JP2010119006A - Image processing apparatus,and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a novel image processing apparatus and an image processing method, capable of removing a background color from an input image in consideration of the background color of the input image. <P>SOLUTION: The invention relates to an image processing apparatus including: a creation means for creating a three-dimensional (3D) histogram on the basis of color information in a 3D color space of pixels constituting an input image; and a calculation means for calculating a color range of a background color of the input image while using lightness information of a color, having a degree equal to or more than a threshold, in the 3D histogram. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

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

  Conventionally, as an image processing method for removing a background color from an input image obtained by reading a document with a scanner, the most frequent lightness is determined as a background color removal level from a lightness histogram of a pixel group constituting the input image, and the input image There is a method of removing, as a background color, a pixel having a lightness equal to or higher than a background color removal level from the pixel group constituting the pixel group.

On the other hand, as a conventional method for determining whether an input image is a color image or a monochrome image, a brightness histogram is applied to a pixel group (region) determined as a chromatic pixel among the pixel groups constituting the input image. Generating and analyzing whether or not the chromatic pixel is a pixel constituting a background color by analyzing the shape of the lightness histogram or the like, and if the chromatic pixel is judged to be a pixel constituting a background color, There is a method for determining that the input image is a monochrome image (see, for example, Patent Document 1).
JP 2005-286571 A

  However, in the prior art, when performing image processing for removing the background color from the input image, the most frequent lightness is determined as the background color removal level on the lightness histogram, so the non-background of the input image has the same lightness. When there are pixels of a plurality of colors, there is a problem that the brightness may be selected as the most frequent brightness.

  Furthermore, in the method of determining the background removal level using the brightness histogram, when the input image is determined to be a color image according to the method of Patent Document 1, the background color is removed from the input image, so In addition to the histogram, it is also necessary to newly create a brightness histogram for the entire input image.

  In Patent Document 1, if a chromatic pixel constitutes a background color and is determined to be monochrome, it is not necessary to generate a histogram again, but the document is monochrome (when it is configured with an achromatic color), and monochrome. If it is determined that the chromatic pixel is not a background color but a color, it is necessary to generate a histogram again when performing the background removal process. Also, such chromatic pixels constitute the background color, and images that are determined to be monochrome are rare as normal images, and in many images, the background, ground color, show-through, etc. The color may be close to an achromatic color. Therefore, when background removal processing is performed, it is necessary to generate a histogram again, which causes a problem.

  SUMMARY OF THE INVENTION Accordingly, it is an object of the present invention to provide a new image processing apparatus and image processing method that can solve the above-described problems and can remove a background color from an input image in consideration of the background color of the input image. To do.

  In addition, the number of histograms for determining the background removal level can be reduced, and color / monochrome discrimination can be performed.

  An image processing apparatus according to the present invention includes a creating unit that creates a three-dimensional histogram based on color information in a three-dimensional color space of each pixel constituting an input image, and the brightness of a color having a frequency equal to or higher than a threshold in the three-dimensional histogram. Calculating means for calculating a color range of the background color of the input image using the information.

  The image processing apparatus according to the present invention determines whether the input image is a color image or a monochrome image based on a frequency of a chromatic color included outside the color range of the background color in the three-dimensional histogram. There may be a discriminating means.

  Furthermore, in the image processing apparatus of the present invention, the calculation means determines a color having the highest frequency in the three-dimensional histogram, determines a lightness corresponding to the color, and a range of colors having a lightness equal to or higher than the determined lightness. May be determined as the color range of the background color.

  Furthermore, the image processing apparatus of the present invention may include a changing unit that changes a color included in the color range of the background color to a predetermined color for each pixel constituting the input image.

  Furthermore, in the image processing apparatus of the present invention, when the frequency of a specific chromatic color is equal to or less than a predetermined value, the determination unit can determine the input image as a monochrome image.

  Furthermore, in the image processing apparatus according to the present invention, whether the creation unit is a pixel corresponding to an edge portion in the input image based on peripheral pixel information of the pixel for each pixel constituting the input image. Determining means for determining whether or not the pixel corresponds to the edge portion, and selecting a pixel disposed near a pixel having color information of a specific color as a correction target pixel, and the three-dimensional correction target pixel Correction means for correcting the color information in the color space so as to approximate the color information of the specific color, and after correcting the color information of the target pixel, in the three-dimensional color space of each pixel constituting the input image A three-dimensional histogram can be created based on the color information.

  The image processing method of the present invention includes a creation step of creating a three-dimensional histogram based on color information in a three-dimensional color space of each pixel constituting an input image, and the brightness of a color having a frequency equal to or higher than a threshold in the three-dimensional histogram. And calculating a background color range of the input image using the information.

  The program of the present invention is characterized in that each step of the image processing method of the present invention is executed on a computer. The program of the present invention can be installed or loaded on a computer through various recording media such as a CD-ROM, a magnetic disk, and a semiconductor memory.

  According to the image processing apparatus and the image processing method according to the present invention configured as described above, the color range of the background color of the input image is calculated from the three-dimensional histogram of the color space. Even when there are a plurality of color pixels having the same brightness, the background color can be correctly determined, and as a result, the background color can be accurately removed from the input image.

  In addition, the number of histograms for determining the background removal level can be reduced, and simple processing can be realized. In addition, the number of histograms for determining the background removal level can be reduced, and color / monochrome discrimination can be performed.

DESCRIPTION OF EXEMPLARY EMBODIMENTS Hereinafter, preferred embodiments for carrying out the invention will be described with reference to the drawings.
<First Embodiment>
FIG. 1 is a block diagram showing a schematic configuration of an image processing system 1 including an image processing apparatus 10 according to the first embodiment of the present invention.

  As shown in FIG. 1, the image processing system 1 includes an image processing device 10, a scanner device 20, and a printer device 30.

  The scanner device 20 is a device that reads an original and acquires input image data (hereinafter referred to as “input image”) as RGB (R (red), G (green), B (blue)) data. The configuration itself of the scanner device 20 is the same as that of the conventional scanner device, and thus detailed description thereof is omitted. For example, the scanner device 20 is composed of components such as a scanner light source, a lens, a scanning motor, and a CCD sensor. Scanning was performed while irradiating the light irradiated from the original to the original, and the reflected light was guided to a CCD sensor with R (red), G (green), and B (blue) filters, and the CCD sensor read the light. Lightness information for RGB is converted into a digital signal for each pixel of the reflected light of the document and output.

  The printer device 30 performs predetermined processing on the input image (RGB data) acquired by the scanner device 20 by the image processing device 10 and then uses the processed image data (R′G′B ′ data) as printing ink. Are converted to print data (CMYK signals: C (cyan), M (magenta), Y (yellow), K (black))) corresponding to the print data. Since the configuration of the printer device 30 is the same as that of a conventional printer device, detailed description thereof is omitted. For example, refer to a color conversion table in which combinations of color conversions stored in advance in a storage device such as an HDD are recorded. Then, the image data is converted into print data, and based on the print data, each of the CMYK inks is ejected and printed on a print medium such as plain paper.

  The image processing apparatus 10 determines whether the document read by the scanner device 20 is a color document or a monochrome document based on the input image (RGB data), and also the background color (background color) that is the background of the document. The image processing apparatus appropriately processes an input image (RGB data) so as to remove the image.

  As illustrated in FIG. 2, the image processing apparatus 10 includes a CPU (Central Processing Unit) 101 that performs various calculations, a RAM 102 that temporarily stores programs executed by the CPU 101 or image data, various data, Can communicate with ROM 103 for storing various programs in advance, external storage device 104 such as HDD, display unit 105 such as LCD for displaying screens, input unit 106 such as an operation panel having various key buttons, and external devices A component such as an interface 107 for connecting to the network is provided.

  As shown in FIG. 1, the image processing apparatus 10 functionally includes an input image acquisition unit 11, a three-dimensional histogram creation unit 12, a background color color range calculation unit 13, and a smoothing / edge enhancement processing unit 14. A color conversion / background color removal unit 15, a color / monochrome determination unit 16, and an image data output unit 17. Each of these units is realized mainly by the CPU 101 executing a program stored in the RAM 102 or the ROM 103 and controlling each hardware.

  The input image acquisition unit 11 acquires an input image (RGB data) acquired by the scanner device 20 reading a document. The timing for acquiring the input image can be, for example, the timing when the scanner device 20 reads the document and acquires the input image. In this case, every time the scanner device 20 acquires an input image, the scanner 20 transmits the input image to the input image acquisition unit 11. As a result, the input image acquisition unit 11 automatically acquires the input image (RGB data). can do.

  The three-dimensional histogram creation unit 12 functions as a creation unit that creates a three-dimensional histogram based on color information in the three-dimensional color space of each pixel constituting the input image. In the present embodiment, as color information in the three-dimensional color space of each pixel, an RGB value representing each RGB element color with a plurality of gradations (for example, 256 gradations from 0 to 255) is used. The RGB value of one pixel can be expressed as (255, 255, 0), for example. Specifically, the three-dimensional histogram creation unit 12 creates a three-dimensional histogram by plotting and counting the RGB values of each of the plurality of pixels constituting the input image in a three-dimensional color space with RGB as axes. To do. In the three-dimensional histogram, if the plot width on each axis of RGB is created in accordance with the gradation, the number of arrays of 256 × 256 × 256 is required on the program, and the memory usage increases. Therefore, in order to reduce the number of arrangements on the program, each axis of RGB may be divided and counted, for example, every 10 gradations. In this case, the three-dimensional histogram of each RGB value can be expressed, for example, as an array as shown in FIG. 3, and as described later, the RGB value of the array value whose frequency (count number) is equal to or greater than a threshold value is determined as the background color. can do.

  The background color color range calculation unit 13 functions as a calculation unit that calculates the color range of the background color of the input image using lightness information of a color having a frequency equal to or higher than the threshold in the three-dimensional histogram. That is, since the RGB values of the pixels constituting the background color are the same or approximate, an area where the frequency is equal to or greater than the threshold in the three-dimensional histogram can be determined as the background color. Then, the lightness (L1) corresponding to the RGB value of the area determined as the background color is obtained, and a pixel having a lightness equal to or higher than the lightness information is calculated as a background color range. The threshold is set according to the proportion of the background color in the input image, and can be set according to various conditions such as the type of the input image. Of these, the frequency of 50% can be set as the threshold value.

  The smoothing / edge enhancement processing unit 14 performs a smoothing process on the photographic image or the halftone dot image to prevent the occurrence of moire according to the characteristics of the input image. Functions as a smoothing / edge enhancement processing means for performing edge enhancement processing to form a clear edge. The smoothing / edge enhancement processing unit 14 performs, for example, averaging processing so that the RGB values are averaged based on nine surrounding pixels centered on a certain target pixel, or performs edge enhancement processing. Since this process itself is the same as the conventional method, detailed description thereof is omitted. Note that the smoothing / edge enhancement processing unit 14 may be omitted as necessary in the image processing apparatus 10 of the present embodiment.

  The color conversion / background color removal unit 15 is used as a color conversion means for converting RGB data into Lab data, Lab data into RGB data, and in order to remove the background color from the input image. It functions as a changing means (background color removing means) for changing the contained color to a predetermined color. Specifically, as shown in FIG. 4, a process of converting RGB data as an input image into Lab data, a process of removing background data from Lab data and changing it to L′ a′b ′ data, L′ a ′ A process of converting the b ′ data into R′G′B ′ data for output by the printer 30 is executed. The color conversion process itself is the same as the conventional method and will not be described in detail. For example, a color conversion table stored in advance in the external storage device 104 of the image processing apparatus 10 is read and the color conversion table is read out. Referring to, various data conversion processing is performed. The background color removal processing is performed by, for example, converting Lab data having a brightness equal to or higher than the brightness (L1) obtained by the background color color range calculation unit 13 to L ′ = 100 (maximum value) and a = b = 0 (achromatic color). For the lightness L less than L1, L′ a′b ′ data from which the background color has been removed can be obtained by changing L ′ = L × 100 / L1.

  The color / monochrome discriminating unit 16 functions as a discriminating unit that discriminates whether the input image is a color image or a monochrome image based on the frequency of chromatic colors included outside the color range of the background color in the three-dimensional histogram. To do. That is, when it is outside the color range of the background color calculated by the background color color range calculation unit 13 in the three-dimensional histogram and has a frequency equal to or more than a certain value outside the achromatic color range, it is determined as a color image or specified. It is possible to determine a color image when a chromatic color range of a color (for example, skin color) is determined in advance and is outside the background color range and has a certain frequency or more in the determined chromatic color range. it can. Note that the achromatic color range can be arbitrarily set according to the input image. For example, in the three-dimensional histogram, the achromatic color range can be set to a certain range (for example, each of the RGB values ± 10) from the axis R = G = B. it can.

  The image data output unit 17 functions as a data output unit that outputs image data (R′G′B ′ data) to be printed by the printer 30 to the printer 30. Specifically, the R′G′B ′ data converted by the color conversion / background color removal unit 15 and the determination result by the color / monochrome determination unit 16 are output.

  Hereinafter, an image processing method implemented using the image processing apparatus 10 will be described with reference to a flowchart shown in FIG. The following processing is mainly executed by the CPU 101. In addition, each process (including the partial process to which the code | symbol is not provided) can be arbitrarily changed in order within the range which does not produce contradiction in the processing content, or can be performed in parallel. The CPU 101 has various functions, but descriptions of functions not directly related to image processing are omitted.

  First, the input image acquisition unit 11 acquires an input image (RGB data) acquired by the scanner device 20 reading a document (step S100). The input image can be acquired every time the input image is sent from the scanner device 20 every time the scanner device 20 reads a document and acquires the input image, for example.

  Next, the three-dimensional histogram creation unit 12 creates a three-dimensional histogram based on the color information in the three-dimensional color space of each pixel constituting the input image (step S101). Specifically, a three-dimensional histogram is created by plotting and counting the RGB values of each of the plurality of pixels constituting the input image on a three-dimensional color space with RGB as axes.

  Next, the background color range calculation unit 13 calculates the color range of the background color of the input image using the brightness information of the color having a frequency equal to or higher than the threshold in the three-dimensional histogram (step S102). That is, an area having a frequency equal to or higher than a threshold in the three-dimensional histogram is determined as a background color, and a lightness (L1) corresponding to the RGB value of the area determined as the background color is obtained and has a lightness equal to or higher than the lightness information. Pixels are calculated as the background color range. The threshold is set according to the proportion of the background color in the input image, and can be set according to various conditions such as the type of the input image. Of these, the frequency of 50% can be set as the threshold value.

  Next, the smoothing / edge enhancement processing unit 14 performs a smoothing process on the photographic image and the halftone dot image to prevent the occurrence of moire according to the characteristics of the input image. On the other hand, edge enhancement processing is performed to form a clear edge (step S103). In the present embodiment, one of these processes may be omitted, or both processes may be omitted.

  Next, the color conversion / background color removal unit 15 converts the RGB data as the input image into Lab data (step S104). Note that the conversion from RGB data to Lab data is performed by converting various data based on the color conversion table, as in the conventional color conversion process.

  Next, the color conversion / background color removal unit 15 removes the background color of the Lab data and changes the data to L′ a′b ′ data (step S105). Specifically, for example, Lab data having a brightness equal to or higher than the brightness (L1) obtained by the background color range calculator 13 is set to L ′ = 100 (maximum value), a = b = 0 (achromatic color), and L1 By changing L ′ = L × 100 / L1 for the lightness L below, L′ a′b ′ data from which the background color has been removed can be obtained.

  Next, the color conversion / background color removal unit 15 converts the L′ a′b ′ data into R′G′B ′ data for output by the printer 30 (step S106). In this color conversion process, various data conversion processes are performed based on the color conversion table, as in the conventional color conversion process.

  Here, after the process of step S102, separately from the processes of steps S103 to S106, the color / monochrome determination unit 16 performs the chromatic color frequency included outside the color range of the background color in the three-dimensional histogram. It is determined whether the input image is a color image or a monochrome image (step S107). In the three-dimensional histogram, it is determined that the image is a color image when it is outside the background color range calculated by the background color range calculation unit 13 and has a certain frequency other than the achromatic color range, or a specific color A chromatic color range (for example, skin color) is determined in advance, and can be determined as a color image when it is outside the background color range and the determined chromatic color range has a certain frequency or more.

  Next, after the processing of step S106 and step S107, the image data output unit 17 outputs image data (R′G′B ′ data) to be printed by the printer 30 to the printer 30 (step S108). . Specifically, the R′G′B ′ data converted by the color conversion / background color removal unit 15 and the determination result by the color / monochrome determination unit 16 are output.

  As described above, according to the image processing apparatus and the image processing method of the present embodiment, since the color range of the background color of the input image is calculated from the three-dimensional histogram of the color space, the same brightness as the non-background of the input image Even when there are pixels of a plurality of colors having the background color, the background color can be correctly determined.

  In addition, it is possible to remove the background color from the input image by creating only one type of three-dimensional histogram, and to determine whether the input image is a color image or a monochrome image. And memory usage can be reduced.

Furthermore, even if the background color of the input image is a color, the input image can be determined monochrome regardless of the background color by performing color / monochrome determination after removing the background color.
<Second Embodiment>
FIG. 5 is a block diagram showing a schematic configuration of an image processing system 1 ′ including the image processing apparatus 10 ′ according to the second embodiment of the present invention.

  The image processing apparatus 10 ′ according to the second embodiment is different from the image processing apparatus 10 according to the first embodiment in a method of creating a three-dimensional histogram, and among the pixels constituting the input image, three pixels satisfying a specific condition are included. It is characterized in that a histogram is created after correcting color information in a dimensional color space.

  As shown in FIG. 5, the image processing apparatus 10 ′ of the second embodiment is the same component as that of the first embodiment except for the three-dimensional histogram creation means 12 ′.

  The three-dimensional histogram creation unit 12 ′ includes a selection unit 121 and a correction unit 122.

  The selection unit 121 determines whether each pixel constituting the input image is a pixel corresponding to an edge portion in the input image based on peripheral pixel information of the pixel, and corresponds to the edge portion. It functions as a selection unit that selects a pixel that is determined as a pixel and that is arranged near a pixel having color information of a specific color as a correction target pixel. Note that the processing for detecting the pixel corresponding to the edge portion is the same as the conventional edge detection processing in which an edge portion having a certain edge strength or more is detected as the edge portion based on peripheral pixel information for the target pixel. Detailed explanation is omitted. Whether or not a pixel has color information of a specific color can be determined by, for example, setting color information of a specific color in advance and comparing it with its RGB value. Therefore, the selection unit 121 can select a pixel corresponding to the edge portion and disposed near a pixel having color information of a specific color as a correction target pixel. In the present embodiment, the specific color can be an achromatic color such as black, for example.

  The correction unit 122 corrects the color information of the correction target pixel in the three-dimensional color space so as to approach an achromatic color, and functions as a correction unit. That is, correction is performed so as to approach the R = G = B axis (achromatic color axis) in the three-dimensional histogram. For example, in the color space, a perpendicular line is formed from the RGB value point of the correction target pixel to the achromatic color axis. Move it down and move it along the perpendicular. For example, the boundary pixel of a character area of a specific color may approach the background color due to the influence of the background area when read by a scanner. In this embodiment, even in such a case, the boundary pixel that approaches the background color can be returned to the original specific color by the correction unit 122.

  Then, the three-dimensional histogram creating unit 12 ′ corrects the color information of the correction target pixel, and then creates a three-dimensional histogram based on the color information in the three-dimensional color space of each pixel constituting the input image.

  Hereinafter, an image processing method implemented using the image processing apparatus 10 ′ will be described with reference to a flowchart shown in FIG. The following processing is mainly executed by the CPU 101. In addition, each process (including the partial process to which the code | symbol is not provided) can be arbitrarily changed in order within the range which does not produce contradiction in the processing content, or can be performed in parallel.

  First, as in step S101, the input image acquisition unit 11 acquires an input image (RGB data) acquired by the scanner device 20 reading a document (step S200).

  Next, the three-dimensional histogram creation unit 12 ′ determines, for each pixel constituting the input image, whether or not it is a pixel corresponding to an edge portion in the input image based on peripheral pixel information of the pixel, A pixel that is determined to be a pixel corresponding to the edge portion and that is disposed near a pixel having color information of a specific color is selected as a correction target pixel (step S201). Note that the processing for detecting the pixel corresponding to the edge portion is the same as the conventional edge detection processing in which an edge portion having a certain edge strength or more is detected as the edge portion based on peripheral pixel information for the target pixel. Detailed explanation is omitted. Whether or not a pixel has color information of a specific color can be determined by, for example, setting color information of a specific color in advance and comparing it with its RGB value. In the present embodiment, the specific color can be an achromatic color such as black, for example.

  Next, the three-dimensional histogram creation unit 12 ′ corrects the correction target pixel so as to approach the color range of the specific color in the three-dimensional color space (step S202). In the three-dimensional histogram, correction is performed so as to approach the axis of R = G = B (achromatic color axis). For example, in the color space, a perpendicular line is dropped from the point of the RGB value of the correction target pixel to the achromatic color axis, Move along the perpendicular to the axis. As a specific example, if the RGB value of a certain correction target pixel is (150, 130, 150), the RGB value of that pixel is corrected to (150, 150, 150).

  Next, the three-dimensional histogram creating unit 12 ′ corrects the color information of the correction target pixel, and then creates a three-dimensional histogram based on the color information in the three-dimensional color space of each pixel constituting the input image (step) S203).

  Next, similarly to the processes in steps S102 to S108 in the first embodiment, the processes in steps S204 to S209 are performed. In addition, since the process of step S204-S210 can be made to be the same as the process of step S102-S107, detailed description is abbreviate | omitted here.

According to the image processing apparatus 10 ′ of the present embodiment, the background color can be accurately extracted from the input image. That is, it should be determined as an achromatic color originally, but it is possible to relieve a chromatic color drawn by a specific color such as an edge, so that the determination accuracy can be improved.
<Modification>
The preferred embodiments of the present invention have been described above. However, the present invention should not be limited to the above embodiments, and does not depart from the spirit and scope expressed in the claims. Various modifications, additions, and omissions can be made by those skilled in the art.

  For example, in the above embodiment, whether the input image is a color image or a monochrome image is performed together with the process of removing the background color. However, the present invention is not limited to this. For example, only the process of removing the background color is performed. Of course, you may.

  In the above-described embodiment, the case has been described in which image data (RGB data) obtained by reading a document from the scanner device 20 is subjected to image processing. However, the present invention is not limited to this. For example, the image processing device 20 is connected to the image processing device 20 via a communication network. Image data can also be appropriately processed from a connected computer.

  Furthermore, in the above-described embodiment, the image processing apparatus 10, the scanner apparatus 20, and the printer apparatus 30 are described separately. However, the present invention is not limited to this. For example, the image processing apparatus is included in the scanner apparatus 20 or the printer apparatus 30. Ten functions may be provided. In this case, the control unit of the scanner device or the printer device can realize each function of the image processing apparatus 10. Furthermore, it is a matter of course that the functions of the image processing apparatus 10, the scanner apparatus 20, and the printer apparatus 30 can be realized by an MFP housed in a single casing. In this case, the control unit of the MFP performs the image processing apparatus. Each of the ten functions is realized.

  Furthermore, in the above-described embodiment and the like, a three-dimensional histogram is created based on RGB data that is an input image. However, the present invention is not limited to this, and a three-dimensional histogram can be created based on Lab data. However, since the accuracy of the histogram is affected by the conversion table for converting RGB data to Lab data, it is desirable to create a three-dimensional histogram with RGB data.

1 is a schematic diagram illustrating an image processing system 1 including an image processing apparatus 10 according to a first embodiment. It is the schematic which shows the hardware constitutions of the image processing apparatus 10 of 1st Embodiment. It is a figure which shows the example of the three-dimensional histogram produced in the image processing apparatus 10 of 1st Embodiment. It is a figure showing the flow of the process of color conversion and background color removal in the image processing apparatus 10 of 1st Embodiment. It is a flowchart which shows the processing content of the image processing apparatus 10 of 1st Embodiment. It is the schematic which shows image processing system 1 'containing image processing apparatus 10' of 2nd Embodiment. It is a flowchart which shows the processing content of image processing apparatus 10 'of 2nd Embodiment.

Explanation of symbols

1 image processing system,
10 image processing apparatus,
11 Input image acquisition unit,
12 3D histogram generator,
13 background color color range calculation unit,
14 Smoothing / edge enhancement processing unit,
15 color conversion / background color removal unit,
16 color / monochrome discriminator,
17 Image data output unit,
20 Scanner device,
30 Printer device.

Claims (8)

Creating means for creating a three-dimensional histogram based on color information in a three-dimensional color space of each pixel constituting the input image;
Calculating means for calculating a color range of a background color of the input image using lightness information of a color having a frequency equal to or higher than a threshold in the three-dimensional histogram;
An image processing apparatus comprising:   Further, the image processing apparatus further includes a determination unit configured to determine whether the input image is a color image or a monochrome image based on a frequency of a chromatic color included outside the color range of the background color in the three-dimensional histogram. The image processing apparatus according to claim 1.   The calculation means determines a color having the highest frequency in the three-dimensional histogram, determines a lightness corresponding to the color, and determines a color range having a lightness equal to or higher than the calculated lightness as a color range of the background color. The image processing apparatus according to claim 1, wherein the image processing apparatus is an image processing apparatus.   Furthermore, it has a change means which changes the color contained in the color range of the said background color into a predetermined color about each pixel which comprises the said input image, It is any one of Claims 1-3 characterized by the above-mentioned. Image processing apparatus.   The image processing apparatus according to claim 2, wherein the determination unit determines that the input image is a monochrome image when the frequency of a specific chromatic color is equal to or less than a predetermined value. The creating means includes
It is determined whether each pixel constituting the input image is a pixel corresponding to an edge portion in the input image based on peripheral pixel information of the pixel, and is determined to be a pixel corresponding to the edge portion Selection means for selecting, as a correction target pixel, a pixel arranged near a pixel having color information of a specific color;
Correcting means for correcting the color information in the three-dimensional color space of the correction target pixel so as to approach the color information of the specific color;
6. The three-dimensional histogram is created based on color information in a three-dimensional color space of each pixel constituting the input image after correcting the color information of the correction target pixel. Image processing device. Creating a three-dimensional histogram based on color information in the three-dimensional color space of each pixel constituting the input image;
A calculation step of calculating a color range of a background color of the input image using lightness information of a color having a frequency equal to or higher than a threshold in the three-dimensional histogram;
An image processing method comprising:   A program for causing a computer to execute the image processing method according to claim 7.

Images