation means based on this data. By region of the image data corresponding to the mask data is extracted, it is disclosed that to obtain the desired cut-out image.

  Further, for example, Patent Document 2 has an object of providing a new image segmentation algorithm for object-based image retrieval, extracts color regions from a multidimensional image, and extracts the boundary of all color region pairs. Compute complexity and merge region pairs when the boundary complexity value of a color region pair is greater than a given boundary complexity threshold and the color distance of the region pair is less than a given distance threshold Merge color regions using hierarchical cluster analysis and then merge color regions using boundary analysis to determine if a color region is small and surrounded by another color region If is true, merge the small color region into the surrounding color region, and finally It is disclosed that assigned to each color region of Ndeta.

  Further, for example, Patent Document 3 has an object of accurately detecting a halftone dot region with respect to halftone dots with various numbers of lines. The input image is scaled to obtain both the original image and the scaled image. It is disclosed that a halftone dot region is detected, the halftone dot region detected from the scaled image is inversely scaled, and then integrated with the halftone dot region of the original image and output as a halftone dot detection result.

  Further, for example, Patent Document 4 discloses a halftone dot region detection that can accurately separate a halftone dot portion and a character portion even when it is difficult to locally distinguish a halftone dot region / non-halftone dot region. An object is to provide an apparatus, an image forming apparatus, a program, a storage medium, and a halftone dot region detection method, and a halftone dot separation unit, a linear detection unit that detects a linear part constituting a character, and a halftone dot Dot detection means for detecting a dot or a gap between dots, and a halftone dot area detection means for detecting a halftone dot area based on the detection result in the linear detection means and the dot detection means. By using the pole pixel information and the linear part information as the judgment material for detection, it is possible to accurately identify the halftone dot portion and the character portion even when it is difficult to distinguish the halftone dot region / non-halftone dot region locally. It is disclosed that it can be separated To have.

  In addition, for example, Patent Document 5 has a problem of determining a part composed of lines in image data. For image data obtained by reading a document, about 5 × 5 pixels centering on a pixel of interest, By adding the five pixel values of each column of 5 × 5 pixels and obtaining the addition value by the column unit pixel value addition unit, the subtraction / comparison circuit subtracts the addition values from each other and compares them with the reference value th1, It is disclosed that a concave / convex pattern having an image density indicated by an addition value is determined and AND is performed by an AND determination unit to determine whether the pattern corresponds to a specific line pattern.

  Further, for example, Patent Document 6 uses an image processing apparatus that can identify with high accuracy whether the read image data exists in a character area, a photographic area, or a halftone dot area. An image forming apparatus, an image processing method, and a storage medium are provided. In the region separation processing unit, an image signal of a local block composed of a first pixel of interest and a plurality of neighboring pixels is stored in the first block memory. The edge detection circuit outputs a determination signal as to whether or not the first pixel of interest is an edge from the image signal stored in the first block memory by the edge detection circuit. The input edge determination signal is stored, and the identification circuit uses the edge determination signal stored in the second block memory to perform the second attention of the second block memory. The element or local block around the second noticed pixel to identify whether in a halftone dot area is disclosed.

  Further, for example, Patent Document 7 discloses an image processing apparatus, an image forming apparatus, and a line area identification that can perform image processing optimal for a line area by accurately identifying a line area in image data. An object of the present invention is to provide a method, a document type determination method, a computer program, and a recording medium. An area separation processing unit of an image processing apparatus includes a 7 × 7 pixel including a pixel of interest from image data provided from an input tone correction unit. The size area is extracted, and the sum of absolute values of density differences between adjacent pixels is calculated in four directions of 0 °, 90 °, 45 °, and 135 °, and the calculated sum is direction-dependent. Is present, it is determined that the pixel of interest is a pixel included in the line region, and this determination is performed for all the pixels of the image data, thereby specifying the line region.

JP 05-216993 A JP 2007-149139 A JP 2000-33002 A JP 2002-300387 A JP 2002-300388 A JP 2002-305654 A JP 2008-104139 A

  An object of the present invention is to provide an image processing apparatus and an image processing program that classify pixels of an image that has undergone image variation processing while suppressing the influence of the image variation processing.

The gist of the present invention for achieving the object lies in the inventions of the following items.
The invention of claim 1 is based on a dividing unit that divides an image into regions, a classification unit that classifies pixels in the region divided by the dividing unit, and a shape of a pixel group classified by the classification unit, An image processing apparatus comprising an integration unit that integrates pixels between classifications.

  The invention according to claim 2 is the image processing apparatus according to claim 1, wherein the integrating unit further integrates pixels between regions divided by the dividing unit based on the integrated pixels. It is.

  The invention according to claim 3 is characterized in that the integration unit integrates the pixels after dividing the classified pixel group based on an area of a circumscribed rectangle of the pixel group classified by the classification unit. An image processing apparatus according to claim 1.

  According to a fourth aspect of the present invention, the image processing according to any one of the first to third aspects further includes a configuration generation unit configured to generate a configuration of the image based on a result of integration by the integration unit. Device.

  According to a fifth aspect of the invention, the computer is divided into a shape of a pixel group classified by the classifying unit, a classifying unit for classifying the pixels in the region divided by the dividing unit, and a classifying unit for dividing the image into regions. An image processing program that functions as an integration unit that integrates pixels between classifications based on the image processing program.

  According to the image processing apparatus of the first aspect, it is possible to classify the pixels while suppressing the influence of the image variation processing on the image subjected to the image variation processing as compared with the case where the present configuration is not provided. .

  According to the image processing apparatus of the second aspect, it is possible to classify the pixels between the plurality of regions as compared with the case where the present configuration is not provided.

  According to the image processing apparatus of the third aspect, compared with the case where the present configuration is not provided, more precise classification can be performed in the classification within the region.

  According to the image processing apparatus of the fourth aspect, it is possible to analyze the configuration of the image while suppressing the influence of the image variation processing as compared with the case where the present configuration is not provided.

  According to the image processing program of claim 5, it is possible to classify the pixels while suppressing the influence of the image variation processing on the image subjected to the image variation processing as compared with the case where the present configuration is not provided. .

It is a conceptual module block diagram about the structural example of this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is a flowchart which shows the process example by this Embodiment. It is explanatory drawing which shows the example of an object block. It is explanatory drawing which shows the process example by a pixel classification module. It is explanatory drawing which shows the process example by a classification result integration module. It is a flowchart which shows the process example by a classification result integration module. It is explanatory drawing which shows the example of an object block. It is explanatory drawing which shows the process example by a pixel classification module. It is explanatory drawing which shows the process example of circumscribed rectangle production | generation. It is explanatory drawing which shows the process example which divides | segments the classified area | region. It is explanatory drawing which shows the process example by a classification result integration module. It is a block diagram which shows the hardware structural example of the computer which implement | achieves this Embodiment.

Hereinafter, an example of a preferred embodiment for realizing the present invention will be described with reference to the drawings.
FIG. 1 shows a conceptual module configuration diagram of a configuration example of the present embodiment.
The module generally refers to components such as software (computer program) and hardware that can be logically separated. Therefore, the module in the present embodiment indicates not only a module in a computer program but also a module in a hardware configuration. Therefore, the present embodiment also serves as an explanation of a computer program, a system, and a method. However, for the sake of explanation, the words “store”, “store”, and equivalents thereof are used. However, when the embodiment is a computer program, these words are stored in a storage device or stored in memory. It is the control to be stored in the device. In addition, the modules correspond almost one-to-one with the functions. However, in mounting, one module may be composed of one program, or a plurality of modules may be composed of one program. A plurality of programs may be used. The plurality of modules may be executed by one computer, or one module may be executed by a plurality of computers in a distributed or parallel environment. Note that one module may include other modules. Hereinafter, “connection” is used not only for physical connection but also for logical connection (data exchange, instruction, reference relationship between data, etc.).
In addition, the system or device is configured by connecting a plurality of computers, hardware, devices, and the like by communication means such as a network (including one-to-one correspondence communication connection), etc., and one computer, hardware, device. The case where it implement | achieves by etc. is included. “Apparatus” and “system” are used as synonymous terms. “Predetermined” means that the process is determined before the target process, and not only before the process according to this embodiment starts but also after the process according to this embodiment starts. In addition, if it is before the target processing, it is used in accordance with the situation / state at that time or with the intention to be decided according to the situation / state up to that point.

Hereinafter, screen processing will be mainly exemplified and described as the image variation processing. Screen processing is used to reproduce halftones in output such as printing, and the density of halftone dots also changes depending on the density (number of lines) of lines on the screen. When a screen-processed image is read by an image reading device such as a scanner, pseudo gradation or the like may occur.
The image processing apparatus according to the present embodiment generates a screen-processed image configuration. As shown in FIG. 1, a block division module 110, a pixel classification module 120, a classification result integration module 130, data A conversion module 140 is included.

The block division module 110 is connected to the pixel classification module 120. Accept an image and divide the image into regions. Then, the divided image is transferred to the pixel classification module 120.
Here, accepting an image means, for example, reading an image with a scanner, a camera, etc., receiving an image from an external device via a communication line by fax or the like, a hard disk (in addition to what is built in a computer, For example, reading out an image stored in a network (including those connected via a network). The image may be a binary image or a multi-value image (including a color image). One image may be received or a plurality of images may be received. Further, the contents of the image may be a document used for business, a pamphlet for advertisement, or the like.

  Moreover, dividing into areas may be, for example, a rectangular area or an area having another shape. Hereinafter, a square (for example, 8 pixels × 8 pixels) block will be described as an example. Note that the block size may be determined so that a plurality of lines by screen processing are included. As a more specific example, the block size may be determined according to the resolution of the image and the number of lines of screen processing.

The pixel classification module 120 is connected to the block division module 110 and the classification result integration module 130. The pixels in the block divided by the block division module 110 are classified. Then, the classification result is passed to the classification result integration module 130.
For example, the pixel classification module 120 classifies each pixel in the block according to the mutual pixel value distance. The pixel values of each pixel may be grouped using a clustering method, pixels whose pixel values are within a predetermined threshold may be grouped, or other existing methods may be used. .

The classification result integration module 130 is connected to the pixel classification module 120 and the data conversion module 140. Based on the shape of the pixel group classified by the pixel classification module 120, the pixels between the classifications are integrated. Then, the integration result is passed to the data conversion module 140. The classification result integration module 130 determines whether or not to integrate the classification results of the respective blocks according to the shape of the pixel group in the block of the pixels classified into the same category. As the shape of the pixel group, for example, there is whether or not the pixel group is divided into a plurality of parts in the block. When the pixel group is divided into a plurality of pixels, the pixel group of the classification and the pixel group classified into others are integrated. The pixel group to be integrated may belong to another classification and may be in a condition that it is in contact with the pixel group of the target classification. Further, a pixel group having the same shape as the target classification pixel group may be selected.
Further, the shape of the pixel group is not limited to within a block, and may be a shape after including pixels classified into the same category in the block and in the peripheral block.

  The classification result integration module 130 may further integrate pixels between blocks divided by the block division module 110 based on the integrated pixels. That is, after integration within a block, integration between a plurality of blocks is performed. Thereby, the pixels of the entire image may be classified. For example, the classification result in each block (the classification result here is the classification result after integrating the classifications in the block) and the distance of the average pixel value in the classification (the average pixel value in the two classifications) Are integrated based on the difference) and the contact relationship, and integrated as a classification result of the entire image. That is, if the distance of the average pixel value is within a predetermined threshold and the classification touches across blocks, integration is performed.

  Further, the classification result integration module 130 may integrate the pixels after dividing the classified pixel group based on the circumscribed rectangle area of the pixel group classified by the pixel classification module 120. This processing will be described later using the flowchart shown in the example of FIG. 7 and the processing examples shown in FIGS.

The data conversion module 140 is connected to the classification result integration module 130. Based on the result of the integration by the classification result integration module 130, an image configuration is generated. Then, the generated configuration is output. For example, a color distribution in the image corresponds to the image configuration. As a more specific example, the position (X coordinate, Y coordinate), size (width, height), contour, etc. of the pixel group (pixel group of a certain color) within a certain pixel value range, It is generated as a configuration of the image.
The configuration of the output image may be stored as a search attribute together with the image in an image database, for example. Alternatively, an image may be searched from the image database using the configuration of the output image as a search key.

2 and 3 are flowcharts showing an example of processing according to the present embodiment.
In step S202, the block division module 110 divides the received image into blocks.
FIG. 4 is an explanatory diagram illustrating an example of the target block. The target block has a screen-processed portion like a block 400 shown in the example of FIG. The block 400 is a block composed of three colors, and includes a color A401, a color B402, a color A403, a color B404, a color A405, and a color C406. For example, the color A is pink, the color B is red, and the color C is black.

  In step S204, the pixel classification module 120 classifies the pixels in each block based on the pixel values. FIG. 5 is an explanatory diagram showing a processing example by the pixel classification module 120 for the block 400 shown in the example of FIG. The pixel values are classified into three. The classification C506 shown in the example of FIG. 5A is a classification of the color C406 portion, and the classifications A501, 503, and 505 shown in the example of FIG. 5B are colors A401, 403, and 405. Is classified into one classification, and classifications B502 and 504 shown in the example of FIG. 5C are obtained by classifying the color B402 and 404 parts into one classification.

  In step S206, the classification result integration module 130 determines whether or not the area is divided within the same classification. If it is split, the process proceeds to step S208. Otherwise, the process proceeds to step S212. Whether or not there is a division may be determined, for example, by labeling the portions determined to be the same classification, and as a result of determining whether or not there are a plurality of labels. As a result, it is determined that the example shown in FIG. 5A is not split, and the examples shown in FIGS. 5B and 5C are determined to be split.

  In step S <b> 208, the classification result integration module 130 determines whether or not the area that is in contact with the classification is divided in the same classification. If it is split, the process proceeds to step S210. Otherwise, the process proceeds to step S212. Whether or not they are in contact with each other may be determined, for example, based on whether or not the areas of the classifications have a common boundary. The classifications that are in contact with the classification A shown in the example of FIG. 5B are the classification C (FIG. 5A) and the classification B (FIG. 5C). Proceeding to S212, classification B is split, and so the process proceeds to step S210. Note that the processing from step S208 to step S212 is repeated as many times as the number of categories in contact with the target category.

In step S210, the classification result integration module 130 integrates both classifications. For example, classification A shown in the example of FIG. 5B and classification B shown in the example of FIG.
In step S212, if the classification result integration module 130 determines No in step S206 or No in step S208, the classification is not targeted for integration. For example, the classification C shown in the example of FIG. 5A is not integrated.
In step S214, the classification result integration module 130 repeats the processing from step S206 to step S212 for the classification in the target block.
FIG. 6 is an explanatory diagram illustrating an example of processing performed by the classification result integration module 130. The block 400 shown in the example of FIG. 4 is classified and integrated into the integrated area 601 and the integrated area 602 shown in the example of FIG.
In step S216, the classification result integration module 130 repeats the processing from step S206 to step S214 for the block in the target image.

In step S218, the classification result integration module 130 further integrates the integration results in each block. That is, classification is integrated between blocks. As a result, the entire image is divided into regions having equivalent pixel values.
In step S220, the data conversion module 140 converts the integration result obtained in step S218 into data that can be used in other systems. For example, the data is converted into data such as the position, size, contour, and the like of a region having an equivalent pixel value (may be a color name or the like).
In step S222, the data conversion module 140 outputs the data.

FIG. 7 is a flowchart illustrating an example of processing performed by the classification result integration module 130. You may make it carry out by step S210 shown in the flowchart example of FIG. A specific example will be described with reference to FIGS.
FIG. 8 is an explanatory diagram illustrating an example of a target block. The target block is a screen-processed portion like the block 800 shown in the example of FIG. 8, and the block 800 is a block composed of three colors, which are a color D801, a color E802, a color D803, a color E804, A color D805, a color F806, and a color F807 are included. For example, the color D is pink, the color E is red, and the color F is green.
FIG. 9 is an explanatory diagram showing a processing example by the pixel classification module 120 for the block 800 shown in the example of FIG. The pixel values are classified into three. The classifications D901, 903, and 905 shown in the example of FIG. 9A are obtained by making the portions of the colors D801, 803, and 805 into one classification, and the classifications E902 and 904 shown in the example of FIG. The portions of the colors E802 and 804 are classified into one category, and the categories F906 and 907 shown in the example of FIG. 9C are obtained by classifying the portions of the colors F806 and 807 into one category.

  In step S702, it is determined whether or not the difference between the areas of the circumscribed rectangles in the other categories that are in contact with the area of the circumscribed rectangles in that category is greater than or equal to a predetermined value. First, a circumscribed rectangle of the target classification and a circumscribed rectangle of the classification in contact with the classification are generated. For example, the circumscribed rectangle of the classification D shown in the example of FIG. 9A is one whole block (the circumscribed rectangle 1000 shown in the example of FIG. 10). The circumscribed rectangle of classification E shown in the example of FIG. 9B is a circumscribed rectangle 1001 shown in the example of FIG. The difference between the two areas is calculated, and it is determined whether the difference is equal to or greater than a predetermined value. In this example, it is assumed that the value is equal to or greater than a predetermined value. Note that the category to be compared here is the category that is Yes in step S206 in the flowchart example shown in FIG.

  In step S704, the classification in which the circumscribed rectangle has a large area is divided. In the example shown in FIG. 9, since the circumscribed rectangle of the classification D shown in the example of FIG. The area of classification D is divided so that the portion in contact with classification E is maximized. That is, as shown in the example of FIG. 11, the classification D901 is divided into a classification G1101 and a classification H1104, the classification D903 is divided into a classification G1102 and a classification H1105, and the classification D905 is divided into a classification G1103 and a classification H1106.

In step S706, the classifications in contact are integrated. In the example shown in FIG. 9, the classification G (1101, 904) shown in the example of FIG. 11A obtained by dividing the classification E (902, 904) and the classification D (901, 903, 905) shown in the example of FIG. 1102 and 1103) are in contact with each other. Similarly, the classification H (1104, 1105, 1106) shown in the example of FIG. 11B obtained by dividing the classification F (906, 907) and the classification D (901, 903, 905) shown in the example of FIG. 9C. Since both are in contact with each other, they are integrated. The result is as shown in the example of FIG. That is, the block 800 shown in the example of FIG. 8 is classified and integrated into two areas, that is, the integrated area 1201 and the integrated area 1202 shown in the example of FIG.
In step S708, processing equivalent to that in step S210 shown in the flowchart example of FIG. 2 is performed.

  A hardware configuration example of the image processing apparatus according to the present embodiment will be described with reference to FIG. The configuration shown in FIG. 13 is configured by a personal computer (PC), for example, and shows a hardware configuration example including a data reading unit 1317 such as a scanner and a data output unit 1318 such as a printer.

  A CPU (Central Processing Unit) 1301 is an execution sequence of each module such as the block division module 110, the pixel classification module 120, the classification result integration module 130, and the data conversion module 140 described in the above embodiment. It is a control part which performs processing according to a computer program which described.

  A ROM (Read Only Memory) 1302 stores programs used by the CPU 1301, calculation parameters, and the like. A RAM (Random Access Memory) 1303 stores programs used in the execution of the CPU 1301, parameters that change as appropriate during the execution, and the like. These are connected to each other by a host bus 1304 including a CPU bus.

  The host bus 1304 is connected to an external bus 1306 such as a PCI (Peripheral Component Interconnect / Interface) bus via a bridge 1305.

  A keyboard 1308 and a pointing device 1309 such as a mouse are input devices operated by an operator. The display 1310 includes a liquid crystal display device or a CRT (Cathode Ray Tube), and displays various types of information as text or image information.

  An HDD (Hard Disk Drive) 1311 has a built-in hard disk, drives the hard disk, and records or reproduces a program executed by the CPU 1301 and information. The hard disk stores received images, result data of the data conversion module 140, and the like. Further, various computer programs such as various other data processing programs are stored.

  The drive 1312 reads data or a program recorded on a removable recording medium 1313 such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, and reads the data or program into an interface 1307 and an external bus 1306. , The bridge 1305, and the RAM 1303 connected via the host bus 1304. The removable recording medium 1313 can also be used as a data recording area similar to a hard disk.

  The connection port 1314 is a port for connecting the external connection device 1315 and has a connection unit such as USB and IEEE1394. The connection port 1314 is connected to the CPU 1301 and the like via the interface 1307, the external bus 1306, the bridge 1305, the host bus 1304, and the like. A communication unit 1316 is connected to a network and executes data communication processing with the outside. The data reading unit 1317 is, for example, a scanner, and executes document reading processing. The data output unit 1318 is, for example, a printer, and executes document data output processing.

  Note that the hardware configuration of the image processing apparatus illustrated in FIG. 13 shows one configuration example, and the present embodiment is not limited to the configuration illustrated in FIG. 13, and the modules described in the present embodiment are executed. Any configuration is possible. For example, some modules may be configured with dedicated hardware (for example, Application Specific Integrated Circuit (ASIC), etc.), and some modules are in an external system and connected via a communication line Alternatively, a plurality of systems shown in FIG. 13 may be connected to each other via communication lines so as to cooperate with each other. Further, it may be incorporated in a copying machine, a fax machine, a scanner, a printer, a multifunction machine (an image processing apparatus having any two or more functions of a scanner, a printer, a copying machine, a fax machine, etc.).

In the above-described embodiment, the classification result integration module 130 integrates pixels between classifications based on the shape of the classified pixel group. In addition to the shape, the classification pixel is further classified. You may make it integrate based on a value. For example, the average pixel value in the classification to be integrated is calculated, and the integration is performed when the pixel group is divided in the classification and the distance of the average pixel value is within a predetermined threshold. It may be. Further, in addition to the shape, the circumscribed rectangles of the classification may be overlapped as the integration condition. Moreover, it is good also as conditions for integration that both shapes other than the shape are similar. “Similar” means, for example, a situation in which, when the two pixel groups are overlapped, the difference is not more than a predetermined value with respect to the area of the pixel group. A combination of these four conditions (pixel group shape (split), pixel value, circumscribed rectangle overlap, and shape similar) may be used.
Further, in the description of the embodiment, in the comparison with a predetermined value, “more than”, “less than”, “greater than”, “less than (less than)” is inconsistent in the combination. As long as it does not occur, “larger”, “smaller (less than)”, “more”, and “less” may be used.

The program described above may be provided by being stored in a recording medium, or the program may be provided by communication means. In that case, for example, the above-described program may be regarded as an invention of a “computer-readable recording medium recording the program”.
The “computer-readable recording medium on which a program is recorded” refers to a computer-readable recording medium on which a program is recorded, which is used for program installation, execution, program distribution, and the like.
The recording medium is, for example, a digital versatile disc (DVD), which is a standard established by the DVD Forum, such as “DVD-R, DVD-RW, DVD-RAM,” and DVD + RW. Standard “DVD + R, DVD + RW, etc.”, compact disc (CD), read-only memory (CD-ROM), CD recordable (CD-R), CD rewritable (CD-RW), Blu-ray disc ( Blu-ray Disc (registered trademark), magneto-optical disk (MO), flexible disk (FD), magnetic tape, hard disk, read-only memory (ROM), electrically erasable and rewritable read-only memory (EEPROM), flash Includes memory, random access memory (RAM), etc. .
The program or a part of the program may be recorded on the recording medium for storage or distribution. Also, by communication, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), a wired network used for the Internet, an intranet, an extranet, etc., or wireless communication It may be transmitted using a transmission medium such as a network or a combination of these, or may be carried on a carrier wave.
Furthermore, the program may be a part of another program, or may be recorded on a recording medium together with a separate program. Moreover, it may be divided and recorded on a plurality of recording media. Further, it may be recorded in any manner as long as it can be restored, such as compression or encryption.

110: Block division module 120 ... Pixel classification module 130 ... Classification result integration module 140 ... Data conversion module

Claims (5)

A dividing means for dividing the image into regions;
Classification means for classifying pixels in the area divided by the dividing means;
An image processing apparatus comprising: an integration unit that integrates pixels between classifications based on a shape of a pixel group classified by the classification unit. The image processing apparatus according to claim 1, wherein the integrating unit further integrates pixels between regions divided by the dividing unit based on the integrated pixels. 3. The integration unit according to claim 1, wherein the integration unit divides the classified pixel group based on an area of a circumscribed rectangle of the pixel group classified by the classification unit, and then integrates the pixels. Image processing apparatus. The image processing apparatus according to claim 1, further comprising: a configuration generation unit configured to generate a configuration of the image based on a result of integration by the integration unit. Computer
A dividing means for dividing the image into regions;
Classification means for classifying pixels in the area divided by the dividing means;
An image processing program that functions as an integration unit that integrates pixels between classifications based on the shape of a pixel group classified by the classification unit.

Images