JP2009065378A - Base region detecting method, image processor, image forming apparatus, computer program, and recording medium - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide a base region detecting method capable of detecting and eliminating a base region from image data with high accuracy, an image processor, an image forming apparatus, a computer program and a recording medium. <P>SOLUTION: A region separation processing part 24 of the image processor 20 detects edges of image data input from an image input device 11. A base detection processing part 25 has a plurality of counters for creating histogram, switches the counters in accordance with an edge detection result in each prescribed region of the image data to count the number of pixels in each density value, extracts a base density candidate value at which a count value becomes a maximum in each prescribed region, determines the existence/absence of a base region and a base density value compared with a threshold, and extracts a base region from the image data in accordance with whether pixels of the base density value continue. A base region elimination processing part 26 eliminates the base region from the image data in accordance with a detection result from the base region detection processing part 25. <P>COPYRIGHT: (C)2009,JPO&INPIT

Description

  The present invention relates to a background area detection method that detects a background area from an input image, an image processing apparatus that performs background area detection processing using this method, and image formation that forms an image based on the detection result of the background area The present invention relates to an apparatus, a computer program for detecting a ground area, and a recording medium on which the computer program is recorded.

  2. Description of the Related Art Conventionally, an image forming apparatus that forms an image by an electrophotographic method or an inkjet method has been widely used. With the development of image processing technology, image forming apparatuses can reproduce color images with high image quality, and in recent years, full-color digital copiers and multifunction machines have been commercialized. In these image forming apparatuses, various kinds of originals are copied, and in order to reproduce an image of the original with higher image quality, it is necessary to perform optimum image processing according to the type of the original.

  For example, some originals have a background color. Color copying requires more time for image formation than a black and white copy, and consumes a large amount of toner or ink necessary for image formation. For this reason, when an original having a background color is copied in color, if it is not necessary to reproduce the background, it is desirable in terms of time and cost to perform image formation by removing the background. Further, when a color original having a background color is copied in black and white, the visibility of characters or images on the copy can be improved by removing the background. However, since there are a wide variety of background patterns on a document, it is not easy to automatically and accurately remove the background.

  In Patent Document 1, a histogram of the read image data is created, the maximum density value and the minimum density value are obtained from this histogram, and the temporary background density is detected from the maximum density value and the density of the histogram frequency maximum value. There has been proposed a background density detection method for a read image in which the background density is detected from the provisional background density and the minimum density value. In this background density detection method, for example, the background density is detected according to the density histogram of the read image as compared to the case where the background is uniformly determined from the density value by comparison with a threshold value. The background density can be detected, and the background can be accurately removed.

  In Patent Document 2, a histogram of density values and frequencies of image data is generated, a maximum frequency and a density value having this frequency are detected from the generated histogram, and a density range for performing background removal is determined from the detected values. In addition, by removing the background depending on whether or not each density value of the image data is within this density range, it is possible to save toner without copying a portion such as a color background of a document in a copying machine or the like. In addition, there has been proposed a background removal device that can improve the visibility of characters on a copied document. In addition, this background removal device removes uneven background and gradation background by the user instructing the density area to be inspected and the ratio of determining the frequency removal level with respect to the maximum frequency from the operation unit. can do.

In Patent Document 3, there is provided a binarization processing apparatus capable of performing binarization accurately even when the brightness of an input image is not uniform and when the background density changes depending on the location. Proposed. This binarization processing device blocks an input image for each predetermined region, extracts an edge region, calculates a density histogram of pixels in the edge region from the extraction result, and calculates a binarization threshold value for each block. Also, the binarization processing device extracts a background area for each block, and calculates binarization threshold value interpolation data based on the average value of the pixel density values of the background area and the binarization threshold value. Based on the binarization threshold value and the binarization threshold interpolation data, the binarization processing apparatus binarizes the block including the graphic area with the binarization threshold value, and binarizes the block including the background area. Binarization is performed using threshold interpolation data.
JP-A-1-196971 Japanese Patent Laid-Open No. 3-44268 JP 2005-165925 A

  However, in the background density detection method described in Patent Document 1, a histogram is created for the entire read image data, and the threshold value of the density value to be removed as the background is calculated from the histogram. When a histogram is created for the entire image data obtained by reading a document including a document, a portion that is not a background region may be determined as a background and removed.

  The background removal apparatus described in Patent Document 2 is also configured to determine a density range for background removal from a histogram generated from the entire image data, and similarly, a portion that is not a background area may be determined as a background and removed. There is. In this background removal apparatus, since the user can instruct from the operation unit the density region to be inspected and the ratio for determining the frequency removal level with respect to the maximum frequency, erroneous removal can be prevented by the user instruction. . However, when the number of pages of the document is large, there is a problem that the user's operation is complicated and inconvenient.

  In the binarization processing apparatus described in Patent Document 3, the input image is divided into blocks for each predetermined area, and the background area is extracted for each block and binarization is performed. Can be binarized suitable for each block. However, this binarization processing apparatus is configured to count the number of edges for each line in the horizontal direction or vertical direction of the input image, and extract a background region depending on whether the number of edges exceeds a threshold value. It does not remove the underlying region. In addition, since processing is performed for each block having a small amount of information, processing accuracy such as background region extraction determination and threshold calculation may be low.

  The present invention has been made in view of such circumstances, and an object of the present invention is to detect an edge for each of a plurality of predetermined areas of input image data, and to detect a plurality of edges according to the result of edge detection. A background density candidate value for each predetermined area is extracted, and a background removal process based on an accurate background density is performed by obtaining a representative background density candidate value from a plurality of extracted background density candidate values. An object of the present invention is to provide a background area detection method, an image processing apparatus, an image forming apparatus, a computer program, and a recording medium.

  Furthermore, a background area detection method, an image processing apparatus, an image forming apparatus, and a computer program that can detect a background area more accurately by determining the presence or absence of a background area from the continuity of pixels having representative background density candidate values And providing a recording medium.

  A background area detection method according to the present invention is a background area detection method for detecting a background area included in input image data, wherein an edge is detected from input image data, and a plurality of predetermined areas in the image data are detected. In addition, for the pixels included in the detected edge, the number of pixels is counted for each density value, and for each pixel not included in the edge, the number of pixels is counted for each density value. In addition, a background density candidate value is extracted based on both count results, and a representative background density candidate value is extracted from a plurality of background density candidate values calculated for each predetermined area based on the number of pixels of each background density candidate value. , Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number, determining whether the representative background density candidate value exceeds a predetermined density value, and based on both determination results, the image The data contains a ground area And judging whether or not Luke.

  The background area detection method according to the present invention is a background area detection method for detecting a background area included in input image data, wherein an edge is detected from the input image data, and a plurality of predetermined areas in the image data are detected. For each region, for pixels not included in the detected edge, the number of pixels is counted for each density value, and for each predetermined region, a background density candidate value is extracted based on the count result, and calculated for each predetermined region. A representative background density candidate value is extracted from a plurality of background density candidate values based on the number of pixels of each background density candidate value, and it is determined whether or not the number of pixels of the representative background density candidate value exceeds a predetermined number, It is determined whether or not a representative background density candidate value exceeds a predetermined density value, and based on both determination results, it is determined whether or not a background area is included in the image data.

  Further, the background area detection method according to the present invention uses a plurality of counting means for counting the number of pixels for each density value in the background area detection method for detecting the background area included in the input image data, and the input image Edges are detected from the data, and for each of a plurality of predetermined areas in the image data, the counting means is switched according to the detection result of the edges, and the number of pixels is counted for each density value. A background density candidate value is extracted based on the counting result of the counting means, and a representative background density candidate value is extracted from a plurality of background density candidate values calculated for each predetermined area based on the number of pixels of each background density candidate value. , Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number, determining whether the representative background density candidate value exceeds a predetermined density value, and based on both determination results, the image Does the data contain a background area? Or wherein the determining.

  Further, in the background region detection method according to the present invention, the extraction of the background density candidate value is performed by extracting a density value corresponding to the largest number of pixels from the count result, and the extraction of the representative background density candidate value is This is performed by extracting a background density candidate value having the largest number of pixels from a plurality of background density candidate values extracted for each predetermined region.

  In the ground area detection method according to the present invention, when the image data is composed of a plurality of pixels arranged in parallel in the vertical and horizontal directions, the predetermined area is one or a plurality of the vertical or horizontal of the image data. It is an area composed of columns.

  Further, the background region detection method according to the present invention determines continuity in the image data for a plurality of pixels having the representative background density candidate value, and when a predetermined number or more of the pixels are continuous, It is determined that a background area is included in the image data.

  Also, the background area detection method according to the present invention is characterized in that the background area included in the image data is removed.

  Further, an image processing apparatus according to the present invention is an image processing apparatus that detects a background region included in input image data, an edge detection unit that detects an edge from the input image data, and a plurality of the image data in the image data. Counting means for counting the number of pixels for each density value for pixels included in the detected edge for each predetermined area, and the number of pixels for each density value for pixels not included in the edge for each predetermined area. A counting means for counting, a background density candidate value extracting means for extracting a background density candidate value based on the counting results of both counting means for each predetermined area, and a plurality of background density candidate values extracted for each predetermined area Representative background density candidate value extracting means for extracting a representative background density candidate value based on the number of pixels of each background density candidate value, and a pixel for determining whether or not the number of pixels of the representative background density candidate value exceeds a predetermined number Based on the determination results of the determination means, the density value determination means for determining whether or not the representative background density candidate value exceeds a predetermined density value, and the pixel number determination means and the density value determination means, And a background determination means for determining whether or not a background area is included.

  Further, an image processing apparatus according to the present invention is an image processing apparatus that detects a background region included in input image data, an edge detection unit that detects an edge from the input image data, and a plurality of the image data in the image data. For each pixel that is not included in the detected edge, a counting unit that counts the number of pixels for each density value, and for each predetermined region, a background density candidate value is extracted based on the counting result of the counting unit. And a background density candidate value extraction means for extracting a background density candidate value from the plurality of background density candidate values extracted for each predetermined area based on the number of pixels of each background density candidate value. And a pixel number determining means for determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number, and a density value determining means for determining whether the representative background density candidate value exceeds a predetermined density value When Based on the determination result of the pixel number determination means and the density value determination means, characterized in that it comprises a base determination means for determining whether contains background region in the image data.

  In addition, an image forming apparatus according to the present invention outputs the above-described image processing apparatus, an input unit that inputs image data to the image processing apparatus, and an image related to the image data image-processed by the image processing apparatus. Output means.

  The computer program according to the present invention is a computer program for causing a computer to detect a background area included in image data, causing the computer to detect an edge from the image data, and for each of a plurality of predetermined areas in the image data. For each pixel included in the detected edge, the number of pixels is counted for each density value, and for each predetermined area, for each pixel not included in the edge, the number of pixels is counted for each density value. The background density candidate value is extracted based on both count results, and the representative background density candidate value is extracted based on the number of pixels of each background density candidate value from the plurality of background density candidate values extracted for each predetermined region, Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number; determining whether the representative background density candidate value exceeds a predetermined density value; Based on the constant results, characterized in that to determine if it contains a background region in the image data.

  The computer program according to the present invention is a computer program for causing a computer to detect a background area included in image data, causing the computer to detect an edge from the image data, and for each of a plurality of predetermined areas in the image data. For each pixel not included in the detected edge, the number of pixels is counted for each density value, and for each predetermined area, a background density candidate value is extracted based on the count result, and a plurality of backgrounds extracted for each predetermined area The representative background density candidate value is extracted from the density candidate value based on the number of pixels of each background density candidate value, and it is determined whether or not the number of pixels of the representative background density candidate value exceeds a predetermined number. Determining whether or not the candidate value exceeds a predetermined density value, and determining whether or not a background area is included in the image data based on both determination results To.

  A recording medium according to the present invention is recorded with the computer program described above.

  In the present invention, the edge is detected from the input image data, and the number of pixels for each density value is counted by a counter or the like for each of a plurality of predetermined regions of the image data and included in the edge. The number of pixels for each density value is counted by a counter or the like for pixels that are not. That is, a histogram of density values is created for each of the edge component and the other components. Although there are few edge components included in the background area, there are many edge components included in the character area and the image area, etc., so by generating a histogram by switching the counter according to the edge detection result, The histograms of other regions can be separated. Accordingly, it is easy to estimate the density value of the background or calculate the threshold value for separating the background area from other areas, and it is possible to accurately perform the calculation.

  In the present invention, an edge is detected from input image data, and the number of pixels for each density value is counted by a counter or the like for each of a plurality of predetermined areas of the image data, It is also possible to create a histogram of density values for only components other than the edges and detect the background area. In the case of this method, there is a possibility that the detection accuracy may be slightly reduced as compared with the above-described method in which the background region is detected in consideration of the pixels included in the edge (for example, for pixels in the character region sandwiched between edges) Since the density value of this pixel cannot be determined to be the density value of the character, if there are many characters, the density value of the character may be erroneously determined as the density value of the background). It is possible to do.

  In the present invention, for example, a plurality of counters are used as counting means for counting the number of pixels for each density value. The image data is processed for each pixel sequentially in the horizontal direction or the vertical direction. Edges are detected from the input image data at this time, and for example, rising edges are detected for each of a plurality of predetermined areas of the image data. Alternatively, a plurality of histograms are created by performing counting while switching the counter according to the fall or the like. Since the background region and the character region or the image region in the document are switched at the edge, the histogram can be created separately for each region. Accordingly, it is easy to estimate the density value of the background or calculate the threshold value for separating the background area from other areas, and it is possible to accurately perform the calculation.

  A background density candidate value in each predetermined region is extracted from the plurality of histograms thus created, and a representative background density candidate value is further extracted from the extracted plurality of background density candidate values. In the present invention, for example, a density value having the largest number of pixels is extracted from a plurality of counting results, that is, a plurality of histograms, and set as background density candidate values in each predetermined region. Further, a background density candidate value having the largest number of pixels is extracted from a plurality of background density candidate values extracted for a plurality of predetermined areas, and set as a representative background density candidate value. This representative background density candidate value is an estimated value of the background density value of the entire document. When the number of representative background density candidate values counted exceeds a predetermined number and the representative background density candidate value exceeds a predetermined density value, the representative background density candidate value is a density value that exists uniformly in the entire image data. Therefore, it can be determined that the background area is included in the image data using the representative background density candidate value as the background density value.

  In the present invention, when the image data is composed of a plurality of pixels arranged side by side in the vertical and horizontal directions, the predetermined area for counting the number of pixels and creating a histogram is set as one or a plurality of vertical or horizontal of the image data. It is assumed that a region composed of columns, that is, one or more lines of image data. Processing for separating image data into predetermined areas is easy. By detecting the background density candidate value for each predetermined area and further extracting the representative background density candidate value, it is detected whether or not the background density pixels exist uniformly in the entire image data. Therefore, it is difficult for erroneous detection to occur when the density is biased to a part of the image data.

  In the present invention, whether or not pixels having representative background density candidate values are continuously present in the image data, and the number of pixels when they are consecutive, are determined as continuity. When pixels having representative background density candidate values continue, it is highly possible that the area is a background area, and it can be determined that the background area is included in the image data.

  In the present invention, pixels having representative background density candidate values and having continuity are removed as a background area. Since the background area can be determined with high accuracy as described above, it is possible to accurately remove only the background area without degrading the image quality of the entire document.

  In the present invention, the detection and removal of the base region by the above-described method is performed by an image processing apparatus, an image forming apparatus, or the like. Thereby, the image processing result by the image processing apparatus and the image quality of the image formed by the image forming apparatus are improved. In addition, the detection and removal of the background area by the above-described method is performed by a computer program. Thereby, it becomes possible to detect and remove the base region with high accuracy by a general-purpose computer, and versatility is enhanced. In addition, by recording this computer program on a recording medium, a large number of computers can be easily detected and removed.

  According to the present invention, a plurality of histograms are created for each predetermined area of the image data according to the result of edge detection, a background density candidate value for each predetermined area is extracted, and the representative background density is extracted from the plurality of background density candidate values. By extracting the candidate value and determining the background area when the representative background density candidate value and the number of pixels exceed a predetermined threshold, the background area can be detected with high accuracy. Furthermore, detection accuracy can be further improved by detecting the background region by examining the continuity of pixels having representative background density candidate values. Therefore, it is possible to perform processing such as removal of the background area with high accuracy from the image data of the document, and to improve the image quality of the processed image data.

  Hereinafter, the present invention will be specifically described with reference to the drawings showing embodiments thereof. FIG. 1 is a block diagram showing a configuration of an image forming apparatus according to the present invention. In the figure, reference numeral 1 denotes a central processing unit (CPU) that controls each part of the image forming apparatus and performs various calculations. The CPU 1 includes a ROM (Read Only Memory) 2, a RAM (Random Access Memory) 3, an operation unit 4, a display unit 5, a memory mounting unit 6, an image input device 11, an image output device 12, an image processing device 20, and the like. Are connected to each other, and these controls are performed. The image forming apparatus shown in this figure is a so-called digital color copying machine.

  The ROM 2 is configured by a non-volatile memory element such as a mask ROM, an EEPROM (Electrically Erasable Programmable ROM) or a flash memory, and stores a program executed by the CPU 1 and data necessary for the execution in advance. After the image forming apparatus is turned on, the CPU 1 reads the program from the ROM 2 and executes it to start the processing. The RAM 3 is composed of a large-capacity memory element capable of rewriting data by SRAM (Static RAM), DRAM (Dynamic RAM), flash memory, or the like, and is set by the user and data generated when the CPU 1 performs arithmetic processing. Various setting values and the like are stored.

  The operation unit 4 includes a function key, a start key, a numeric keypad, a power key, and the like, and can accept operations such as a copy start command or a copy setting input from the user. The operation unit 4 is configured to give the received user operation to the CPU 1. The display unit 5 includes a liquid crystal display, and displays an operation state of the image forming apparatus, a warning message to the user, various menus for assisting the user's operation, and the like on the liquid crystal display based on a display command from the CPU 1. It is. Note that the operation unit 4 and the display unit 5 may be a touch panel configured integrally with each other.

  The memory mounting unit 6 is a so-called memory card slot, and is configured so that a memory card 100 such as an SD memory card or a memory stick can be mounted detachably. When the memory card 100 is loaded in the memory loading unit 6, the CPU 1 can read data stored in the memory card 100 and write data to the memory card 100. When the program code 101 is stored in the memory card 100, the CPU 1 reads the program code 101 from the memory card 100 and stores it in the RAM 3, and executes the program code 101 to perform processing related to the program code 101. So that you can do it. If the ROM 2 is composed of a rewritable memory element, the program code 101 read from the memory card 100 may be stored in the ROM 2.

  The image input device 11 includes a light source that irradiates light on a document, and a scanner that includes a light receiving unit in which image sensors such as a CCD (Charge Coupled Device) are arranged in parallel. Based on the control of the CPU 1, the image input device 11 irradiates the original with light from the light source and moves the light receiving unit in one direction so that reflected light from the original is R (red) G (green) B (blue). ) Are separated into three color components, read by the light receiving unit, and supplied to the image processing apparatus 20 as RGB analog signals.

  The image processing apparatus 20 includes an A / D conversion unit 21, a shading correction unit 22, an input tone correction unit 23, a region separation processing unit 24, a background detection processing unit 25, a background removal processing unit 26, a spatial filter processing unit 27, A double processing unit 28, a color correction unit 29, a black generation and under color removal unit 30, an output gradation correction unit 31, a gradation reproduction processing unit 32, and the like are provided. The A / D converter 21 converts an RGB analog signal given from the image input device 11 into, for example, an 8-bit digital signal, that is, RGB image data. The converted RGB image data is a shading correction unit. 22 is given.

  The shading correction unit 22 acquires in advance various distortions that occur in the illumination system, imaging system, imaging system, and the like of the image input device 11 from the RGB image data provided from the A / D conversion unit 21. A shading process is performed according to certain information, and the RGB image data subjected to the shading process is provided to the input tone correction unit 23. The input tone correction unit 23 performs processing such as color balance adjustment and contrast adjustment on the RGB image data from which distortion has been removed by the shading correction unit 22, and the processed RGB image data is processed. The region separation processing unit 24 is provided.

  The region separation processing unit 24 determines whether each pixel in the RGB image data given from the input tone correction unit 23 belongs to a character region, a halftone region, a photographic region, or the like, and separates each pixel. I have to do it. The region separation processing unit 24 obtains information indicating which region each pixel belongs to as a processing result (region separation result), a background detection processing unit 25, a spatial filter processing unit 27, a black generation and under color removal unit 30, and In addition to being provided to the gradation reproduction processing unit 32, the RGB image data provided from the input gradation processing unit 23 is provided to the background detection processing unit 25 as it is. In addition, when the character region is separated, the region separation processing unit 24 performs image data edge detection processing and performs separation based on the edge detection result. Note that edge detection of image data can be performed, for example, by performing image processing using a Sobel filter.

  The background detection processing unit 25 detects a background region included in the RGB image data given from the region separation processing unit 24. As will be described in detail later, the background detection processing unit 25 determines whether or not the background area is included in the given RGB image data, and if the background area is included, information on this area is detected. As a result, the image data is output to the background removal processing unit 26, and the given RGB image data is output to the background removal processing unit 26.

  When the background area is detected by the background detection processing unit 25, the RGB image data and the background detection result are input to the background removal processing unit 26 in synchronization. The background removal processing unit 26 performs background removal processing based on the background detection result for the given RGB image data, and outputs the RGB image data from which the background is removed to the spatial filter processing unit 27. is there.

  The spatial filter processing unit 27 performs a spatial filter process using a digital filter on the RGB image data whose background is removed by the background removal processing unit 26 based on the result of the region separation given from the region separation processing unit 24. It is. As a result, the spatial frequency characteristics of the image are corrected, and it is possible to prevent the image output from the image output device 12 from being blurred or deteriorated in graininess. For example, in the region separated into the character region by the region separation processing unit 24, the spatial filter processing unit 27 performs a sharp emphasis filter process for the purpose of improving the reproducibility of the black character or the color character in particular. To emphasize. Further, for example, the spatial filter processing unit 27 performs low-pass filter processing on the region separated into halftone dot regions by the region separation processing unit 24 to remove the input halftone component. The RGB image data subjected to the spatial filter processing in this way is given from the spatial filter processing unit 27 to the scaling processing unit 28.

  In the image forming apparatus, the user can set enlargement / reduction of an image to be formed by operating the operation unit 4. The scaling processing unit 28 performs an enlargement calculation process or a reduction calculation process on the RGB image data subjected to the spatial filter process so as to have a predetermined magnification set by the user. RGB image data is output to the color correction unit 29.

  The color correction unit 29 converts the RGB image data given from the scaling processing unit 28 into image data in a color space of C (cyan), M (magenta), and Y (yellow), and at the image output device 12. In order to achieve faithful color reproduction, color correction processing is performed on each color component of CMY. Specifically, the color correction processing is processing for removing color turbidity based on spectral characteristics of CMY toners or inks including unnecessary absorption components from the CMY color components. The color correction unit 29 provides the converted CMY image data to the black generation and under color removal unit 30.

  The black generation and under color removal unit 30 calculates a color component of K (black) based on the region separation result given from the region separation processing unit 24 and each color component of the CMY image data given from the color correction unit 29. A black generation process to be generated is performed, and a process of generating a new CMY signal by subtracting the K component generated by the black generation process from each color component of the original CMY is performed. As a result, the CMY image data provided from the color correction unit 29 is converted into image data having four color components of CMYK.

For example, when performing black generation processing using skeleton black, the input / output characteristics of the skeleton curve are set to y = f (x), the input data are C, M, and Y, and the output data are C ′ and M ′. , Y ′ and K ′, and the UCR (Under Color Removal) rate is α (0 <α <1), the black generation and under color removal processing is expressed by the following equation. The CMYK image data converted by the black generation / undercolor removal process of the black generation / undercolor removal unit 30 is subjected to the correction process by the output gradation correction unit 31 and is then supplied to the gradation reproduction processing unit 32. It is.
K ′ = f {min (C, M, Y)}
C ′ = C−αK ′
M ′ = M−αK ′
Y ′ = Y−αK ′

  The gradation reproduction processing unit 32 performs gradation reproduction processing on the CMYK image data provided from the output gradation correction unit 31 according to the region separation result provided from the region separation processing unit 24. is there. The gradation reproduction process is a process for classifying image data into a plurality of pixels so that a halftone can be reproduced, and a binary or multi-value dither method or an error diffusion method can be used. For example, in the region separated into character regions by the region separation processing unit 24, the tone reproduction processing unit 32 performs high frequency component of the image output device 12 for the purpose of improving the reproducibility of black characters or color characters. A binarization process or a multi-level process suitable for reproducing the image is performed. Further, for example, in an area separated into halftone dot areas by the area separation processing unit 24, the output tone correction unit 31 converts the density of the image data into a halftone dot area ratio that is a characteristic value of the image output device 12. A gradation correction process is performed, and an intermediate gradation process is performed so that the gradation reproduction processing unit 32 can separate image data into pixels and reproduce each gradation. In addition, for example, the gradation reproduction processing unit 32 performs binarization processing or multi-value quantization processing suitable for gradation reproducibility in the image output device 12 in the region separated into the photograph region by the region separation processing unit 24. It is.

  The CMYK image data processed by the gradation reproduction processing unit 32 is temporarily stored in a storage unit such as an image memory (not shown), and then read from the storage unit in accordance with the timing of image formation under the control of the CPU 1. And output to the image output device 12. The image output device 12 outputs given image data onto a recording paper such as paper, and is a printer such as an electrophotographic system or an inkjet system. For example, in the case of the electrophotographic system, the image output device 12 is a charger that charges the photosensitive drum to a predetermined potential, and emits a laser beam in accordance with the given image data to electrostatic latent image on the surface of the photosensitive drum. A laser writer for generating an image, a developer for supplying toner to the electrostatic latent image generated on the surface of the photosensitive drum to make it visible, and a transfer for transferring the toner image formed on the surface of the photosensitive drum onto paper Equipped with containers. Note that the image output device 12 may be a display device such as a display.

  In the image processing apparatus 20 shown in FIG. 1, the background detection processing unit 25 and the background removal processing unit 26 are arranged immediately after the region separation processing unit 24. However, the present invention is not limited to this, and the spatial filter processing unit 27 may be arranged at other positions such as after 27, and may be arranged at any position as long as it is at least after the region separation processing unit 24 and before the color correction unit 29. In addition, the background detection processing unit 25 and the background removal processing unit 26 do not have to be continuously arranged, and the spatial filter processing unit 27 and the like may be arranged between them.

  Next, details of the background detection processing unit 25 of the image processing apparatus 20 will be described. 2 to 5 are block diagrams showing the detailed configuration of the background detection processing unit of the image processing apparatus 20 according to the present invention. The background detection processing unit 25 includes a counting unit 35, a background determination unit 36, a background region extraction unit 37, and the like. The RGB image data output from the region separation processing unit 24 is the counting unit 35 of the background detection processing unit 25. To be given to. The counting unit 35 has three counters, a first counter 41, a second counter 42, and a background density counter 43 (see FIG. 3). The first counter 41 and the second counter 42 include a region separation processing unit 24. The edge detection result included in the region separation result is given. The first counter 41 is a counter that can create a histogram by counting the pixels included in the image data for each pixel density value (0 to 255), and is an aggregate of 256 counters. The second counter 42 and the background density counter 43 have the same configuration.

  FIG. 6 is a schematic diagram for explaining counting by the first counter 41 and the second counter 42 of the counting unit 35, and shows a part of image data given to the counting unit 35 in an enlarged manner. In addition, as a result of edge detection performed by the region separation processing unit 24, pixels corresponding to the edges are indicated by hatched squares, and pixels not corresponding to the edges are indicated by non-hatched squares. The counting unit 35 examines the density value of each pixel according to the horizontal line for the given RGB image data, and performs counting by the first counter 41 and the second counter 42.

  For example, the counting unit 35 uses the first counter 41 to start counting the number of pixels from the pixel a, and adds 1 to the count value corresponding to the density value of the pixel a of the first counter 41. The counting unit 35 continuously performs counting by the first counter 41 according to the horizontal line. When the pixel b corresponding to the edge is reached, the counter 35 switches the counter from the first counter 41 to the second counter 42, and the second counter The pixel is counted using. After that, when the pixel c that does not correspond to the edge is reached, the counting unit 35 switches the counter from the second counter 42 to the first counter 41 and counts the pixels using the first counter 41. . That is, the counting unit 35 counts pixels that do not correspond to the edges in the image data (pixels not hatched) by the first counter 41 to create a histogram of components other than the edges, and the second counter 42. The edge component histogram is created by counting the pixels corresponding to the edges (pixels with hatching).

  The counting unit 35 performs counting by the first counter 41 and the second counter 42 for each predetermined line (one line to several lines) of the image data. The counting unit 35 extracts the density value having the maximum count value from the counting results of the first counter 41 and the second counter 42 when the counting for the pixels of the predetermined line is completed. At this time, the density value with the maximum count value is extracted from the first counter 41, the density value with the maximum count value is extracted from the second counter 42, and the count values of these two density values are compared, What is necessary is just to further extract the density value with the larger count value. Thereby, a background density candidate value in a predetermined line of the input image data is obtained. The counting unit 35 adds 1 to the count value of the background density counter 43 according to the extracted density value (background density candidate value).

  Thereafter, the counting unit 35 resets the count values of the first counter 41 and the second counter 42, and repeats counting for each predetermined line until the counting for all image data is completed. When the above-described processing is completed for all image data, the counting unit 35 extracts the density value with the maximum count value as the representative background density candidate value from the count result by the background density counter 43, and the maximum count value and The density value is output to the background determination unit 36.

  The counting unit 35 not only extracts the maximum count value from the count result of the background density counter 43, but also sets a density value equal to or higher than a predetermined threshold value of the background density counter 43 to a plurality of representative background densities. It is good also as a structure extracted as a candidate value. When extracting only the largest count value, if there are few background areas included in the area where the density values are counted, density values other than the background area are extracted. Therefore, when there are a plurality of such regions, there is a possibility that erroneous determination occurs when determining the final background region. Therefore, by extracting a plurality of density values in which the count value of the background density counter 43 is equal to or greater than a predetermined threshold value, if there is some background in each area even if the count value is not the maximum, the density value of the background area is changed. Since it is extracted as a plurality of representative background density candidate values, there is a high possibility that the correct background density is determined in the final determination.

  The background determination unit 36 includes a maximum count value determination unit 45, a density value determination unit 46, and the like, and determines whether a background exists in the image data from the maximum count value and the density value given from the count unit 35. To do. The output from the counting unit 35 is given to the maximum count value determining unit 45, and the maximum count value determining unit 45 determines whether or not the given maximum count value exceeds a predetermined first threshold value. It is. The first threshold value can be set to a count value of about 60% of the total count value by the background density counter 43, for example. However, the first threshold value is not limited to this, and an appropriate value can be set by examining various image data. That's fine.

  When the counting unit 35 is configured to extract density values having a count value of the background density counter 43 equal to or greater than a predetermined threshold as a plurality of representative background density candidate values, the background determination unit 36 determines the maximum count value. It can be set as the structure which does not have the part 45. FIG. In this case, the background determination unit 36 gives a plurality of count values and density values from the counting unit 35 to the density value determination unit 46.

  When the maximum count value exceeds the first threshold value, the maximum count value determination unit 45 gives the density value given from the counting unit 35 to the density value determination unit 46 so that the density value can be determined. The density value determination unit 46 determines whether or not the given density value exceeds a predetermined second threshold value. Similarly to the first threshold value, the second threshold value may be determined by investigating various image data and setting a density range allowed as a background in advance. For example, when a density value of 200 or more is set as the background density value, The second threshold may be set to 199. When the density value determination unit 46 determines that the density value exceeds the second threshold, the background determination unit 36 determines that the input image data includes a pixel of background density, and the density value at this time Is output to the background area extraction unit 37 as a background density value.

  In the case where the counting unit 35 is configured to extract density values having a count value of the background density counter 43 equal to or greater than a predetermined threshold as a plurality of representative background density candidate values, the density value determination unit 46 is given. It is determined whether or not the plurality of representative background density candidate values exceed the second threshold value, and all density values exceeding the second threshold value are output to the background area extraction unit 37 as background density values.

  The background determination unit 36 outputs not only the background density value determined as the background density by comparison with the threshold value 1 and the threshold value 2 but also a plurality of density values including the density values before and after this value as the background density value. May be. The background determination unit 36 acquires a counter value corresponding to the density value for the predetermined range before and after the determined background density value from the background density counter 43, and sets the density background where the counter value exceeds the predetermined value as the background density value. Good. The predetermined value at this time is, for example, a value equal to or greater than 1/4 with respect to the number of all predetermined areas of the image data (that is, the total value of all the count values of the background density counter 43).

  The background region extraction unit 37 includes a background density determination unit 51, a continuity counter 52, a background region determination unit 53, a background line counter 54, and the like. The background area extraction unit 37 extracts a background area from the input RGB image data based on the background density value given from the background determination unit 36, and a predetermined number or more of pixels of the background density value are consecutive. In this case, the continuous pixels are extracted as the base region. The RGB image data and the background density value are provided to the background density determination unit 51. The background density determination unit 51 sequentially determines whether the density value of each pixel of the image data matches the given background density value according to the line. I have to do it. The background density determination unit 51 adds 1 to the continuity counter 52 when the density value of each pixel of the image data matches the background density value, and resets the continuity counter 52 when they do not match. is there. The background density determination unit 51 performs processing for each line of image data, and resets the continuity counter 52 every time one line of processing is completed.

  The continuity counter 52 is for counting the number of consecutive pixels having background density values in the image data, and is a simple counter for counting one value. The continuity counter 52 is configured to output a count value, which is a counting result, to the background area determination unit 53. The background area determination unit 53 determines whether or not the count value of the continuity counter 52 exceeds the third threshold value. If the count value exceeds the third threshold value, the background area determination unit 53 displays information indicating that consecutive pixels are background pixels. The data is output to the background removal processing unit 26 in synchronization with the data.

  Further, the background area determination unit 53 determines whether or not a background pixel is included in each line of the image data (that is, whether or not the count value of the continuity counter 52 exceeds the third threshold even once for each line). If a background pixel is included, 1 is added to the background line counter 54. The background area determination unit 53 performs this determination for each line of the image data, performs the counting by the background line counter 54, and after the processing of all the lines of the image data is completed, the number of lines including the background pixels is all. It is checked whether or not a predetermined ratio (for example, 70%) of the number of lines is exceeded. When the number of lines including the background pixels exceeds a predetermined ratio, the background area determination unit 53 determines that the given image data includes the background area, and the number of lines including the background pixels does not exceed the predetermined ratio. In this case, it is determined that the image data does not have a background area, and the determination result is notified to the background removal processing unit 26. Based on this determination result, the background removal processing unit 26 performs the background removal processing only when the image data has a background area.

  Note that the counting unit 35 is configured to extract, as a plurality of representative background density candidate values, density values whose count value of the background density counter 43 is equal to or greater than a predetermined threshold value, and all the densities for which the background determination unit 36 exceeds the second threshold value. When the value is output to the background area extraction unit 37 as the background density value, the background area extraction unit 37 performs the following processing to determine that the local background is not the background area, and It is possible not to perform the removal. For example, the background area extraction unit 37 performs determination for each of a plurality of given background density values by the background density determination unit 51, and the continuity counter 52 has the largest count value (that is, the highest continuity). It is possible to adopt a configuration in which the background area determination unit 53 determines the object.

  Further, instead of performing the background removal processing in the background removal processing unit 26, for example, the image forming apparatus includes a plurality of paper trays, sets sheets of different colors in each paper tray, and sets the paper color and the paper. In the case of a configuration in which the correspondence with the tray can be related, output is performed using the paper of the color closest to this color based on the color of the background area extracted by the background area extraction unit 37. It is good also as a structure.

  FIG. 7 is a flowchart showing a procedure of image processing relating to the background of image data performed by the image forming apparatus according to the present invention, which is processing performed by the image processing apparatus 20 under the control of the CPU 1 that executes the program code 101. . First, the image processing device 20 performs edge detection of the image data input from the image input device 11 at the region separation processing unit 24 (step S1). Based on the result of the edge detection, the image processing apparatus 20 performs a counting process in the counting unit 35 of the background detection processing unit 25 (step S2), and extracts a representative background density candidate value. Next, based on the extracted representative background density candidate value, the image processing apparatus 20 performs background determination processing using the first threshold value and the second threshold value in the background determination unit 36 of the background detection processing unit 25 (step S3), and image data It is checked whether or not the background density value is included in (step S4).

  When the background density value is included (S4: YES), the image processing apparatus 20 performs the background area extraction process in the background area extraction unit 37 of the background detection processing unit 25 (step S5), and has the background density value. From the continuity of the pixels, it is checked whether or not a background area exists in the image data (step S6). If a background area exists (S6: YES), the image processing apparatus 20 performs a background removal process in the background removal processing unit 26 (step S7), and the process is terminated. If the background density area is not included in step S4 (S4: NO), or if the background area does not exist in step S6 (S6: NO), the image processing apparatus 20 performs the process without performing the background removal process. finish.

  8 and 9 are flowcharts showing the procedure of the counting process performed by the image forming apparatus according to the present invention, which is the process performed in step S2 of the flowchart of FIG. The counting unit 35 of the image processing apparatus 20 first selects the first counter 41 as a counter used for counting (step S21), and acquires image data for one pixel (step S22). One pixel of the image data is composed of 8-bit (0 to 255) density values of R, G, and B, with density value 0 representing black and density value 255 representing red, green, and blue. Shall.

  Next, the counting unit 35 acquires an edge detection result from the region separation processing unit 24 for the acquired pixel (step S23), and determines whether or not an edge change has occurred from edge to non-edge or from non-edge to edge. Check (step S24). When a change occurs in the edge (S24: YES), the counting unit 35 switches the counter from the first counter 41 to the second counter 42 or from the second counter 42 to the first counter 41 (step S25) and is selected. Using the counter, the count value corresponding to the acquired density value of the pixel is counted up (step S26). If no change has occurred in the edge (S24: NO), the counting unit 35 counts up the selected counter without switching the counter (step S26).

  Next, the counting unit 35 checks whether or not the above process has been completed for a predetermined line (step S27). If not completed (S27: NO), the counting unit 35 returns to step S22 and repeats the above process. . When the process is completed for the predetermined line (S27: YES), the counting unit 35 examines the count values of the first counter 41 and the second counter 42 and extracts the density value (background density candidate value) having the maximum count value. Then, the background density counter 43 corresponding to the extracted density value is counted up (step S29), and the first counter 41 and the second counter 42 are reset (step S30).

  Next, the counting unit 35 checks whether or not the above process has been completed for all the pixels of the image data (step S31). If the process has not been completed for all the pixels (S31: NO), the process returns to step S21. The above process is repeated. When the processing has been completed for all pixels (S31: YES), the counting unit 35 extracts the density value (representative background density candidate value) having the maximum count value from the count value of the background density counter 43 (step S32). The extracted maximum count value and the corresponding density value are output to the background determination unit 36, and the counting process is terminated.

  FIG. 10 is a flowchart showing the procedure of the background determination process performed by the image forming apparatus according to the present invention, and is the process performed in step S3 of the flowchart of FIG. First, the background determination processing unit 36 of the image processing unit 20 acquires the maximum count value and the density value output from the counting unit 35 (step S41), and determines whether or not the acquired maximum count value exceeds the first threshold value. The count value determination unit 45 checks (step S42). When the maximum count value exceeds the first threshold (S42: YES), the background determination processing unit 36 further checks whether or not the acquired density value exceeds the second threshold by the density value determination unit 46 ( Step S43). When the density value exceeds the second threshold value (S43: YES), the background determination processing unit 36 outputs this density value as the background density value to the background area extraction unit 37 (step S44), and ends the background determination process. If the maximum count value does not exceed the first threshold value in step S42 (S42: NO), or if the density value does not exceed the second threshold value in step S43 (S43: NO), the background determination processing unit 36 selects the image It is determined that the background area is not included in the data and the background density value does not exist (step S45), and the background determination process ends.

  11 and 12 are flowcharts showing the procedure of the background area extraction process performed by the image forming apparatus according to the present invention, which is the process performed in step S5 of the flowchart of FIG. First, the background region extraction unit 37 of the image processing unit 20 acquires the background density value from the background determination processing unit 36 (step S61), acquires image data for one pixel (step S62), Whether the density is a background density is checked by the background density determination unit 51 (step S63). When the acquired pixel density is the background density (S63: YES), the continuity counter 52 is counted up (step S64), and the process proceeds to step S68.

  When the acquired pixel density is not the background density (S63: NO), the background area extraction unit 37 further checks whether the count value of the continuity counter 52 exceeds the third threshold value by the background area determination unit 53 ( Step S65). When the count value exceeds the third threshold (S65: YES), the background area extraction unit 37 synchronizes the background area information indicating that the continuous pixels are the pixels of the background area with the image data, and the background removal processing unit 26 (Step S66), the continuity counter 52 is reset (step S67), and the process proceeds to step S68. If the count value of the continuity counter 52 does not exceed the third threshold (S65: NO), the background area extraction unit 37 resets the continuity counter 52 without outputting the background area information ( The process proceeds to step S67) and step S68. After counting up or resetting the continuity counter 52, the background area extraction unit 37 checks whether or not the above-described processing has been completed for a predetermined line of image data (step S68). (S68: NO), the process returns to step S62 and the above process is repeated.

  When the processing is completed for the predetermined line (S68: YES), the ground area extraction unit 37 further checks whether or not the ground pixel is included in the predetermined line (step S69). If the predetermined line includes a background pixel (S69: YES), the background region extraction unit 37 counts up the background line counter 54 (step S70), and proceeds to step S71. If no background pixel is included in the predetermined line (S69: NO), the background area extraction unit 37 proceeds to step S71 without counting up the background line counter 54. Next, the background area extraction unit 37 checks whether or not the above-described processing has been completed for all the pixels of the image data (step S71), and if not completed for all the pixels (S71: NO), proceeds to step S62. Return and repeat the above process.

  When the processing has been completed for all the pixels of the image data (S71: YES), the background area extraction unit 37 further checks whether the number of background lines counted by the background line counter 54 has exceeded a predetermined ratio with respect to all lines. (Step S72). When the number of background lines exceeds a predetermined ratio (S72: YES), the background area extraction unit 37 determines that there is a background area in the image data (step S73), and ends the process. If the number of background lines does not exceed the predetermined ratio (S72: NO), the background area extraction unit 37 determines that there is no background area in the image data (step S74), and ends the process.

  FIG. 13 is a flowchart showing the procedure of the background removal process performed by the image forming apparatus according to the present invention, which is the process performed in step S7 of the flowchart of FIG. The background removal processing unit 26 of the image processing apparatus 20 first acquires image data for one pixel output from the background detection processing unit 25 (step S81), and outputs the image data as a background detection result in synchronization with the image data. Background area information is acquired (step S82). Next, the background removal processing unit 26 checks whether the pixel of the acquired image data is a background pixel based on the acquired background area information (step S83). If the acquired pixel is a background (S83: YES), the background removal processing unit 26 removes the background (step S84) and proceeds to step S85. The background removal can be performed by converting the density value of the background pixel to a predetermined density value such as 255, for example. If the acquired pixel is not a background (S83: NO), the background removal processing unit 26 proceeds to step S85 without removing the background. Next, the background removal processing unit 26 checks whether or not the above-described processing has been completed for all the pixels of the image data (step S85), and if not completed for all the pixels (S85: NO), step Returning to S81, the above-described processing is repeated, and if all the pixels are finished (S85: YES), the background removal processing is finished.

  FIG. 14 is a schematic diagram illustrating an example of image data input to the image processing unit 20 by the image input device 11. The illustrated image data has areas for characters, halftone dot photographs, and halftone dot backgrounds, and other areas are background areas. The background detection processing unit 25 of the image processing unit 20 performs processing using one to several lines in the horizontal direction of the image data as a predetermined region. In FIG. 14, three predetermined regions 121 to 123 are indicated by a one-dot chain line. It is illustrated as a surrounding area. The predetermined area 121 includes characters and background pixels, the predetermined area 122 includes characters, halftone pictures, and background pixels, and the predetermined area 123 includes characters, halftone dots, and background pixels. It is included.

  FIG. 15 is a schematic diagram for explaining the configuration of the pixels in the predetermined areas 121 to 123, where (a) shows the configuration of the predetermined area 121, (b) shows the configuration of the predetermined area 122, and (c). The structure of the predetermined area 123 is shown in FIG. In FIGS. 15A to 15C, the density values of the image data are shown in the upper level in the upper stage, the pixels having low density values (that is, dark) are shown on the upper side, and the density values are high (that is, bright). ) Pixels are shown below. Further, the lower part shows the edge detection result of the image data, and the hatched pixels are detected as edges. In the image data shown in FIG. 15, each predetermined area is composed of 37 pixels. However, this is a simplified one, and the image data is actually composed of a larger number of pixels.

  FIG. 16 is a chart showing a counting example of the first counter 41 and the second counter 42 of the counting unit 35. The counting results in FIGS. 15 (a) to 15 (c) are shown in FIGS. c). In FIG. 16, it is assumed that the character density value in the image data is 10, the background density value is 200, and the halftone dot similarity value is unevenly distributed from 100 to 199. Suppose that the density values of the halftone dots are uniformly distributed between 150 and 250.

  The predetermined area 121 includes two types of pixels, a base 121a and a character 121b, and 14 of all 37 pixels are edges (see FIG. 15A). As described above, the counting unit 35 of the background detection processing unit 25 counts the number of pixels by the first counter 41 for each density value for pixels that are not edges, and counts the number of pixels by the second counter 42 for pixels at the edges. It is like that. Therefore, the first counter 41 creates a histogram for a portion other than the edge of the base 121a and a portion other than the edge of the character 121b (that is, the inside of the character 121b). The second counter 42 creates a histogram of the edge portions of the base 121a and the character 121b.

  In the counting result of the predetermined area 121 (see FIG. 16A), the number of pixels of the density value 10 by the first counter 41 is 10, and the number of pixels of the density value 200 is 17. Further, the number of pixels having the density value 10 by the second counter 42 is 6, and the number of pixels having the density value 200 is 8. Therefore, the maximum count value is the count value 17 of the density value 200 of the first counter 41, and the counting unit 35 uses the density value 200 as a background density candidate value and counts the count value of the density value 200 of the background density counter 43. Up.

  The predetermined area 122 includes three types of pixels, that is, a background 122a, a photograph 122b, and a character 122c (see FIG. 15B). In the counting result of the predetermined area 122 (see FIG. 16B), the number of pixels having the density value 10 by the first counter 41 is 1, nine pixels are dispersed in the density values 100 to 199, and the number of pixels having the density value 200. Is 8. Further, the number of pixels with the density value 10 by the second counter 42 is 4, 7 pixels are dispersed in the density values 100 to 199, and the number of pixels of the density area 200 is 8. Since the pixels having the density values of 100 to 199 are dispersed, the maximum count value is the count value 8 of the density value 200 of the first counter 41 and the second counter 42, and the counting unit 35 uses the density value 200 as the background density. As a candidate value, the count value of the density value 200 of the background density counter 43 is counted up.

  The predetermined area 123 includes three types of pixels, a background 123a, a halftone background 123b, and a character 123c (see FIG. 15C). In the counting result of the predetermined area 123 (see FIG. 16C), the number of pixels with the density value 10 by the first counter 41 is 4, and the number of pixels with the density value 150 is 3 (pixels in the halftone area that are not edges). The number of pixels is 6, but in the halftone dot area, the pixels having the density value 150 and the pixels having the density value 250 are evenly distributed), so the number of pixels of the density value 200 is 9, and the number of pixels of the density value 250 is 3 It is. Further, the number of pixels of the density value 10 by the second counter 42 is 6, the number of pixels of the density value 150 is 5, the number of pixels of the density value 200 is 2, and the number of pixels of the density value 250 is 5. . Therefore, the maximum count value is the count value 9 of the density value 200 of the first counter 41, and the counting unit 35 sets the density value 200 as a background density candidate value and counts the count value of the density value 200 of the background density counter 43. Up.

  In the count results of the first counter 41 and the second counter 42 for the three predetermined areas 121 to 123, the count value of the density value 200 is the maximum, and therefore, the count value of the density value 200 of the background density counter 43 is 3. Is added. However, when counting is performed for the entire image data, the count value of the density value 200 is not necessarily the maximum. In this case, the corresponding count value of the background density counter 43 is counted up. However, as in the image forming apparatus according to the present invention, the number of pixels for each density value is partially counted using one line to several lines of image data as a predetermined area, and the number of pixels having a density value that maximizes the count value. Since the background density counter 43 counts a large number of density values that exist throughout the entire image data, the density value corresponding to the maximum count value of the background density counter 43 exists in the entire image data. The density value to be

  However, if the maximum value of the number of predetermined areas counted by the background density counter 43 does not reach a certain number with respect to the number of all predetermined areas of the image data, the density value corresponding to this maximum value In the image forming apparatus according to the present invention, the background determination unit 36 compares the maximum count value by the background density counter 43 with the threshold value 1 so that the maximum count value is not distributed over the entire image data. When the threshold value 1 is not exceeded, it is determined that the background area is not included in the image data. Further, when the density value corresponding to the maximum count value is small, that is, when the density is high, the density value may not be the density of the background. Therefore, in the image forming apparatus according to the present invention, the background determination unit 36 performs the background determination. The density value corresponding to the maximum count value of the density counter 43 is compared with the threshold value 2, and it is determined that the density value does not include the background area in the image data. In addition, the background determination unit 36 that determines the background density value by performing the comparison process with the threshold value 1 and the threshold value 2 also determines the background density and the density value before and after the background density value based on the counter value of the background density counter 43. It is also possible to adopt a configuration that determines and outputs a plurality of background density values.

  After obtaining the background density using the first counter 41, the second counter 42, and the background density counter 43, the background area extraction unit 37 extracts the background area from the input image data. The background area extraction unit 37 is provided with image data for each pixel, and the background area extraction unit 37 determines whether or not the density value of the given pixel is the background density value. When the density value of the given pixel is the background density value, the background area extraction unit 37 adds 1 to the continuity counter 52 and first adds 1 to the continuity counter 52 (that is, the continuity counter 52 When the value changes from 0 to 1, the position information of this pixel is retained. When the density value of the given pixel is not the background density value, the background area extraction unit 37 determines the continuity up to the previous pixel in the same predetermined area based on the count value of the continuity counter 52. When the count value of the continuity counter 52 does not exceed the threshold value 3, the ground area extraction unit 37 determines that these pixels are not in the ground area. When the count value of the continuity counter 52 exceeds the threshold 3, the background area extraction unit 37 determines that these pixels are those of the background area, and synchronizes with the pixels up to the previous position of this pixel, A signal indicating the background area is output to the background removal processing unit 26 as a background detection result. For example, when the number of pixels in one line of the image data is 7000, the threshold value 3 is 700, and it can be determined that there is continuity when pixels having a ratio of 10% or more continue. This ratio may be determined in advance experimentally or empirically, but depends on the size or magnification of the image data. In addition, in order to synchronize the background detection processing unit 25 and the background removal processing unit 26, image data output from the background detection processing unit 25 is held in a line buffer for one line, and all pixels in one line are stored. The background region extraction unit 37 repeatedly determines the continuity until the process is completed, and resets the value of the continuity counter 52 when the process for one line is completed.

  With these processes, the background area detection process for the image data input from the image input device 11 is completed. FIG. 17 is a schematic diagram showing an example of the detection result of the background region, and shows the processing result obtained by performing the above-described processing on the image data shown in FIG. The areas indicated by hatching in FIG. 17 are the detected base areas. Note that the character area of the image data is actually separated according to the character shape for each character, but in FIG. 17, it is illustrated as separated for each character string for simplification. Therefore, the background detection processing unit 25 actually outputs a pixel other than the character included in the character string portion as the background region.

  After the background area is detected by the background detection processing unit 25, the background removal processing unit 26 performs background removal processing from the image data based on the detection result. When the background detection result is given to the background removal processing unit 26 in synchronization with the image data, and the pixel to be processed is a pixel in the background region, the background removal processing unit 26 converts the density value of this pixel to white To do. If it is not a pixel in the background area, the background removal processing unit 26 outputs the given pixel as it is. The background removal processing unit 26 performs this process for all the pixels of the image data.

  However, for example, the background detection processing unit 25 generates a gamma curve such that the background density value is converted to white based on the detected background density value, and supplies the gamma curve to the background removal processing unit 26 as a background detection result. The processing unit 26 may be configured to convert image data based on the gamma curve.

  In the image forming apparatus having the above configuration, the background density candidate values are extracted using a plurality of counters (first counter 41 and second counter 42) for each predetermined region of one line or a plurality of lines of image data. A representative background density candidate value is extracted from the background density candidate value using the background density counter 43, and the count value and the representative background density candidate value at this time are compared with the threshold values 1 and 2 by the background determination unit 36, and the background density is compared. With this configuration, the density widely distributed over the entire image data can be acquired as the background density value, so that the image forming apparatus can form a high-quality image with the background removed accurately. Can do. Further, only when a predetermined number or more of pixels having the background density value are continuous, the image forming apparatus determines the background area from the image data more accurately by determining these consecutive pixels as the background area. Can be detected.

  In the present embodiment, the CPU 1 reads out and executes the program code 101 (executable program, intermediate code program, source program, etc.) from the memory card 100, and the image forming apparatus performs the above-described background detection processing. However, the present invention is not limited to this, and the program code 101 may be stored in the ROM 2 in advance. Alternatively, the above-described background detection processing may be performed on a computer by executing the program code 101 on a general-purpose computer or the like. Further, the program code 101 may be held not in the memory card 100 but in a ROM, RAM, hard disk, or the like provided in the computer. Furthermore, as a recording medium that can be attached to and detached from the image forming apparatus or computer, a tape medium such as a magnetic tape or a cassette tape, a magnetic disk medium such as a flexible disk or a hard disk, a disk medium such as a CD-ROM, MO, MD, or DVD The program code 101 may be stored in a card medium such as an IC card or an optical card, or a semiconductor memory such as a mask ROM, EPROM, EEPROM, or flash memory. Accordingly, the program code 101 for performing the background detection process and the background removal process can be freely carried by the recording medium and provided.

  Further, the program code 101 held in these recording media may be directly read and executed by the image forming apparatus or the computer, or may be stored in advance on a hard disk provided in the image forming apparatus or the computer. The program code 101 which is installed and the image forming apparatus or the computer is installed may be read and executed.

  In addition, a connection function may be installed in an image forming apparatus, a computer, or the like on a network such as the Internet and a LAN, and the program code 101 may be downloaded via the network. In this case, a program for performing the download process may be stored in advance in an image forming apparatus or a computer, or may be configured to install and execute a program held in various recording media. Note that the present invention can also be realized in the form of a computer data signal in which the program code 101 is embedded in a carrier wave embodied by electronic transmission. Further, the program code 101 is configured not to execute only the above-described background detection processing and background removal processing, but to be executed comprehensively including other processing of the image forming apparatus. Good.

  Further, as the image input device 11, for example, a device such as a flat head scanner, a film scanner, or a digital camera can be used. As the image output device 12, for example, an image display device such as a CRT display or a liquid crystal display, or an electrophotographic or inkjet printer that outputs a processing result to a recording paper such as paper can be used. Further, the image forming apparatus may include a modem or the like as communication means for connecting to a server apparatus or the like via a network.

  In this embodiment, the image forming apparatus is configured to perform background detection processing on RGB image data. However, the present invention is not limited to this, and may be CMYK or CIELAB depending on detection accuracy, image processing configuration, and the like. For example, the background detection processing may be performed on image data in another color space. In this case, in a color space such as CMYK in which density values and color information are mixed, background detection processing may be performed by the same processing as in the case of RGB. In a color space such as CIELAB in which luminance and chromaticity are separated, processing may be performed with luminance as the center, and chromaticity information may be used as auxiliary information.

(Modification 1)
In the above-described embodiment, the counting unit 35 has two counters, the first counter 41 and the second counter 42, and the counter used for counting is switched between the edge component and the non-edge component of the image data. However, the present invention is not limited to this, and a configuration in which counting is performed using three or more more counters may be employed. In the first modification, a case will be described in which the counting unit of the image forming apparatus has three counters of a first counter to a third counter.

  The image forming apparatus according to the first modification detects the edge of the image data, and switches the three counters according to the rise and fall of the edge component of the image data. The counting unit of the image forming apparatus according to Modification 1 sequentially counts each pixel of the image data. For example, the counting unit first starts counting using the first counter, and detects the edge component of the image data. The counter is switched from the first counter to the second counter at each rising edge and from the second counter to the third counter, and from the third counter to the second counter at each falling edge component of the image data, from the second counter. The counter is switched to the first counter.

  FIG. 18 is a schematic diagram for explaining a counter switching example of the image forming apparatus according to the first modification of the present invention. The example shown in the figure is a case where the image data has a background, a halftone dot background, a character, and a character on a halftone dot (a character on a halftone dot background). The counting unit of the image forming apparatus first starts counting the background pixels by the first counter, and switches the counter from the first counter to the second counter at the rising edge of the background and the halftone background and performs the counting. Further, at the rising edge of the halftone dot base and the character on the halftone dot, the counting unit switches the counter from the second counter to the third counter and performs counting. Thereafter, the counting unit performs counting by switching the counter from the third counter to the second counter at the falling edge of the halftone dot character and the halftone dot edge, and at the falling edge of the halftone dot edge and the background edge. Counting is performed by switching the counter from the second counter to the first counter. Similarly, the counting unit performs counting by switching the counter from the first counter to the second counter at the rising edge of the background and the character edge, and performs counting from the second counter at the falling edge of the character and the background edge. The counter is switched to the counter and counts.

  As described above, by switching the counter at the rising edge and the falling edge, the first counter counts the background pixel, the second counter counts the halftone dot background and the character pixel, Since the three counters can count the characters on the halftone dots, it is possible to create a histogram in which each region is separated by the three counters. Therefore, it is possible to more accurately detect the density that exists uniformly in the entire image data as the background density. When the counting by the three counters is completed for one predetermined area, the counting unit extracts the density value (background density candidate value) having the maximum count value from the three counters, and uses this density value of the background density counter 43 as the density value. Add 1 to the corresponding count value. Since the subsequent processing is the same as the above-described processing, description thereof is omitted.

(Modification 2)
In the above-described embodiment, the counting unit 35 has two counters, the first counter 41 and the second counter 42, and the counter used for counting is switched between the edge component and the non-edge component of the image data. However, the present invention is not limited to this, and it may be configured to perform counting only for non-edge components.

  FIG. 19 is a block diagram illustrating a configuration of the counting unit 135 of the image processing apparatus according to the second modification of the present invention. 3 includes two counters, a first counter 41 and a second counter 42. However, the counter 135 of the image forming apparatus according to the second modification includes only the first counter 41. The second counter 42 is not provided. The first counter 41 is given an edge detection result included in the region separation result of the region separation processing unit 24, and a histogram is created by counting pixels that are not edges from the edge detection result.

  The counting unit 35 performs the counting by the first counter 41 for each predetermined line of the image data, and extracts the density value having the maximum count value from the counting result of the first counter 41 when the counting for the pixels of the predetermined line is completed. To do. Thereby, a background density candidate value in a predetermined line of the input image data is obtained. The counting unit 35 adds 1 to the count value of the background density counter 43 corresponding to the extracted background density candidate value.

  Even in the case of the configuration of Modification 2 described above, the detection accuracy of the background region may be somewhat lowered, but the detection of the background region can be performed. That is, compared to the case where the background area is detected considering both the edge component and the non-edge component, when the background area is detected only from the non-edge component, for example, the character area between the edges is detected. Since there is no information to determine that this density value is the character density value for the pixel density value, there may be areas where the character density value is erroneously determined as the background candidate density value in image data with many characters There is a possibility that the detection accuracy of the base region is lowered. However, even with the configuration of the second modification, it is possible to detect the background region, and there is an advantage that the configuration of the counting unit 135 can be simplified and hardware resources can be saved.

1 is a block diagram illustrating a configuration of an image forming apparatus according to the present invention. It is a block diagram which shows the detailed structure of the background detection process part of the image processing apparatus which concerns on this invention. It is a block diagram which shows the detailed structure of the background detection process part of the image processing apparatus which concerns on this invention. It is a block diagram which shows the detailed structure of the background detection process part of the image processing apparatus which concerns on this invention. It is a block diagram which shows the detailed structure of the background detection process part of the image processing apparatus which concerns on this invention. It is a schematic diagram for demonstrating the count by the 1st counter and 2nd counter of a counting part. 4 is a flowchart illustrating a procedure of image processing relating to a background of image data performed by the image forming apparatus according to the present invention. 6 is a flowchart illustrating a counting process performed by the image forming apparatus according to the present invention. 6 is a flowchart illustrating a counting process performed by the image forming apparatus according to the present invention. 6 is a flowchart illustrating a procedure of background determination processing performed by the image forming apparatus according to the present invention. 6 is a flowchart illustrating a procedure of background area extraction processing performed by the image forming apparatus according to the present invention. 6 is a flowchart illustrating a procedure of background area extraction processing performed by the image forming apparatus according to the present invention. 3 is a flowchart illustrating a procedure of background removal processing performed by the image forming apparatus according to the present invention. It is a schematic diagram which shows an example of the image data which an image input device inputs into an image process part. It is a schematic diagram for demonstrating the structure of the pixel of a predetermined area | region. It is a chart which shows one count example of the 1st counter of a counting part, and the 2nd counter. It is a schematic diagram which shows an example of the detection result of a base area | region. FIG. 10 is a schematic diagram for explaining a counter switching example of the image forming apparatus according to the first modification of the present invention. It is a block diagram which shows the structure of the counting part of the image processing apparatus which concerns on the modification 2 of this invention.

Explanation of symbols

1 CPU
2 ROM
3 RAM
6 Memory mounting part 11 Image input device (input means)
12 Image output device (output means)
DESCRIPTION OF SYMBOLS 20 Image processing apparatus 21 A / D conversion part 22 Shading correction part 23 Input gradation correction part 24 Area | region separation process part (edge detection means)
25 Background detection processing unit (background density candidate extraction means, representative background density candidate value extraction means)
26 Background Removal Processing Unit 27 Spatial Filter Processing Unit 28 Scaling Processing Unit 29 Color Correction Unit 30 Black Generation and Undercolor Removal Unit 31 Output Tone Correction Unit 32 Tone Reproduction Processing Unit 35 Counting Unit 36 Background Determination Unit 37 Background Area Extraction Unit (Background area determination means)
41 First counter (counting means)
42 Second counter (counting means)
43 Background density counter 45 Maximum count value determination unit (pixel number determination means)
46 Density value determination unit (density value determination means)
51 Background Density Determination Unit 52 Continuity Counter 53 Background Area Determination Unit 100 Memory Card (Recording Medium)
101 Program code (computer program)
121-123 predetermined area

Claims (13)

In a background area detection method for detecting a background area included in input image data,
Detect edges from input image data,
For each of a plurality of predetermined areas in the image data, for the pixels included in the detected edge, count the number of pixels for each density value,
For each pixel that is not included in the edge for each predetermined area, count the number of pixels for each density value,
For each predetermined area, extract a background density candidate value based on both count results,
From the plurality of background density candidate values calculated for each predetermined region, a representative background density candidate value is extracted based on the number of pixels of each background density candidate value,
Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number;
Determining whether the representative background density candidate value exceeds a predetermined density value;
A background area detection method, comprising: determining whether a background area is included in the image data based on both determination results. In a background area detection method for detecting a background area included in input image data,
Detect edges from input image data,
For each of a plurality of predetermined regions in the image data, for pixels not included in the detected edge, count the number of pixels for each density value,
For each predetermined area, extract the background density candidate value based on the counting result,
From the plurality of background density candidate values calculated for each predetermined region, a representative background density candidate value is extracted based on the number of pixels of each background density candidate value,
Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number;
Determining whether the representative background density candidate value exceeds a predetermined density value;
A background area detection method, comprising: determining whether a background area is included in the image data based on both determination results. In a background area detection method for detecting a background area included in input image data,
Using a plurality of counting means for counting the number of pixels for each density value,
Detect edges from input image data,
For each of a plurality of predetermined regions in the image data, the counting unit is switched according to the edge detection result, and the number of pixels is counted for each density value.
For each predetermined area, extract the background density candidate value based on the counting result of each counting means,
From the plurality of background density candidate values calculated for each predetermined region, a representative background density candidate value is extracted based on the number of pixels of each background density candidate value,
Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number;
Determining whether the representative background density candidate value exceeds a predetermined density value;
A background area detection method, comprising: determining whether a background area is included in the image data based on both determination results. The extraction of the background density candidate value is performed by extracting the density value corresponding to the largest number of pixels from the counting result,
2. The representative background density candidate value is extracted by extracting a background density candidate value having the largest number of pixels from a plurality of background density candidate values extracted for each of the predetermined areas. Item 4. The background region detection method according to any one of Items 1 to 3. When the image data is composed of a plurality of pixels arranged side by side vertically and horizontally,
The ground region detection method according to any one of claims 1 to 4, wherein the predetermined region is a region formed of one or a plurality of columns of the image data in the vertical or horizontal direction. . Determining continuity in the image data for a plurality of pixels having the representative background density candidate value;
6. The background according to claim 1, wherein when the predetermined number or more of the pixels are continuous, it is determined that the background area is included in the image data. Region detection method. The ground area detection method according to claim 1, wherein a ground area included in the image data is removed. In an image processing apparatus for detecting a background area included in input image data,
Edge detection means for detecting edges from input image data;
Counting means for counting the number of pixels for each density value for the pixels included in the detected edge for each of a plurality of predetermined regions in the image data;
Counting means for counting the number of pixels for each density value for pixels not included in the edge for each predetermined area;
A background density candidate value extracting means for extracting a background density candidate value based on the counting results of both counting means for each predetermined area;
Representative background density candidate value extraction means for extracting a representative background density candidate value based on the number of pixels of each background density candidate value from a plurality of background density candidate values extracted for each predetermined region;
A pixel number determination means for determining whether or not the number of pixels of the representative background density candidate value exceeds a predetermined number;
Density value determining means for determining whether the representative background density candidate value exceeds a predetermined density value;
An image processing apparatus comprising: a background determination unit that determines whether or not a background region is included in the image data based on determination results of the pixel number determination unit and the density value determination unit. In an image processing apparatus for detecting a background area included in input image data,
Edge detection means for detecting edges from input image data;
Counting means for counting the number of pixels for each density value for pixels not included in the detected edge for each of a plurality of predetermined regions in the image data;
A background density candidate value extracting means for extracting a background density candidate value based on a counting result of the counting means for each predetermined area;
Representative background density candidate value extraction means for extracting a representative background density candidate value based on the number of pixels of each background density candidate value from a plurality of background density candidate values extracted for each predetermined region;
A pixel number determination means for determining whether or not the number of pixels of the representative background density candidate value exceeds a predetermined number;
Density value determining means for determining whether the representative background density candidate value exceeds a predetermined density value;
An image processing apparatus comprising: a background determination unit that determines whether or not a background region is included in the image data based on determination results of the pixel number determination unit and the density value determination unit. The image processing apparatus according to claim 8 or 9,
Input means for inputting image data to the image processing device;
An image forming apparatus comprising: an output unit configured to output an image related to image data image-processed by the image processing apparatus. In a computer program for causing a computer to detect a background area included in image data,
On the computer,
Detecting edges from the image data;
For each of a plurality of predetermined areas in the image data, for the pixels included in the detected edge, the number of pixels is counted for each density value,
For each pixel that is not included in the edge for each predetermined area, the number of pixels is counted for each density value,
For each predetermined area, based on both counting results, extract a background density candidate value,
From the plurality of background density candidate values extracted for each predetermined area, the representative background density candidate value is extracted based on the number of pixels of each background density candidate value,
Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number;
Determining whether the representative background density candidate value exceeds a predetermined density value;
A computer program for determining whether or not a background area is included in the image data based on both determination results. In a computer program for causing a computer to detect a background area included in image data,
On the computer,
Detecting edges from the image data;
For each of a plurality of predetermined regions in the image data, for pixels not included in the detected edge, the number of pixels is counted for each density value,
For each predetermined area, based on the counting result, extract a background density candidate value,
From the plurality of background density candidate values extracted for each predetermined area, the representative background density candidate value is extracted based on the number of pixels of each background density candidate value,
Determining whether the number of pixels of the representative background density candidate value exceeds a predetermined number;
Determining whether the representative background density candidate value exceeds a predetermined density value;
A computer program for determining whether or not a background area is included in the image data based on both determination results.   A computer-readable recording medium on which the computer program according to claim 11 or 12 is recorded.

Images