JP2009301090A - Image processor and image processing program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To satisfactorily determine the type of an image by using the differential value of the frequency distribution of the pixel value of an object image. <P>SOLUTION: An image processor 10 includes an image acceptance part 11 for accepting the object image and a type determination part 12 for determining the type of the object image based on the differential value of the frequency distribution of the pixel value of the object image. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

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

  Various techniques have been proposed as an image processing technique (see, for example, Patent Documents 1 to 3).

  In Patent Document 1, as a method for identifying the characteristics of a color image, three primary color values representing a color image are input, a threshold binarization range is calculated based on the input value, and the threshold binarization range is included in the threshold binarization range. And binarizing the input value, identifying a color area in the image, defining a frame surrounding the color area, and binarizing a second threshold based on the input three primary color values corresponding to the color area A description is given of calculating a range and binarizing an input three primary color value corresponding to a color region based on the second threshold binarization range.

  Patent Document 2 describes an image processing apparatus that selectively uses two image processes according to the number of colors of a color image to be processed. Specifically, an image processing apparatus that performs labeling using color palette clustering for a color image with a small number of colors and performs labeling using an adjacent extension method for a color image with a large number of colors Is described.

  In Patent Document 3, foreground and background are separated from input image data, a line segment having a predetermined number of pixels is extracted from input image data, and the same label is assigned to connected pixels as foreground. The image feature amount is calculated for each label region to which the same label is assigned, the attribute of the label region is determined from the label feature amount for each label region, and the extracted line segment is calculated using the attribute determination result. An image processing apparatus for correcting the above is described.

Japanese Patent Laid-Open No. 2000-132589 JP 2000-172849 A JP 2001-127999 A

  It is an object of the present invention to provide an image processing apparatus and an image processing program that can favorably determine the type of image.

  The image processing apparatus according to the present invention includes: an image receiving unit that receives a target image; and a type determination unit that determines a type of the target image based on a differential value of a frequency distribution of pixel values of the target image. Features.

  An image processing apparatus according to the present invention includes an image receiving unit that receives an image, a background color specifying unit that specifies a background color of the image, and an area partitioned by the background color region from the image. The type of the target image is determined based on a region extraction means for extracting as a component region and a differential value of a frequency distribution of pixel values of the extracted image component region image (hereinafter referred to as “target image”). And a type determining means.

  An image processing apparatus according to the present invention includes an image receiving unit that receives an image, a background color specifying unit that specifies a background color of the image, and an area partitioned by the background color region from the image. Area extraction means for extracting as a component area, and classification means for classifying the extracted image component area into an area composed only of lines and other areas (hereinafter referred to as “picture areas”) And type determination means for determining the type of the target image based on the differential value of the frequency distribution of the pixel values of the image component region image (hereinafter referred to as “target image”) classified into the pattern region; It is characterized by having.

  In one aspect of the present invention, the type determination unit determines the type of the target image based on a frequency distribution of pixel values of the target image and a differential value of the frequency distribution.

  In the aspect of the invention, the type determination unit may have a relatively small number of target images when the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the frequency distribution is smaller than a predetermined lower threshold. If it is determined that the image is a non-continuous tone image of the number of colors (hereinafter referred to as “low-color non-continuous tone image”), and the number N1 of pixel values is larger than a predetermined upper threshold, the target image Is an image having a relatively large number of colors or a continuous tone image (hereinafter collectively referred to as “multicolor / continuous tone image”), and the number N1 of pixel values is equal to or greater than the lower threshold value. When the absolute value of the differential value is equal to or greater than a predetermined value and the number N2 of pixel values equal to or greater than the predetermined threshold when the absolute value of the differential value is equal to or lower than the upper threshold, the target image is determined to be a low-color non-continuous tone image , When the number N2 of pixel values is less than the predetermined threshold, Image is determined to be multi-color / continuous tone images.

  In one aspect of the present invention, the type determination unit generates a reduced image by reducing the target image to a predetermined resolution, or based on a differential value of a frequency distribution of pixel values of the reduced image, or the frequency distribution And the type of the target image is determined based on the differential value of the frequency distribution.

  In the aspect of the invention, the type determination unit reduces the target image so that an edge portion in the target image is stored.

  In the aspect of the invention, the type determination unit may determine a predetermined pixel value of the plurality of reference pixels when obtaining one pixel value of the reduced image from pixel values of the plurality of reference pixels in the target image. One pixel value of the reduced image is obtained based on the pixel value of the reference pixel and the pixel value of the reference pixel having a pixel value difference between the reference pixel other than the reference pixel and the reference pixel that is equal to or less than a predetermined value.

  An image processing program according to the present invention causes a computer to execute a procedure for receiving a target image and a procedure for determining the type of the target image based on a differential value of a frequency distribution of pixel values of the target image. Features.

  An image processing program according to the present invention includes: a procedure for accepting an image to a computer; a procedure for specifying a background color of the image; and a region partitioned by the background color region from the image. A procedure for extracting as a region, a procedure for determining the type of the target image based on a differential value of a frequency distribution of pixel values of the image of the extracted image component region (hereinafter referred to as “target image”), Is executed.

  An image processing program according to the present invention includes: a procedure for accepting an image to a computer; a procedure for specifying a background color of the image; and a region partitioned by the background color region from the image. A procedure for extracting as a region, a procedure for classifying the extracted image component region into a region composed only of lines, and a region other than that (hereinafter referred to as a “design region”), and the design region And a procedure for determining the type of the target image based on the differential value of the frequency distribution of the pixel values of the images of the image component region classified as follows (hereinafter referred to as “target image”). To do.

  According to the first aspect of the present invention, the type of the target image can be satisfactorily determined using the differential value of the frequency distribution of the pixel values of the target image.

  According to the invention described in claim 2, it is possible to satisfactorily determine the image type of the image component area in the image.

  According to the third aspect of the present invention, it is possible to satisfactorily determine the image type of the pattern area in the image.

  According to the invention described in claim 4, it is possible to satisfactorily determine the type of the target image using the frequency distribution of the pixel values of the target image and its differential value.

  According to the fifth aspect of the present invention, the target image is classified into the low-color non-continuous tone image and the multi-color / continuous-tone image using the frequency distribution of the pixel values of the target image and its differential value. It becomes possible.

  According to the sixth aspect of the present invention, it is possible to determine the type of the target image after uniformizing the color distribution in the substantially uniform color region in the target image.

  According to the seventh aspect of the present invention, it is possible to reduce the adverse effect on the determination of the type of the target image by the target image reduction process.

  According to the invention described in claim 8, it is possible to reduce the target image while reducing the adverse effect on the determination of the type of the target image by the reduction process of the target image.

  According to the ninth aspect of the present invention, it is possible to satisfactorily determine the type of the target image using the differential value of the frequency distribution of the pixel values of the target image.

  According to the invention described in claim 10, it is possible to satisfactorily determine the image type of the image component area in the image.

  According to the eleventh aspect of the present invention, it is possible to satisfactorily determine the image type of the pattern area in the image.

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

[First Embodiment]
FIG. 1 is a block diagram illustrating an example of a configuration of an image processing apparatus 10 according to the first embodiment. The image processing apparatus 10 is an apparatus that determines the type of image.

  In one embodiment, the image processing apparatus 10 is realized by cooperation of hardware resources and software, and is, for example, a computer. Specifically, the functions of the image processing apparatus 10 are realized by reading an image processing program recorded on a recording medium into a main memory and executing it by a CPU (Central Processing Unit). The image processing program can be provided by being recorded on a computer-readable recording medium such as a CD-ROM, or can be provided by communication as a data signal. However, the image processing apparatus 10 may be realized only by hardware. Further, the image processing apparatus 10 may be physically realized by one apparatus or may be realized by a plurality of apparatuses.

  As illustrated in FIG. 1, the image processing apparatus 10 includes an image reception unit 11, a type determination unit 12, and an image processing unit 13.

  The image receiving unit 11 receives a target image that is a determination target image. In one embodiment, the target image is a color image, for example, image data such as an RGB color space, a YCbCr color space, or a Lab color space. The target image is, for example, image data in which a plurality of pixels are arranged in a matrix in the horizontal direction and the vertical direction, and each pixel has pixel values of various color spaces. Note that the target image may be a grayscale image.

  The type determining unit 12 determines the type of the target image based on the differential value of the pixel value frequency distribution (hereinafter referred to as “histogram”) of the target image received by the image receiving unit 11.

  Here, the pixel values to be subjected to the histogram are, for example, lightness values, luminance values, and gradation values. More specifically, pixel values to be subjected to the histogram include, for example, a Y value (luminance value) in the YCbCr color space, an L value (lightness value) in the Lab color space, and a G value (green component level) in the RGB color space. Key value). The pixel value that is the target of the histogram may be any one pixel value (for example, Y of Y, Cb, and Cr) that constitutes the target image, or is calculated from a plurality of pixel values that constitute the target image. May be a pixel value (for example, Y calculated from R, G, and B).

  Specifically, the type determination unit 12 calculates a histogram of pixel values of the target image, calculates a differential value (specifically, a primary differential value) of the histogram, and determines the type of the target image based on the differential value. To do. In one specific aspect, the type determination unit 12 obtains a histogram representing the frequency value of each pixel value in the target image, and calculates the differential value of the histogram by calculating the difference between the frequency values of adjacent pixel values in the histogram. Ask for. For example, the type determination unit 12 counts each frequency value f (x) of the pixel value x (x = 0, 1, 2,..., 255), and the differential value d (x) = f (x) -F (x + 1) is calculated.

  In one aspect, the type determination unit 12 obtains the number of pixel values whose differential value is greater than or equal to a predetermined value, and determines the type of the target image based on the number of pixel values. Specifically, the type determination unit 12 determines that the target image is a first type image when the number of pixel values is equal to or greater than a predetermined threshold value T, and the number of pixel values is equal to the predetermined threshold value. If it is less than T, it is determined that the target image is the second type of image.

  In one aspect, the type determination unit 12 determines whether the target image is a non-continuous tone image having a relatively small number of colors (hereinafter referred to as a “low-color non-continuous tone image”). Is an image having a relatively large number of colors or a continuous tone image (hereinafter referred to as “multicolor / continuous tone image”), or the target image is a low-color non-continuous tone image and Which of the multicolor / continuous tone images is determined is determined based on the differential value of the histogram. In a specific aspect, the type determination unit 12 determines that the target image is a low-color non-continuous tone image when the number of pixel values whose differential value is greater than or equal to a predetermined value is equal to or greater than a predetermined threshold T. If the number of pixel values is less than the predetermined threshold T, it is determined that the target image is a multicolor / continuous tone image.

  The predetermined threshold T may be a fixed value or a variable value. For example, the type determination unit 12 obtains the number A of pixel values whose frequency values are not zero in the histogram, obtains the number B of pixel values having an absolute value of a differential value equal to or larger than a predetermined value, and B ≧ k · A (= T) In this case, it is determined that the target image is the first type image (or the low-color non-continuous tone image), and when B <k · A (= T), the target image is the second type image ( Or a multicolor / continuous tone image). However, k is a constant.

  As an image determined as the low-color non-continuous tone image, for example, an image in which a non-continuous tone foreground having a relatively small number of colors is arranged on a background of a non-continuous tone having a relatively small number of colors. Is mentioned. Examples of the foreground include characters, figures (including figures whose interiors are filled with colors), uniform color areas, and the like. More specifically, the image determined as the low-color non-continuous tone image includes, for example, an image created with draw software. On the other hand, examples of the image determined as the multicolor / continuous tone image include a photograph and a gradation image of computer graphics.

  In one aspect, the type determination unit 12 determines the type of the target image based on the pixel value histogram of the target image and the differential value of the histogram.

  In a specific aspect, the type determination unit 12 determines whether the target value is based on the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram and the number N2 of pixel values having an absolute value of a differential value equal to or greater than the predetermined value. Determine the type of image. In one aspect, the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram is the number of pixel values having a frequency value equal to or higher than a predetermined ratio (for example, 5%) of the mode value of the histogram.

  In a more specific aspect, the type determination unit 12 determines that the target image is a first type image (if the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram is smaller than a predetermined lower threshold value). Or the number N1 of pixel values is larger than a predetermined upper threshold value, the target image is a second type of image (multicolor / continuous tone image). Judge that there is. When the number N1 of pixel values is greater than or equal to the lower threshold and less than or equal to the upper threshold, the type determination unit 12 determines the type of the target image using the differential value of the histogram. That is, the type determination unit 12 determines that the target image is the first type image (or the low-color non-continuous tone image) when the number N2 of pixel values whose differential values are greater than or equal to a predetermined value is greater than or equal to a predetermined threshold. When the number N2 of pixel values is less than the predetermined threshold, it is determined that the target image is the second type image (or multicolor / continuous tone image). The predetermined threshold value may be a fixed value or a variable value as described above.

  FIG. 2 is a diagram showing a histogram of pixel values and an absolute value of a differential value of a general character / graphic image (specifically, an image in which characters and graphics are described on a substantially uniform color background). It is. FIG. 3 is a diagram illustrating a histogram of pixel values and an absolute value of a differential value of a general photographic image. 2 and 3, the histograms are normalized so that the mode value is 100. The same applies to FIGS. 4 and 5 later.

  As can be seen from FIGS. 2 and 3, the number of pixel values having a frequency value above a predetermined level (for example, 5% or more of the mode value) in the histogram is clearly larger in the photographic image than in the character / graphic image, From this, both images can be distinguished. For example, according to the above specific embodiment, the character / graphic image having the histogram of FIG. 2 is determined that the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram is smaller than a predetermined lower threshold value. It is determined that the image is a low-color discontinuous tone image. On the other hand, the photographic image having the histogram of FIG. 3 is determined to have a number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram larger than a predetermined upper threshold, and is determined to be a multicolor / continuous tone image. .

  FIG. 4 shows a histogram of pixel values and a differential value thereof of a character / graphic image expressed in several colors (specifically, a pie chart image having seven areas each uniformly filled with different colors). It is a figure which shows the absolute value of. FIG. 5 is a diagram illustrating a histogram of pixel values and an absolute value of a differential value of a photographic image having a relatively small number of colors as a photographic image (specifically, a desert photographic image).

  As can be seen from FIGS. 4 and 5, a character / graphic image expressed in several colors and a photographic image having a relatively small number of colors as a photographic image have the number of pixel values having a predetermined frequency value or more in the histogram. There is no clear difference, and the two images cannot be distinguished only by the number of the pixel values. 4 and 5, when the absolute value of the differential value is a predetermined level or more (for example, 10 or more), the number of pixel values is clearly larger in the character / graphic image than in the photographic image. From this, both images can be distinguished. For example, according to the above-described specific aspect, in the character / graphic image having the histogram of FIG. 4, the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram is greater than or equal to the lower threshold and less than or equal to the upper threshold. It is determined that the number N2 of pixel values having an absolute value of the differential value greater than or equal to a predetermined value is greater than or equal to a predetermined threshold, and it is determined that the image is a low-color discontinuous tone image. On the other hand, in the photographic image having the histogram of FIG. 5, it is determined that the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the histogram is greater than or equal to the lower threshold value and less than or equal to the upper threshold value. It is determined that the number N2 of pixel values is less than a predetermined threshold, and it is determined that the image is a multicolor / continuous tone image.

  The image processing unit 13 performs image processing corresponding to the type of the target image on the target image based on the determination result of the type determination unit 12.

  In one aspect, when it is determined that the target image is a low-color non-continuous tone image, the image processing unit 13 converts the character extraction method suitable for the low-color non-continuous tone image or a non-continuous tone image. Characters are extracted from the target image using a suitable character extraction method. On the other hand, when it is determined that the target image is a multicolor / continuous tone image, the image processing unit 13 performs character extraction method suitable for the multicolor / continuous tone image or character extraction suitable for the continuous tone image. Using the method, characters are extracted from the target image.

  In another aspect, when it is determined that the target image is a low-color non-continuous tone image, the image processing unit 13 generates vector image data by vectorizing the target image. On the other hand, when it is determined that the target image is a multicolor / continuous tone image, the image processing unit 13 does not vectorize the target image, and outputs it as bitmap image data, for example.

  FIG. 6 is a flowchart illustrating an example of the operation of the image processing apparatus 10 according to the first embodiment. Hereinafter, an example of the operation of the image processing apparatus 10 will be described with reference to FIG.

  The image processing apparatus 10 receives the target image (S11).

  Next, the image processing apparatus 10 determines the type of the target image based on the differential value of the histogram of the pixel value of the target image (S12). Specifically, the image processing apparatus 10 executes a type determination process shown in FIG.

  Then, the image processing apparatus 10 performs image processing corresponding to the type of the target image on the target image based on the determination result of step S12 (S13).

  Hereinafter, the type determination process of FIG. 7 will be described.

  The image processing apparatus 10 collects a histogram of pixel values of the target image (S101).

  Next, the image processing apparatus 10 determines the mode value of the collected histogram, and counts the number N1 of pixel values having a frequency value equal to or higher than a predetermined ratio of the mode value (S102).

  Next, the image processing apparatus 10 determines whether or not the number N1 of pixel values is smaller than a predetermined lower threshold (S103).

  When it is determined that the number N1 of pixel values is smaller than the predetermined lower threshold (S103: YES), the image processing apparatus 10 determines that the target image is a low-color non-continuous tone image (S104).

  On the other hand, when it is determined that the number N1 of pixel values is equal to or greater than the predetermined lower threshold (S103: NO), the image processing apparatus 10 determines whether the number N1 of pixel values is greater than the predetermined upper threshold. (S105).

  When it is determined that the number N1 of pixel values is greater than the predetermined upper threshold (S105: YES), the image processing apparatus 10 determines that the target image is a multicolor / continuous tone image (S106).

  On the other hand, when it is determined that the number N1 of pixel values is equal to or smaller than the predetermined upper threshold (S105: NO), the image processing apparatus 10 advances the process to step S107.

  In step S107, the image processing apparatus 10 collects the differential value of the histogram by calculating the difference between the frequency values of adjacent pixel values in the collected histogram.

  Next, the image processing apparatus 10 counts the number A of pixel values whose frequency values are not zero in the collected histogram (S108).

  Next, the image processing apparatus 10 counts the number N2 of pixel values in which the absolute value of the differential value is equal to or greater than a predetermined value in the differential value of the collected histogram (S109).

  Next, the image processing apparatus 10 determines whether or not a value N2 / A obtained by dividing the number N2 of pixel values by the number A of pixel values is equal to or greater than a predetermined threshold (S110).

  When it is determined that the value N2 / A is equal to or greater than the predetermined threshold (S110: YES), the image processing apparatus 10 determines that the target image is a low-color non-continuous tone image (S111).

  On the other hand, when it is determined that the value N2 / A is less than the predetermined threshold (S110: NO), the image processing apparatus 10 determines that the target image is a multicolor / continuous tone image (S112).

[Second Embodiment]
FIG. 8 is a block diagram illustrating an example of the configuration of the image processing apparatus 20 according to the second embodiment. The image processing apparatus 20 extracts an image component region (that is, an image component region) from the input image, determines an image type of the image component region, and performs image processing according to the image type. This is applied to the image of the image component area. In the following description, an image component is referred to as an “image object”, and an image component region is referred to as an “image object region”.

  The realization mode of the image processing apparatus 20 is the same as that of the first embodiment. That is, the image processing apparatus 20 may be realized by cooperation of hardware resources and software, or may be realized only by hardware. In addition, the image processing apparatus 20 may be physically realized by one apparatus or may be realized by a plurality of apparatuses. The image processing program for realizing the functions of the image processing apparatus 20 can be provided by being recorded on a computer-readable recording medium or can be provided by communication as a data signal. is there.

  As illustrated in FIG. 8, the image processing apparatus 20 includes an image receiving unit 21, a background color specifying unit 22, a region extracting unit 23, a type determining unit 24, and an image processing unit 25.

  The image receiving unit 21 receives an image (hereinafter referred to as “input image”). In one aspect, the input image is a color image, for example, image data such as an RGB color space, a YCbCr color space, or a Lab color space. The input image is, for example, image data in which a plurality of pixels are arranged in a matrix in the horizontal direction and the vertical direction, and each pixel has pixel values of various color spaces. In a specific aspect, the input image is bitmap image data of 8 bits for each color of RGB. The input image is, for example, image data generated by an image reading apparatus that optically reads a document image. However, the input image may be image data recorded on various recording media.

  FIG. 9 shows an example of a full-color input image. The input image in FIG. 9 includes a background 50 and foregrounds 51 to 54. In FIG. 9, hatched hatching represents a continuous tone region, and the foreground 51 is, for example, an image in which a character string “ABC” is described on a photograph. A halftone dot represents that the color is uniform, and a difference in the density of the halftone dot represents that the color is different. For example, the foregrounds 52 and 53 are images composed of one or more uniform color regions (also referred to as flat color regions). Here, the uniform color region is a region in which the background portion is expressed in a uniform color, and may include a foreground such as characters and figures. Specifically, the foreground 52 includes a uniform color region in which the character string “DEF” is described on the background of the first color and a uniform color in which the character string “GHI” is described on the background of the second color. This is an image in which regions are connected. The foreground 53 is an image of a uniform color area in which the character string “JKL” is described on the background of the third color. The foreground 54 is the character string “MNO”.

  The background color specifying unit 22 specifies the background color of the input image received by the image receiving unit 21. The background color specifying unit 22 may specify one specific color as the background color, or may specify a specific range of colors in the color space as the background color. The background color specifying unit 22 can specify the background color by various methods. For example, the background color specifying unit 22 specifies a color having the highest appearance frequency in the input image or a color within a predetermined range from the color as the background color.

  The area extraction unit 23 extracts an area partitioned by the background color area (that is, the background area) from the input image as an image object area. In one aspect, the region extraction unit 23 converts the input image into a binary image by classifying the pixels of the input image into pixels of the background color and pixels other than the background color. For example, the region extraction unit 23 sets the pixel value of the background color pixel to “0” and sets the pixel value of the pixels other than the background color to “1”, and displays the full color input image shown in FIG. A binary image is generated. In FIG. 10, the region with the pixel value “0” is expressed in white, and the region with the pixel value “1” is expressed in black. Next, the area extracting unit 23 extracts the area of each connected component of pixels other than the background color in the binary image as an image object area. Here, the connected component is a binary image in which pixels having the same value are connected to each other to form one lump. In a specific aspect, the region extraction unit 23 performs a labeling process on the binary image to generate a labeling image. Here, the labeling process is a process of assigning a different label for each connected component to each connected component pixel in the binary image. For example, the region extraction unit 23 performs a labeling process on the binary image of FIG. 10 to generate a labeling image shown in FIG. In FIG. 11, different connected label numbers 1, 2, 3, 4, 5, and 6 are assigned to the pixels of each connected component. Each pixel group region to which the same label number is assigned corresponds to an image object region. That is, in the example of FIG. 11, six image object regions with label numbers 1 to 6 are extracted.

  The type determination unit 24 determines the image type of the image object region extracted by the region extraction unit 23 in the same manner as the type determination unit 12 of the first embodiment. Specifically, the type determining unit 24 determines the type of the target image in the same manner as the type determining unit 12 using the extracted image of each image object region as the target image. In the example of FIGS. 9 to 11, the type determination unit 24 determines the image type of each of the six image object regions with label numbers 1 to 6. For example, the type determining unit 24 determines that the image of the image object area with the label number 1 (ie, the foreground 51) is a multicolor / continuous tone image, and the image object area with the label numbers 2 to 6 is small. It is determined that the image is a color non-continuous tone image.

  Similar to the image processing unit 13 of the first embodiment, the image processing unit 25 performs image processing corresponding to the type of the target image on the target image based on the determination result of the type determination unit 24. In the example of FIGS. 9 to 11, the image processing unit 25 performs image processing according to the type of image of the image object area for each of the images of the six image object areas with label numbers 1 to 6. Apply to images.

  FIG. 12 is a flowchart illustrating an example of the operation of the image processing apparatus 20 according to the second embodiment. Hereinafter, an example of the operation of the image processing apparatus 20 will be described with reference to FIG.

  The image processing apparatus 20 receives an input image (for example, 24-bit full color image data) (S21).

  Next, the image processing apparatus 20 specifies the background color of the input image (S22).

  Next, the image processing apparatus 20 extracts each area partitioned by the background color area from the input image as an image object area (S23). That is, the image processing device 20 detects an image object area on the background.

  Next, the image processing apparatus 20 determines the type of image for all the extracted image object region images by the same method as in the first embodiment (S24).

  Then, the image processing device 20 performs image processing corresponding to the type of the image on the image of each image object region based on the determination result of step S24 (S25).

[Third Embodiment]
FIG. 13 is a block diagram illustrating an example of the configuration of the image processing apparatus 30 according to the third embodiment. The image processing apparatus 30 extracts an image component area (that is, an image component area) from the input image, classifies the extracted image component area into a character area and a picture area, and classifies it into a picture area. The type of the image in the image component area is determined, and image processing corresponding to the type of image is performed on the image in the image component area. In the following description, an image component is referred to as an “image object”, and an image component region is referred to as an “image object region”.

  The implementation mode of the image processing apparatus 30 is the same as that of the first embodiment. That is, the image processing apparatus 30 may be realized by cooperation of hardware resources and software, or may be realized only by hardware. Further, the image processing apparatus 30 may be physically realized by one apparatus or may be realized by a plurality of apparatuses. The image processing program for realizing the functions of the image processing apparatus 30 can be provided by being recorded on a computer-readable recording medium or can be provided by communication as a data signal. is there.

  As illustrated in FIG. 13, the image processing apparatus 30 includes an image receiving unit 31, a background color specifying unit 32, an area extracting unit 33, a classification unit 34, a type determining unit 35, and an image processing unit 36.

  The image receiving unit 31 receives an image (hereinafter referred to as “input image”). The input image is the same as in the second embodiment.

  The background color specifying unit 32 specifies the background color of the input image received by the image receiving unit 31. The processing of the background color specifying unit 32 is the same as the processing of the background color specifying unit 22 of the second embodiment.

  The area extraction unit 33 extracts an area partitioned by the background color area (that is, the background area) from the input image as an image object area. The processing of the region extraction unit 33 is the same as the processing of the region extraction unit 23 of the second embodiment.

  The classification unit 34 refers to the image object region extracted by the region extraction unit 33 as a region composed of only lines (hereinafter referred to as “character region”) and other regions (hereinafter referred to as “picture region”). ).

  The character area is an area composed of only lines, such as characters, tables, and line drawings.

  In one aspect, the classification unit 34 specifies a circumscribed rectangle of each extracted image object area, and classifies each image object area into a character area and a picture area based on the circumscribed rectangle. Specifically, when the size (for example, area) of the circumscribed rectangle of the image object region is less than a predetermined value, the classification unit 34 classifies the image object region into a character region, and the size of the circumscribed rectangle is predetermined. In the above case, when the ratio (for example, area ratio) of the image object occupying the circumscribed rectangle is less than a predetermined value, the image object area is classified as a character area, and the ratio of the image object area occupying the circumscribed rectangle is When it is equal to or greater than the predetermined value, the image object area is classified into a pattern area.

  For example, in the example of FIGS. 9 to 11, the classification unit 34 classifies the image object areas with the label numbers 1 to 3 into picture areas and classifies the image object areas with the label numbers 4 to 6 into character areas.

  The type determination unit 35 determines the image type of the image object area classified into the pattern area by the classification unit 34 in the same manner as the type determination unit 12 of the first embodiment. Specifically, the type determination unit 35 determines the type of the target image in the same manner as the type determination unit 12 using the images of the respective image object areas classified into the pattern areas as target images. In the example of FIGS. 9 to 11, the type determination unit 35 determines the type of each image in the three image object areas with label numbers 1 to 3. For example, the type determination unit 35 determines that the image of the image object area with label number 1 (ie, foreground 51) is a multicolor / continuous tone image, and the image of the image object area with label numbers 2 and 3 (ie, foreground). 52, 53) are determined to be low-color non-continuous tone images.

  Similar to the image processing unit 13 of the first embodiment, the image processing unit 36 performs image processing corresponding to the type of the target image on the target image based on the determination result of the type determination unit 35. In the example of FIGS. 9 to 11, the image processing unit 36 performs image processing corresponding to the image type of the image object area for each of the three image object areas with the label numbers 1 to 3. Apply to images. For example, the image processing unit 36 extracts the character “ABC” on the image of the image object area with the label number 1 by a character extraction method suitable for a multicolor / continuous gradation image (or continuous gradation image), Characters “DEFGHI” and “JKL” on the images of the image object areas of numbers 2 and 3 are extracted by a character extraction method suitable for a low-color non-continuous tone image (or non-continuous tone image).

  FIG. 14 is a flowchart illustrating an example of the operation of the image processing apparatus 30 according to the third embodiment. Hereinafter, an example of the operation of the image processing apparatus 30 will be described with reference to FIG.

  The image processing apparatus 30 receives an input image (for example, 24-bit full color image data) (S31).

  Next, the image processing device 30 specifies the background color of the input image (S32).

  Next, the image processing apparatus 30 extracts each area partitioned by the background color area from the input image as an image object area (S33). That is, the image processing apparatus 30 detects an image object area on the background.

  Next, the image processing apparatus 30 classifies each image object area extracted in step S33 into a character area and a picture area (S34).

  Next, the image processing apparatus 30 determines the type of image for all the images in the image object area classified as the picture area in step S34 by the same method as in the first embodiment (S35). Specifically, the image processing apparatus 30 classifies the image of each image object area classified into the pattern area into a low-color non-continuous tone image and a multi-color / continuous-tone image.

  Then, the image processing apparatus 30 performs image processing according to the type of the image on the image of each image object region based on the determination result of step S35 (S36). Specifically, the image processing apparatus 30 uses a character extraction method suitable for a low-color non-continuous tone image (or non-continuous-tone image) for images classified as low-color non-continuous tone images. Then, characters extracted from the image are classified into a multi-color / continuous tone image, and a character extraction method suitable for the multi-color / continuous tone image (or continuous tone image) is used. Then, characters on the image are extracted.

[Fourth Embodiment]
The image processing apparatus according to the fourth embodiment is almost the same as the image processing apparatuses according to the first to third embodiments, but the type determination unit reduces the target image and generates a reduced image. The difference is that the type of the target image is determined based on the reduced image. Hereinafter, the process of the type determination unit in the fourth embodiment will be described. Note that, in the processing of the type determination unit in the fourth embodiment, description of parts common to the first to third embodiments will be omitted or simplified.

  In the present embodiment, the type determination unit generates a reduced image by reducing the target image to a predetermined resolution, and based on the differential value of the histogram of the pixel value of the reduced image, or the histogram and the differential value of the histogram Based on the above, the type of the target image is determined. Specifically, the type determination unit determines the type of the target image based on the differential value of the histogram of the reduced image or on the basis of the histogram and the differential value, as in the first to third embodiments. judge.

  The reduction process is performed from the following viewpoint, for example. In a printed material or a scanned image obtained by scanning the printed material, a monochrome region is also represented by a halftone dot, and thus there is a color variation within the monochrome region. When the reduction process is performed on such an image, the colors are made uniform, and variations in colors within the monochromatic region are suppressed. In the histogram of the pixel values of the reduced image, the peak shape is sharper than the histogram of the original printed image.

  If there is an edge part (boundary part) with a large pixel value difference (for example, luminance value or brightness value gradation difference) in the target image, simply reducing the target image may produce a color that did not exist originally. There is. For example, when the target image includes a boundary between a region having a pixel value of 0 and a region having a pixel value of 255, a peak appears at pixel values 0 and 255 in the pixel value histogram of the target image, but the resolution of the target image is reduced to 1 / In the histogram of pixel values of a reduced image reduced to 2, peaks appear at pixel values 0, 64, 128, 192, and 255.

  From a viewpoint of avoiding the above circumstances, in one aspect, the type determination unit reduces the target image so that the edge portion in the target image is preserved.

  Examples of a method for reducing the target image while preserving the edge portion include the following first and second reduction methods.

(First reduction method)
The type determination unit obtains one pixel value of the reduced image from pixel values of a plurality of reference pixels in the target image, thereby converting the target image into a reduced image having a predetermined resolution. The plurality of reference pixels are, for example, four pixels in a 2 × 2 window.

  In the reduction process, when obtaining one pixel value of the reduced image from the pixel value of the reference pixel, the type determination unit specifies the maximum value and the minimum value of the pixel values of the plurality of reference pixels, and sets the maximum value and the minimum value. When the difference is smaller than the predetermined value, one pixel value of the reduced image is obtained using the pixel values of all the reference pixels. For example, the average value of the pixel values of all the reference pixels is calculated, and the average value is set as the pixel value of the reduced image. On the other hand, when the difference between the maximum value and the minimum value is greater than or equal to a predetermined value, one predetermined pixel value among the pixel values of the plurality of reference pixels is determined as one pixel value of the reduced image. For example, the median value of the pixel values of the plurality of reference pixels or the pixel value having the largest number of appearances among the plurality of reference pixels is set as the pixel value of the reduced image.

(Second reduction method)
The type determination unit obtains one pixel value of the reduced image from pixel values of a plurality of reference pixels in the target image, thereby converting the target image into a reduced image having a predetermined resolution.

  In the reduction process, when obtaining one pixel value of the reduced image from the pixel value of the reference pixel, the type determining unit determines the pixel value of a predetermined standard pixel among the plurality of reference pixels and the reference pixel other than the standard pixel. Among them, one pixel value of the reduced image is obtained based on the pixel value of the reference pixel whose pixel value difference with the reference pixel is equal to or less than a predetermined value. The plurality of reference pixels are, for example, nine pixels in a 3 × 3 window, and the reference pixel is, for example, the center pixel of a 3 × 3 window.

  For example, the type determination unit calculates the difference between the pixel value of the reference pixel and the pixel value of each reference pixel other than the reference pixel, and the pixel value of the reference pixel and the pixel of the reference pixel whose calculated difference is equal to or less than a predetermined value An average value is calculated, and the average value is used as the pixel value of the reduced image.

  In one aspect, the type determination unit reduces the target image to a predetermined intermediate resolution image using the second reduction method, and the intermediate resolution image is predetermined using the first reduction method. Reduce to a reduced image with resolution. In another aspect, the type determining unit reduces the target image to an image with a predetermined intermediate resolution using the first reduction method, and uses the second reduction method to output the intermediate resolution image. Is reduced to a reduced image having a predetermined resolution.

  In addition, this invention is not limited to the said embodiment, It can change variously within the range which does not deviate from the summary of this invention.

It is a block diagram which shows an example of a structure of the image processing apparatus which concerns on 1st Embodiment. It is a figure which shows the absolute value of the histogram of a pixel value, and its differential value of a general character and figure image. It is a figure which shows the absolute value of the histogram of a pixel value, and its differential value of a general photographic image. It is a figure which shows the absolute value of the histogram of a pixel value, and its differential value of the character and figure image expressed by several colors. It is a figure which shows the absolute value of the histogram of a pixel value, and its differential value of a photographic image with relatively few colors as a photographic image. 3 is a flowchart illustrating an example of an operation of the image processing apparatus according to the first embodiment. It is a flowchart which shows an example of a kind determination process. It is a block diagram which shows an example of a structure of the image processing apparatus which concerns on 2nd Embodiment. It is a figure which shows an example of an input image. It is a figure which shows an example of the binary image obtained by binarizing the image of FIG. 9 with a background color. It is a figure which shows an example of the labeling image obtained by labeling the image of FIG. 12 is a flowchart illustrating an example of an operation of the image processing apparatus according to the second embodiment. It is a block diagram which shows an example of a structure of the image processing apparatus which concerns on 3rd Embodiment. 10 is a flowchart illustrating an example of an operation of the image processing apparatus according to the third embodiment.

Explanation of symbols

  10, 20, 30 Image processing device, 11, 21, 31 Image receiving unit, 12, 24, 35 Type determining unit, 13, 25, 36 Image processing unit, 22, 32 Background color specifying unit, 23, 33 Area extracting unit 34 Classification section.

Claims (11)

Image receiving means for receiving a target image;
Type determination means for determining the type of the target image based on the differential value of the frequency distribution of the pixel values of the target image;
An image processing apparatus comprising: Image receiving means for receiving images;
Background color specifying means for specifying the background color of the image;
An area extracting means for extracting an area partitioned by the background color area from the image as an image component area;
Type determination means for determining the type of the target image based on a differential value of a frequency distribution of pixel values of the extracted image component region image (hereinafter referred to as “target image”);
An image processing apparatus comprising: Image receiving means for receiving images;
Background color specifying means for specifying the background color of the image;
An area extracting means for extracting an area partitioned by the background color area from the image as an image component area;
Classifying means for classifying the extracted image component area into an area composed only of lines and an area other than that (hereinafter referred to as a “picture area”);
Type determination means for determining the type of the target image based on the differential value of the frequency distribution of the pixel values of the image component region image (hereinafter referred to as “target image”) classified into the picture region;
An image processing apparatus comprising: The image processing apparatus according to any one of claims 1 to 3,
The image processing apparatus according to claim 1, wherein the type determination unit determines the type of the target image based on a frequency distribution of pixel values of the target image and a differential value of the frequency distribution. The image processing apparatus according to claim 4,
The type determining means includes
When the number N1 of pixel values having a frequency value greater than or equal to a predetermined value in the frequency distribution is smaller than a predetermined lower threshold, the target image is a non-continuous tone image having a relatively small number of colors (hereinafter, “low color It is called a “non-continuous tone image”)
When the number N1 of pixel values is larger than a predetermined upper threshold, the target image is an image having a relatively large number of colors or a continuous tone image (hereinafter collectively referred to as “multicolor / continuous tone image”). )
When the number N1 of pixel values is greater than or equal to the lower threshold and less than or equal to the upper threshold, when the number N2 of pixel values where the absolute value of the differential value is greater than or equal to a predetermined value is greater than or equal to the predetermined threshold, the target image Is determined to be a low-color non-continuous tone image, and when the number N2 of pixel values is less than the predetermined threshold, the target image is determined to be a multi-color / continuous tone image.
An image processing apparatus. An image processing apparatus according to any one of claims 1 to 5,
The type determining unit generates a reduced image by reducing the target image to a predetermined resolution, and based on a differential value of a frequency distribution of pixel values of the reduced image, or based on the frequency distribution and a differential value of the frequency distribution. An image processing apparatus that determines a type of the target image based on the image. The image processing apparatus according to claim 6,
The image processing apparatus, wherein the type determination unit reduces the target image so that an edge portion in the target image is preserved. The image processing apparatus according to claim 7,
The type determining means, when obtaining one pixel value of the reduced image from pixel values of a plurality of reference pixels in the target image, a pixel value of a predetermined reference pixel of the plurality of reference pixels, and the reference An image processing apparatus that obtains one pixel value of the reduced image based on a pixel value of a reference pixel that has a pixel value difference that is not more than a predetermined value among reference pixels other than pixels. On the computer,
A procedure for receiving the target image;
A procedure for determining the type of the target image based on a differential value of a frequency distribution of pixel values of the target image;
An image processing program for executing On the computer,
The procedure for accepting images,
Identifying the background color of the image;
A procedure for extracting an area partitioned by the background color area from the image as an image component area;
A procedure for determining a type of the target image based on a differential value of a frequency distribution of pixel values of the extracted image component region image (hereinafter referred to as “target image”);
An image processing program for executing On the computer,
The procedure for accepting images,
Identifying the background color of the image;
A procedure for extracting an area partitioned by the background color area from the image as an image component area;
A procedure for classifying the extracted image component area into an area composed only of lines and an area other than that (hereinafter referred to as a “picture area”);
A procedure for determining the type of the target image based on the differential value of the frequency distribution of the pixel values of the image component region image (hereinafter referred to as “target image”) classified into the pattern region;
An image processing program for executing

Images