JP2005341098A - Image processing unit, program, and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To perform appropriate γ correction according to the attribute of an image in a single image. <P>SOLUTION: A character image is created from a multilevel image that is an original image at a character image creation 22, and an non-character image is created at a non-character image creation 24. The γ correction is performed to the character image at a character color identifier 25, and is performed to the non-character image at the non-character image creation 24. <P>COPYRIGHT: (C)2006,JPO&NCIPI

Description

  The present invention relates to a technique for compressing multi-value image data.

  As a technique for highly compressing multi-value document image data, Patent Document 1 discloses a technique in which a document image is separated into a character part and a picture part, and the character part is compressed by the MMR method and the picture part is compressed by the JPEG method. ing. According to this technology, by efficiently assigning a specific pixel to another binary image, the compression efficiency of the encoding process to be performed later is improved, and the file size is reduced when generating a highly compressed PDF file. be able to.

  Patent Document 2 discloses a technique for compressing a mask image that is a binary image of a character portion of a document image, a foreground that is color information of the character portion, and a background that is a pattern portion of the document image.

Japanese Patent No. 2611012 JP 2002-368986 A

  In the above prior art, since the document image is separated into the character part and the picture part and compressed and encoded, respectively, the document image is separated into the character part and the picture part in order to perform γ correction on the document image. However, it can be said that γ correction considering the characteristics of the character part and the picture part is possible, which is desirable.

  Also, when performing image smoothing or image resolution conversion to a low resolution, the image quality after a series of processing is affected depending on which stage in the series of processing in the prior art. sell.

  However, the conventional technology has not considered these points at all.

  An object of the present invention is to enable appropriate γ correction in one image according to the attribute of the image.

  Another object of the present invention is to enable high-quality image compression by executing smoothing of an image and resolution conversion of the image to a low resolution at an appropriate timing.

  (1) According to the present invention, means for identifying a multivalued image that is a processing target image or a portion having a specific attribute of the processing target image based on a binary image generated from the multilevel image; Generating a binary image in which a portion corresponding to the region not having the specific attribute and a portion corresponding to the region having the specific attribute are replaced with different pixel values, and the specific value for the multi-value image Means for generating a non-specific attribute multi-value image in which pixels of the attribute part are filled with a background color; means for performing γ conversion of the generated multi-value image; and colors constituting the specific attribute part Determining means, means for generating a binary image or a multi-value image of the specific attribute portion made of the determined color based on the binary image replaced with the different pixel values, and a binary after this generation Γ transformation of image or multi-valued image Means for compressing and encoding the multi-valued image of the part that is not the specific attribute after the γ conversion and the binary image or the multi-valued image of the specific attribute part after the γ conversion, An image processing apparatus comprising: means for collecting the images after compression encoding into one file.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and means for performing γ conversion of the generated binary image; Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color with respect to the multi-value image; and means for determining a color constituting the specific attribute portion; Means for generating color information indicating the determined color; means for performing γ conversion of the generated color information; a multi-value image of a portion that is not the specific attribute after the γ conversion; Binary image and the γ transformation Means for compression-encoding the said color information of an image processing apparatus which includes a means, to combine the images after the compression coding into a single file.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a part that is not the specific attribute filled in, means for performing γ conversion of the generated multi-valued image, means for determining a color constituting the specific attribute part, Means for generating a binary image or a multi-valued image of the specific attribute portion having the determined color based on the binary image replaced with different pixel values, and γ of the generated binary image or multi-valued image Means for performing the conversion; Means for compressing and encoding the multi-valued image of the part that is not the specific attribute after the γ conversion, and the binary image or the multi-valued image of the specific attribute part after the γ conversion, and the respective compression encoding A computer-readable program that causes a computer to execute a means for combining subsequent images into one file.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and means for performing γ conversion of the generated binary image; Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color with respect to the multi-value image; and means for determining a color constituting the specific attribute portion; Means for generating color information indicating the determined color; means for performing γ conversion of the generated color information; a multi-value image of a portion that is not the specific attribute after the γ conversion; Binary image and the γ transformation Means for compression-encoding the said color information of a program readable on a computer that is running a unit, to the computer to combine the images after the compression coding into a single file.

(2) The present invention viewed from another aspect is a unit for identifying a portion having a specific attribute of a processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image. When,
Means for generating a binary image in which a portion corresponding to a region that is not the specific attribute of the multi-valued image and a portion corresponding to the region having the specific attribute are replaced with different pixel values; Means for generating a multi-valued image of a portion that is not the specific attribute in which pixels of the specific attribute portion are filled with a background color, means for determining a color constituting the specific attribute portion, and the different pixels Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with a value, a multi-value image of a portion that is not the specific attribute, and the specific image Means for compressing and encoding each binary image or multi-valued image of the attribute part, and means for combining the images after the respective compression encoding into one file, and the means for generating the multi-valued image includes: In the image to be processed Means for obtaining a peripheral color of the specific attribute portion from the multi-valued image, means for replacing the pixel value of the specific attribute portion from the multi-value image as the processing target image with the peripheral color, and the processing target image. Means for obtaining a peripheral color of a multi-valued image and smoothing it later.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; With The means for generating the multi-valued image includes means for obtaining a peripheral color of the specific attribute portion from the multi-value image that is the processing target image, and pixels of the specific attribute portion from the multi-value image that is the processing target image. An image processing apparatus comprising: means for replacing a value with the surrounding color; and means for smoothing a multi-valued image, which is the processing target image, after obtaining the surrounding color.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a part that is not the specific attribute filled in, means for determining a color constituting the specific attribute part, and the determination based on the binary image replaced with the different pixel values Means for generating a binary image or a multi-valued image of the specific attribute part made of the selected color, a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part Each compression mark Means for generating the multi-valued image, and means for generating the multi-valued image from the multi-valued image as the processing target image. Means for obtaining a peripheral color of the attribute portion, means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image, and the multi-value image that is the processing target image A computer-readable program that causes a computer to execute a means for obtaining a color and smoothing it later.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; , The compilation Means for generating the multi-valued image, means for obtaining a peripheral color of the specific attribute portion from the multi-valued image as the processing target image, and the multi-valued image as the processing target image. A computer-readable program that causes a computer to execute means for replacing pixel values of a specific attribute portion with the surrounding color and means for smoothing a multi-valued image that is the processing target image after obtaining the surrounding color. It is.

  (3) According to another aspect of the present invention, means for identifying a portion having a specific attribute of a processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image. And a means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values; Means for generating a multi-valued image of a portion that is not the specific attribute in which pixels of the specific attribute portion are filled with a background color with respect to the value image; means for determining a color that constitutes the specific attribute portion; Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on a binary image replaced with a different pixel value; a multi-value image of a portion which is not the specific attribute; and Binary image of specific attribute part Or means for compressing and encoding each of the multi-valued images and means for combining the images after the respective compression and encoding into one file, and the means for generating the multi-valued image is a multi-image to be processed. Means for obtaining a peripheral color of the specific attribute portion from the value image; means for replacing the pixel value of the specific attribute portion with the peripheral color from the multi-value image which is the processing target image; An image processing apparatus comprising: means for smoothing a value image; and means for converting the resolution of a multi-value image that is the processing target image into a low resolution before executing the smoothing.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; With The means for generating the multi-valued image includes means for obtaining a peripheral color of the specific attribute portion from the multi-value image that is the processing target image, and pixels of the specific attribute portion from the multi-value image that is the processing target image. Means for replacing values with the surrounding color, means for smoothing the multi-valued image as the processing target image, and converting the resolution of the multi-valued image as the processing target image to a low resolution before executing the smoothing And an image processing apparatus.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a part that is not the specific attribute filled in, means for determining a color constituting the specific attribute part, and the determination based on the binary image replaced with the different pixel values Means for generating a binary image or a multi-valued image of the specific attribute portion made of the selected color, a multi-value image of a portion that is not the specific attribute, and a binary image or a multi-value image of the specific attribute portion Each compression mark Means for generating the multi-valued image, and means for generating the multi-valued image from the multi-valued image as the processing target image. Means for obtaining the peripheral color of the attribute portion, means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image, and smoothing the multi-value image that is the processing target image And a computer-readable program for causing a computer to execute a means for converting the multi-valued image as the processing target image into a low resolution before executing the smoothing.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; , The compilation Means for generating the multi-valued image, means for obtaining a peripheral color of the specific attribute portion from the multi-valued image as the processing target image, and the multi-valued image as the processing target image. Means for replacing pixel values of a specific attribute portion with the surrounding color, means for smoothing the multi-valued image as the processing target image, and before executing the smoothing of the multi-valued image as the processing target image A computer-readable program for causing a computer to execute means for converting the resolution to low resolution.

  (4) The present invention viewed from another aspect is a unit for identifying a portion having a specific attribute of a processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image. And a means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values; Means for generating a multi-valued image of a portion that is not the specific attribute in which pixels of the specific attribute portion are filled with a background color with respect to the value image; means for determining a color that constitutes the specific attribute portion; Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on a binary image replaced with a different pixel value; a multi-value image of a portion which is not the specific attribute; and Binary image of specific attribute part Or means for compressing and encoding each of the multi-valued images and means for combining the images after the respective compression and encoding into one file, and the means for generating the multi-valued image is a multi-image to be processed. Means for obtaining a peripheral color of the specific attribute portion from the value image; means for replacing the pixel value of the specific attribute portion with the peripheral color from the multi-value image which is the processing target image; Means for obtaining a peripheral color of the value image and converting the resolution to a low resolution later.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; With The means for generating the multi-valued image includes means for obtaining a peripheral color of the specific attribute portion from the multi-value image that is the processing target image, and pixels of the specific attribute portion from the multi-value image that is the processing target image. An image processing apparatus comprising: means for replacing a value with the surrounding color; and means for determining the surrounding color of the multi-valued image that is the processing target image and then converting the resolution to a low resolution.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a part that is not the specific attribute filled in, means for determining a color constituting the specific attribute part, and the determination based on the binary image replaced with the different pixel values Means for generating a binary image or a multi-valued image of the specific attribute part made of the selected color, a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part Each compression mark Means for generating the multi-valued image, and means for generating the multi-valued image from the multi-valued image as the processing target image. Means for obtaining a peripheral color of the attribute portion, means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image, and the multi-value image that is the processing target image A computer-readable program for causing a computer to execute a means for obtaining a color and then converting the resolution to a lower resolution.

Or
Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image which is a processing target image or a binary image generated from the multi-value image, and not the specific attribute of the multi-value image Means for generating a binary image in which a portion corresponding to a region and a portion corresponding to the region having the specific attribute are replaced with different pixel values; and a pixel of the specific attribute portion in the multi-value image Means for generating a multi-valued image of a portion that is not the specific attribute filled in, means for determining a color constituting the specific attribute portion, means for generating color information indicating the determined color, Means for compressing and encoding each of the multi-valued image of a portion not having a specific attribute, the binary image of the specific attribute portion, and the color information, and means for combining the images after each compression encoding into one file; , The compilation Means for generating the multi-valued image, means for obtaining a peripheral color of the specific attribute portion from the multi-valued image as the processing target image, and the multi-valued image as the processing target image. Read by a computer that causes a computer to execute means for replacing a pixel value of a specific attribute portion with the surrounding color, and means for obtaining the surrounding color and then converting the resolution to a low resolution for the multi-valued image that is the processing target image. It is a possible program.

  According to the present invention of (1), a specific attribute portion such as a character and other images are generated from the processing target image, and γ correction is independently performed on each image, and γ corresponding to the image attribute is obtained. The correction can be made and the user's request can be met.

  According to the present invention of (2), the color of the specific attribute portion does not remain in the image other than the specific attribute portion, and the image other than the specific attribute portion can be accurately separated.

  According to the present invention of (3), the resolution conversion to the low resolution is executed for the specific attribute portion before the smoothing, so that the smoothing process can be performed at a high speed.

  According to the present invention of (4), the peripheral color of the specific attribute portion is specified before the resolution conversion to the low resolution, so that the character image position becomes ambiguous by the resolution conversion to the low resolution. Therefore, it is possible to accurately perform the process of specifying the peripheral color of the character.

  The best mode for carrying out the present invention will be described.

  FIG. 1 is a block diagram showing an electrical connection of the image processing apparatus 1 according to the present embodiment. As shown in FIG. 1, the image processing apparatus 1 is a computer such as a PC, and performs various calculations and centrally controls each part of the image processing apparatus 1, and a memory 3 including various ROMs and RAMs. Are connected by a bus 4.

  A bus 4 includes a magnetic storage device 5 such as a hard disk, an input device 6 such as a keyboard and a mouse, a display device 7, and a storage medium reader 9 that reads a storage medium 8 such as an optical disk via a predetermined interface. And a predetermined communication control device 12 that communicates with the network 11 is connected. As the storage medium 8, various media such as optical disks such as CD and DVD, magneto-optical disks, and flexible disks can be used. Further, as the storage medium reading device 18, specifically, an optical disk drive device, a magneto-optical disk drive device, a flexible disk drive device, or the like is used according to the type of the storage medium 17.

  The image processing apparatus 1 reads the image processing program 13 for executing the program of the present invention from the storage medium 8 for executing the storage medium of the present invention, and installs it in the magnetic storage device 5. These programs may be downloaded and installed via the network 11 such as the Internet. With this installation, the image processing apparatus 1 is in a state in which predetermined processing described later can be executed. The image processing program 13 may operate on a predetermined OS.

  FIG. 2 is a functional block diagram of processing executed by the image processing apparatus 1 by the image processing program 13. The image processing apparatus 1 includes a preprocessing unit 21, a character image creation unit 22, a non-character image creation unit 24, a character color identification unit 25, an image encoding unit 26, and a summary file creation unit 27 according to the image processing program 13. Realize the function. Hereinafter, basic functions of these functional units will be described.

  First, a multi-value document image, which is an original image to be processed, in this example, a 24-bit color image, is subjected to preprocessing such as edge enhancement and smoothing processing by the preprocessing unit 21.

  Thereafter, the character image creating unit 23 identifies a portion having a specific attribute (specific attribute portion) from this original image, in this example, the position of the character portion. In order to know the position of this character part, when acquiring directly from the original image, it is possible to generate a binary image from the original image and acquire from this binary image (when acquiring directly from the original image) In the case of generating a binary image from an original image by using a known technique disclosed in Japanese Patent Laid-Open No. 2002-288589, etc., and obtaining it from this binary image, a known technique disclosed in Japanese Patent Laid-Open No. 6-20092 or the like. See). In this example, it is assumed that a binary image is generated from a multi-valued image and acquired from this binary image. Then, the character image creation unit 23 replaces a portion corresponding to a region (character portion) which is not a specific attribute of the original image which is a multi-valued image and a portion corresponding to a region having a specific attribute with different pixel values. Generate binary images. In this example, black pixels other than characters are erased to form white pixels in the binary image. With this processing, the position of the character can be known in pixel units.

  The character color specifying unit 25 determines the color of the character that is the specific attribute portion. This obtains all pixel colors of the color image at the positions of the black pixels constituting the character, and selects several colors most frequently used in the image from this data as representative colors. Then, it is determined for each pixel or for each connected component which representative color the pixel constituting the character is closest to. Then, an image is generated in which the pixel having the specific attribute has a color determined for each pixel or each connected component. This may be a multi-value image having only a limited color, or a binary image may be generated for each color.

  The non-character image creation unit 24 creates an image in which characters that are specific attribute portions are deleted. This can be done by creating an image in which the pixels of the character portion that is the specific attribute portion are replaced with surrounding colors in the color image.

  The image encoding unit 26 generates a compressed image from an image (non-character image) from which the generated specific attribute pixel is deleted and an image (character image) including only the specific attribute pixel. For example, the non-character image may be compressed by the JPEG method, and the character image may be compressed by the MMR method or the PNG method, thereby effectively reducing the file size.

  Then, the summary file creation unit 27 synthesizes the non-character image in a form that allows the character image to be superimposed and displayed. When the file created by combining in this way is decoded, if these images are overlapped, characters are pasted on the background and can be viewed in the same manner as the original image.

  Next, another functional example of a functional block diagram of processing executed by the image processing apparatus 1 shown in FIG. 2 will be described. In this example, differences from the above-described function example will be described, and detailed description of common points will be omitted. In this example, different functions are functions of the character color specifying unit 25, the image encoding unit 26, and the like.

  The character color specifying unit 25 generates a character mask image from the generated binary image of only characters. Bit ON (here, black pixel) is processed as a pixel to be left in the mask process, and bit OFF (here, white pixel) is processed as a pixel not to be left in the mask process. In addition, the character color corresponding to the black pixel of the specific attribute portion is acquired from the original image, and the black pixel of the character of the specific attribute portion is filled. Then, this image is generated as a foreground image (color information). At this time, pixel portions other than characters are drawn as a background color.

  The image encoding unit 26 compresses the background image using the JPEG (DCT) method, compresses the character mask image including only the specific attribute pixels using the MMR method, and applies the JPEG (DCT) method to the foreground image in which only the specific attribute portion is drawn. Compress with.

  Next, the contents of characteristic processing executed by the image processing apparatus 1 will be described.

  FIG. 3 is a functional block diagram for explaining characteristic processing executed by the character color specifying unit 25.

  The character color specifying unit 25 receives the character image (including ruled lines) created by the character image creation unit 22 and the 24-bit color image formed by the pre-processing unit 21 as “input character color representative color calculation processing”. , “Character color identification processing” and “γ correction processing” are performed to generate a colored character image.

  First, the representative color calculation processing unit 31 performs a process of reducing the color of the character part to the number of colors specified by the user. This process mainly includes two processes: “character part color histogram generation” and “representative color selection from histogram”. Next, these processes will be described.

Character part color histogram generation The pixel value of the part corresponding to the character of the binary image of only the character created by the character image creating part 22 is obtained from the 24-bit color image created by the preprocessing part 21, and RGB Generate a color histogram of. The histogram created here is quantized into 8 colors for each RGB component, the color space is divided into 8 × 8 × 8 colors, and the number of pixels belonging to this space is counted.

Selection of representative color from histogram From the RGB histogram created as described above, 128 colors are selected in descending order of their frequencies and set as initial representative colors. However, there are too many achromatic colors to be selected, so there are restrictions so that achromatic colors are not selected more than a certain amount. If the selected achromatic color exceeds half the maximum number of character colors given by the user, no more are selected. However, the only black color that makes up the characters is an exception. If it exceeds half, only that color is additionally selected.

  Next, the closest color pair is selected from the selected colors, and the one having the smaller number of pixels is deleted from the representative color. This is repeated until the number of colors given by the user is reduced. Even when the color is reduced to the color designated by the user, if the closest color is smaller than a predetermined threshold, it is determined that the color reduction is insufficient and the color reduction is continued. For this reason, the number of colors given by the user is the maximum number of colors.

  The character color specification processing unit 32 performs coloring in character units (rectangular units) when the size of the rectangle formed by the black connected components is smaller than a predetermined size.

  First, an average color (RGB value) inside the character stroke excluding the character edge in the black connected component and an average color RGB value of all pixels constituting the character are obtained. Next, it is determined whether these colors are achromatic colors.

  The average color inside the character stroke in the small connected component and the average color of all the pixels constituting the character are obtained, and one of them is compared with the above-mentioned representative color, and the closest representative color is set as the character color of the corresponding rectangle.

  Here, when the stroke of the connected component is thin and there are only pixels that touch the background pixel, it is possible to compare the darkest color with the representative color to prevent the background color from mixing, but in the darkest color, depending on the character The color tends to vary, and when it is finally reproduced as a character, the color may vary depending on the character. Therefore, in such a case, the average color of all the pixels constituting the character is compared with the representative color. If there is a pixel in the character stroke that is not in contact with the background pixel, the average color is compared with the representative color.

  However, when the obtained average color is an achromatic color (when the absolute value of the difference between the RGB values is smaller than a predetermined threshold. For example, | R−G | <th), a predetermined value is obtained from the RGB value. The reproducibility of black characters is improved by comparing the representative color with the value obtained by subtracting.

  The γ correction unit 33 may make the character color brighter or darker depending on the clustering result of the input image and the character color. Therefore, in order to adjust the brightness value of the character image, Make corrections. The γ correction is performed collectively for RGB.

  Next, the flow of processing in the non-character image creation unit 24 will be described with reference to FIG. The non-character image is created by inputting the 24-bit color image output from the preprocessing unit 21 and the binary image of only the character output from the character image generation unit 22 as “specification of character peripheral color”, By replacing the character color with the specified character peripheral color, each process of “character part removal (hole filling)”, “resolution conversion (lower resolution)”, “smoothing”, and “γ correction” is performed.

  First, the peripheral color specifying unit 41 performs processing for specifying the peripheral color of a character. First, a pixel value of a color image corresponding to rectangular coordinates around a character rectangle of a character-only binary image is obtained. An average value of the obtained pixel values is calculated and set as a color around the connected component. It should be noted that only pixels that are white pixels of the binary image are targeted in order to accommodate the entry of characters.

  Next, the character part removal unit 42 performs character part removal (hole filling) processing on the image. In other words, the pixel value of the portion constituting the character of the color image with the peripheral color obtained by the peripheral color specifying unit 41 is replaced with the peripheral color. Since the surrounding color can be approximately regarded as the background color, a color image in which the characters disappear is generated.

  Then, the resolution conversion unit 43 performs image resolution conversion (reduction in resolution). That is, the file size is reduced by reducing the resolution of the background image. The degree of resolution reduction can be specified by the user, but it is generally preferable that 2 × 2 pixels are combined into one pixel. Specifically, an average color of 2 × 2 pixels of a color image from which characters are erased is obtained, and this pixel value is used as a pixel value of one pixel of a background image with a reduced resolution.

  Next, smoothing processing is performed by the smoothing unit 44. That is, when a photograph is included in the background image, if the resolution is lowered, the portion may not be reproduced properly. Therefore, the background image is smoothed. Smoothing is performed by applying a 3 × 3 pixel size spatial filter, as in the smoothing of the original image.

  The γ correction unit 45 executes γ correction. Depending on the combination of the scanner that acquires the original image to be processed by the image processing apparatus 1 and the image printer that has been processed by the image processing apparatus 1, the image obtained by the processing so far is entirely dark or It may be reproduced with bright colors. Therefore, in order to adjust the brightness value of the background image, γ correction is performed as shown in FIG. γ correction is performed for RGB at once. This also has the effect of increasing the compression efficiency when the background image is compressed by the JPEG method.

  With the configuration as described above, the image processing apparatus 1 separates the image into a character image and a non-character image, and then separates the image into a character image and a non-character image, and then independently by the γ correction units 33 and 45. Γ correction is performed.

  This makes it possible to execute different γ corrections for character images and non-character images, such as making character images darker and brighter, but background images darker and lighter. Therefore, it is possible to meet the demands of users who want to perform different γ corrections.

  In addition, for the non-character image, the specification of the peripheral color by the peripheral color specifying unit 41 is performed before the smoothing by the smoothing unit 44. The peripheral color specifying unit 41 performs processing for specifying the peripheral color of the character. If this processing is performed after the image is smoothed, the character color is mixed into the peripheral color of the character, and the character color is added to the non-character image. It will remain. Therefore, by performing the specification of the peripheral color by the peripheral color specifying unit 41 before the smoothing by the smoothing unit 44, the character color does not remain in the non-character image, and the non-character image is accurately separated. be able to.

  Further, the resolution conversion of the non-character image to the low resolution by the resolution conversion unit 43 is also performed before the smoothing by the smoothing unit 44. This is because if the image size is reduced by resolution conversion, smoothing processing can be performed at high speed.

  In addition, the specification of the peripheral color by the peripheral color specifying unit 41 is performed before the resolution conversion to the low resolution by the resolution converting unit 43. This is because when the resolution conversion to a low resolution is performed, the position of the character image becomes ambiguous and it is difficult to accurately specify the peripheral color of the character.

1 is a block diagram of electrical connection of an image processing apparatus according to an embodiment of the present invention. It is a functional block diagram of the process which an image processing apparatus performs. It is a functional block diagram explaining the process which a character color specific | specification part performs. It is explanatory drawing explaining gamma conversion. It is a functional block diagram explaining the process which a non-character image creation part performs.

Explanation of symbols

1 Image processing device 8 Storage medium 13 Program

Claims (19)

Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for performing γ conversion of the generated multi-valued image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for performing γ conversion of the generated binary image or multi-valued image;
Means for compressing and encoding the multi-valued image of the part that is not the specific attribute after the γ conversion, and the binary image or the multi-valued image of the specific attribute part after the γ conversion;
Means for combining the images after compression encoding into one file;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for performing γ conversion of the generated binary image;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for performing γ conversion of the generated color information;
Means for compressing and encoding each of the multi-value image of the non-specific attribute portion after the γ conversion, the binary image of the specific attribute portion, and the color information after the γ conversion;
Means for combining the images after compression encoding into one file;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image after obtaining the peripheral color;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image after obtaining the peripheral color;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image;
Means for converting the resolution of the multi-valued image as the processing target image to a low resolution before performing the smoothing;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image;
Means for converting the resolution of the multi-valued image as the processing target image to a low resolution before performing the smoothing;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for determining the peripheral color of the multi-valued image that is the processing target image and then converting the resolution to a low resolution;
An image processing apparatus. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
With
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for determining the peripheral color of the multi-valued image that is the processing target image and then converting the resolution to a low resolution;
An image processing apparatus.   The image processing apparatus according to claim 1, further comprising means for transmitting the combined file via a predetermined network.   The image processing apparatus according to claim 1, further comprising means for decoding each of the compressed and encoded images included in the combined file. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for performing γ conversion of the generated multi-valued image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for performing γ conversion of the generated binary image or multi-valued image;
Means for compressing and encoding the multi-valued image of the part that is not the specific attribute after the γ conversion, and the binary image or the multi-valued image of the specific attribute part after the γ conversion;
Means for combining the images after compression encoding into one file;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for performing γ conversion of the generated binary image;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for performing γ conversion of the generated color information;
Means for compressing and encoding each of the multi-value image of the non-specific attribute portion after the γ conversion, the binary image of the specific attribute portion, and the color information after the γ conversion;
Means for combining the images after compression encoding into one file;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image after obtaining the peripheral color;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image after obtaining the peripheral color;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image;
Means for converting the resolution of the multi-valued image as the processing target image to a low resolution before performing the smoothing;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for smoothing the multi-valued image as the processing target image;
Means for converting the resolution of the multi-valued image as the processing target image to a low resolution before performing the smoothing;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating a binary image or a multi-value image of the specific attribute portion composed of the determined color based on the binary image replaced with the different pixel values;
Means for compressing and encoding a multi-valued image of a part that is not the specific attribute, and a binary image or a multi-valued image of the specific attribute part;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for determining the peripheral color of the multi-valued image that is the processing target image and then converting the resolution to a low resolution;
A computer-readable program that causes a computer to execute. Means for identifying a portion having a specific attribute of the processing target image based on a multi-value image that is a processing target image or a binary image generated from the multi-value image;
Means for generating a binary image in which a portion corresponding to the region that is not the specific attribute of the multi-valued image and a portion corresponding to the region that is the specific attribute are replaced with different pixel values;
Means for generating a non-specific attribute multi-value image in which pixels of the specific attribute portion are filled with a background color for the multi-value image;
Means for determining a color constituting the specific attribute portion;
Means for generating color information indicating the determined color;
Means for compressing and encoding each of the multi-valued image of the part not having the specific attribute, the binary image of the specific attribute part, and the color information;
Means for combining the images after compression encoding into one file;
To the computer,
The means for generating the multi-valued image includes
Means for obtaining a peripheral color of the specific attribute portion from the multi-value image which is the processing target image;
Means for replacing the pixel value of the specific attribute portion with the surrounding color from the multi-value image that is the processing target image;
Means for determining the peripheral color of the multi-valued image that is the processing target image and then converting the resolution to a low resolution;
A computer-readable program that causes a computer to execute. A storage medium storing the program according to claim 11.

Images