JP2002232708A - Image processing device, image forming device using the same, and image processing method - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing device which can accurately discriminate image types in an easy way and can prevent the expansion of the circuit scale. SOLUTION: This image processing device has a main scanning direction decision part and a sub-scanning direction decision part which determine to which area a target pixel belongs, after obtaining feature amount by extracting the image data in the main scanning direction and the sub-scanning direction that contain containing the target pixel from a block consisting of a plurality of pixels that were extracted from input image data. The main scanning direction decision part and the sub-scanning direction decision part are respectively provided with a maximum density difference calculation part 33 which calculates the maximum density difference using a minimum density value and a maximum density value determined from those image data obtained for the main scanning direction and the sub-scanning direction respectively, a total density complexity calculation part 34 which calculates the total density complexity based on the sum of the absolute values of density differences between adjacent image data, and a decision region setting part 35 which classifies the target pixel into character/halftone region, or base/photography region based on the maximum density difference, the total density complexity, and a first and second thresholds that have been set in advance.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to image processing for determining whether input data obtained by scanning a document is a character, a halftone dot, a photograph (photographic paper), or a background area. The present invention relates to an apparatus, an image forming apparatus including the same, and an image processing method.

[0002]

2. Description of the Related Art As an image forming apparatus such as a copying machine using an electrophotographic system, a digital type is widely used in addition to a conventional analog type. Full-color digital copiers that reproduce high-quality images have been commercialized.

Original images copied by these image forming apparatuses include backgrounds, characters, halftone dots (printed photographs), photographic paper photographs (photographs), or a combination of these. To obtain an image, it is necessary to perform image processing suitable for each image type or document type.

Here, as a conventional method for determining the image tone (type) of an image represented by a plurality of image data, for example, there is an image identification method disclosed in Japanese Patent Publication No. 5-56067. In the image identification method disclosed in the above publication, a digital image read by a scanner is divided into a plurality of blocks, and within this block, a sum S of absolute values of adjacent pixel density differences, a maximum density value and a minimum density value, and And the maximum density difference ΔDmax is obtained from the difference
Calculate S / ΔDmax. Then, according to the obtained value of the image tone parameter PS, identification is made in three ways: a line drawing area such as a character, a halftone area such as a photograph, and a halftone area.

In order to select an image mode as an operation mode of a digital copying machine according to the type of a document,
Each mode such as a character mode, a character / photo mode, and a photo mode is prepared.

[0006] However, it is very troublesome for the operator to switch between the modes for each document. In addition, when an inappropriate mode is selected, remarkable image deterioration is often observed, and useless copying is performed.

To solve such a problem, for example, an image forming apparatus disclosed in Japanese Patent Application Laid-Open No. Hei 8-251406 has been proposed as an apparatus for automatically determining the type of a document. In the above image forming apparatus, while determining whether the document is chromatic or achromatic,
By performing the image separation function, that is, performing edge separation and halftone dot determination, the original can be converted to line drawings, halftones, continuous tones,
Judge whether it is line drawing and half tone, half tone and continuous tone, continuous tone and line drawing, line drawing, half tone and continuous tone, and automatically filter the processing mode corresponding to this.
It is shown that color correction, selector and gradation processing are provided.

[0008]

However, the conventional image processing apparatus, the image forming apparatus having the same, and the image processing method have the following problems and cannot be said to be sufficient.

First, in the image identification method disclosed in Japanese Patent Publication No. 5-56067, no distinction is made between a photographic paper photograph and a background, and the sum S of absolute values of adjacent pixel density differences is calculated as the maximum density difference ΔDmax. Since the quotient is obtained by dividing by, and the value is identified by the value, there is a problem that if the maximum density difference becomes small, the accuracy becomes extremely poor. Furthermore, in the case of a large character, the sum S of the absolute values of the adjacent pixel density differences is small and the maximum density difference ΔDmax is large, so that the image tone parameter PS becomes small and is erroneously determined as a photographic area.

In addition, since the sum S of the absolute values of the adjacent pixel density differences and the maximum density difference ΔDmax greatly change depending on the signal for each color component even in the same pixel such as a color character, the same is applied to the color character. There is also a problem that it cannot be done. In general, when the type of a document is determined before copying is performed, pre-scan data, that is, image data read at a low resolution is often used. There is a problem that it cannot be applied.

Next, in the image forming apparatus disclosed in Japanese Patent Application Laid-Open No. 8-251406, when the type of the document is determined, the processing contents are different depending on the type of the document, which is very complicated. In addition, since a single color signal is used, the density may vary greatly depending on the signal even for the same pixel as in a color original. Furthermore, since a different determination unit for each area separation is used for pixel determination in the n × n data matrix unit in the main scanning direction and the sub-scanning direction, there is a problem that a circuit for performing processing becomes very large. In addition, as described above, there is a problem that pre-scan data having a reduced resolution in the sub-scanning direction cannot be completely handled.

SUMMARY OF THE INVENTION The present invention has been made in view of the above-described conventional problems, and has as its object to determine the image type of an input image with high accuracy by a simple method.
An object of the present invention is to provide an image processing apparatus capable of preventing an increase in circuit scale, an image forming apparatus including the same, and an image processing method.

[0013]

In order to solve the above-mentioned problems, an image processing apparatus according to the present invention separates input image data read from a document into a plurality of areas including a character area, a halftone area, and a photograph area. In an image processing apparatus including at least an area separating unit that performs
An image in the main scanning direction including a target pixel from a determination block storage unit that stores a block composed of a plurality of pixels extracted from input image data, and a block composed of a plurality of pixels stored in the determination block storage unit Main scanning direction determining means for extracting data to determine a feature amount and determining whether the pixel of interest belongs to a character / halftone area or a background / photograph area; The image data in the sub-scanning direction including the pixel of interest is extracted from the block of pixels to determine the feature amount, and it is determined whether the pixel of interest belongs to the character / halftone area or the background / photograph area. Scanning direction determining means, and the main scanning direction determining means and the sub-scanning direction determining means each include a minimum density obtained from image data in the main scanning direction or the sub-scanning direction. Maximum density difference calculating means for calculating the maximum density difference using the values and the maximum density value, and the total density busyness calculating the total density busyness by calculating the sum of the absolute values of the density differences of adjacent image data Calculating means, the maximum density difference calculated by the maximum density difference calculating means and the total density busyness calculated by the total density busyness calculating means as feature quantities, and these feature quantities and a first predetermined It is characterized in that a determination area setting means for classifying a pixel of interest into one of a character / halftone area and a base / photograph area based on the threshold value and the second threshold value is provided.

According to the above invention, the maximum density difference and the maximum density difference in the main scanning direction and the sub-scanning direction of the target image, respectively,
Calculate the total density busyness which is the sum of the absolute values of the density differences of adjacent pixels, and, based on the calculated maximum density difference and the total density busyness, for each pixel of the target image, It is determined to be a base / photograph area.

More specifically, the maximum density difference and the total density busyness are used as the feature values, and the area having the small maximum density difference and the total density busyness is set as the background / photo area by the first threshold value and the second threshold value. Is determined. For this reason, the character / halftone area or the background / photograph area is determined for each pixel, so that a large character is not erroneously determined. Therefore,
By appropriately setting the first threshold value and the second threshold value, it is possible to obtain a highly accurate determination result by a simple method.

As a result, when determining the image type of the input image, it is possible to provide an image processing apparatus capable of accurately determining the image type by a simple method and preventing an increase in circuit scale.

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, a third density which is determined in advance as a maximum density difference is determined for a region determined as a background / photo region by the determination region setting means. It is characterized in that the pixel of interest is separated into either a background region or a photograph region by comparing with a threshold value.

According to the above invention, the target pixel is compared with the background area or the photographic area by comparing the maximum density difference with a predetermined third threshold value for the area determined as the background / photograph area. By separating the image into any one of them, it becomes possible to switch the image processing on the result of the area separation, and more excellent image reproduction becomes possible.

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, the total density busyness and the maximum density difference are determined for the area determined as the character / halftone area by the determination area setting means. Is compared with a product of a predetermined fourth threshold value to separate the pixel of interest into either a character area or a halftone area.

According to the above invention, the total density busyness is compared with the product of the maximum density difference and the predetermined fourth threshold value for the area determined as the character / halftone area. By separating the pixel of interest into either a character area or a halftone area, it is possible to switch the image processing for the result of the area separation, and to achieve better image reproduction.

According to the image processing apparatus of the present invention, in the above-described image processing apparatus, the area separating means determines the priority by giving priority to the results of the main scanning direction determining means and the sub-scanning direction determining means. And a signal-by-signal determining means for performing

According to the above-mentioned invention, the signal-specific determination means includes:
The priority is set for the results of the main scanning direction determining unit and the sub-scanning direction determining unit, and the determination is performed. For example, when the hardware such as the size of the determination block serving as the determination area or the resolution of the scanner is changed. , The priority can be changed accordingly.

Therefore, for example, when the judgment result is different between the main scanning direction and the sub-scanning direction, it is possible to take a flexible measure such as adopting the result having the larger amount of information. In addition, since it is possible to select, for example, to remove invalid information deteriorated in the sub-scanning direction in the pre-scan data, it is possible to easily apply the present invention to the document discrimination processing.

According to the image processing apparatus of the present invention, in the above-described image processing apparatus, the area separating means sets a priority order for a signal for each color component with respect to a result of the signal-by-signal determining means to make a determination. It is characterized in that a comprehensive determination means for performing the determination is further provided.

According to the above invention, the comprehensive determination means determines the result of the signal-specific determination means by assigning priorities to the signals for each color component. However, the pixel density value greatly changes depending on the color component signal. For example, it is possible to cope with a color character.

The image processing apparatus according to the present invention is characterized in that, in the above-described image processing apparatus, the area separating means determines a document type.

According to the above invention, the area separating means is applied to the discrimination of the document type. That is, since the area separating unit performs the determination for each scanning direction, the image data in the sub-scanning direction, which is the data read by the pre-scan, is used to determine the image data in the sub-scanning direction, which is the useless information. It is easy to remove the result, and it is possible to extract the determination result of the image data in the main scanning direction, which is effective information, and apply the result to the document determination.

Therefore, it is possible to quickly determine the original by a simple method, and it is possible to perform optimal image processing on the input original image.

According to another aspect of the present invention, there is provided an image forming apparatus including the above-described image processing apparatus.

According to the above invention, in the image forming apparatus,
Since accurate discrimination can be performed by a simple method using the above-described image processing apparatus, a high-quality image can be output. Further, since the configuration is simple, the processing speed is increased, the circuit scale is reduced, and the cost of the image forming apparatus is reduced. Further, by applying the present invention to the determination of the document type, it is possible to provide an image forming apparatus having an excellent user interface.

Therefore, it is possible to provide an image forming apparatus capable of accurately determining the image type by a simple method when determining the image type of the input image and preventing an increase in circuit scale.

According to another aspect of the present invention, there is provided an image processing method for performing an area separation process on input image data into a plurality of areas including a character area, a halftone area, and a photograph area. In the above-described area separation processing, a step of extracting image data in the main scanning direction including a pixel of interest from a block composed of a plurality of pixels extracted from the input image data to obtain a feature amount, and extracting the feature amount from the input image data A step of extracting image data in the sub-scanning direction including the pixel of interest from a block composed of a plurality of pixels to obtain a characteristic amount, while the characteristic amount is obtained from the image data in the main scanning direction and the image data in the sub-scanning direction. These are the maximum density difference, which is the difference between the minimum density value and the maximum density value, and the total density busyness, which is the sum of the absolute values of the density differences between adjacent image data. Based on the first and second threshold values defined in advance when, is characterized by classifying the pixel of interest to any of the text and halftone area or background-photograph area.

According to the above-described invention, the maximum density difference and the maximum density difference in each of the main scanning direction and the sub-scanning direction of the target image are obtained.
The total density busyness, which is the sum of the absolute values of the density differences between adjacent pixels, is calculated.Based on the calculated maximum density difference and the total density busyness, each pixel of the target image is assigned to the background area and the photographic paper area. -It is determined to be a character area or a halftone area.

More specifically, the maximum density difference and the total density busyness are used as the feature values, and the area having the small maximum density difference and the total density busyness is determined by the first threshold value and the second threshold value. Is determined. For this reason, the character / halftone area or the background / photograph area is determined for each pixel, so that a large character is not erroneously determined. Therefore,
By appropriately setting the first threshold value and the second threshold value, it is possible to obtain a highly accurate determination result by a simple method.

Since the determination is made for each scanning direction, the result of the determination of the image data in the sub-scanning direction, which is the useless information, is compared with the deteriorated image data in the sub-scanning direction, which is the data read by the prescan. It is easy to remove, and it is possible to extract the determination result of the image data in the main scanning direction, which is effective information, and apply the result to the document determination.

As a result, when determining the image type of the input image, it is possible to provide an image processing method capable of accurately determining the image type by a simple method and preventing an increase in circuit scale.

Further, according to the image processing method of the present invention, in the above-described image processing method, the maximum density difference is compared with a predetermined third threshold value for an area determined to be a background / photograph area. Thus, the pixel of interest is separated into either a base region or a photograph region.

According to the above invention, by comparing the maximum density difference with the predetermined third threshold value with respect to the area determined to be the background / photograph area, the target pixel is set to the background area or the photo area. By separating the image into any one of them, it becomes possible to switch the image processing on the result of the area separation, and more excellent image reproduction becomes possible.

Further, according to the image processing method of the present invention, in the above-described image processing method, a total density busyness and a maximum density difference are predetermined for an area determined as a character / halftone area. By comparing the product with the threshold of 4,
It is characterized in that the pixel of interest is separated into either a character area or a halftone area.

According to the above invention, the total density busyness is compared with the product of the maximum density difference and the predetermined fourth threshold value for the area determined as the character / halftone area. By separating the pixel of interest into either a character area or a halftone area, it is possible to switch the image processing for the result of the area separation, and to achieve better image reproduction.

Further, the image processing method of the present invention is characterized in that, in the above-described image processing method, a step of determining the classification result in the main scanning direction and the sub-scanning direction by setting a priority order is further provided. And

According to the above invention, the classification results in the main scanning direction and the sub-scanning direction are determined by assigning priorities, so that, for example, the size of the determination block serving as the determination area, the resolution of the scanner, etc. If the hardware is changed, the priority can be changed accordingly.

Therefore, for example, when the judgment result is different between the main scanning direction and the sub-scanning direction, it is possible to take a flexible measure such as adopting a result having a larger amount of information. In addition, since it is possible to select, for example, to remove invalid information deteriorated in the sub-scanning direction in the pre-scan data, it is possible to easily apply the present invention to the document discrimination processing.

[0044]

DESCRIPTION OF THE PREFERRED EMBODIMENTS One embodiment of the present invention will be described below with reference to FIGS.

As shown in FIG. 2, an image forming apparatus such as a digital copying machine using an electrophotographic process according to the present embodiment includes a color image input device 1, an image processing device 10, and a color image output device 2. Have.

The above color image input device 1 is, for example,
It is configured by a scanner unit, and reads a reflected light image from a document as an RGB (R: red, G: green, B: blue) analog signal with a CCD (Charge Coupled Device).

The color image output device 2 is a device that performs predetermined image processing in the image processing device 10 and outputs the result. Note that the above color image output device 2
For example, an output device using an ink jet recording method or a sublimation type recording method can be applied.

The image processing apparatus 10 includes an A / D (analog / digital) converter 11, a shading corrector 1,
2. Area separation processing section 20 as area separation means, input tone correction section 13, color correction section 14, black generation / under color removal section 1
5, a spatial filter processing unit 16, an output gradation correction unit 17, and a gradation reproduction processing unit 18.

In the image processing apparatus 10 described above, the analog signal of the original image read by the color image input device 1 is first converted into a digital signal by the A / D converter 11. Then, the shading correction unit 12 performs shading correction for removing various types of distortion generated in the illumination system, the imaging system, and the imaging system of the color image output device 2. Next, the area separation processing unit 20 separates each pixel into any of a character area, a halftone area, a photograph area, and an undercolor area.
Converts an area identification signal indicating to which area a pixel belongs to an input tone correction unit 13, a color correction unit 14, a black generation / under color removal unit 15, a spatial filter processing unit 16, and a tone reproduction processing unit 18 respectively. The details will be described later.

After the area separation processing in the area separation processing section 20, the input tone correction section 13 removes the background density and performs image quality adjustment processing such as contrast. The color correction unit 14 removes color turbidity based on the spectral characteristics of CMY (C: cyan, M: magenta, Y: yellow) color materials that include unnecessary absorption components in order to achieve faithful color reproduction. Correction processing is performed.

Next, the black generation / under color removal unit 15 generates a black (K) signal from the three CMY color signals after color correction, and generates a K signal obtained by black generation from the original CMY signal. Under color removal processing for generating a new CMY signal by subtraction is performed, and the three CMY color signals are converted into four CMYK color signals.

Next, the spatial filter processing unit 16 performs a spatial filter process using a digital filter, and performs processing so as to prevent blurring and deterioration in graininess of the output image by correcting the spatial frequency characteristics. Then, an output gradation correction unit 17 performs an output gradation correction process of converting a signal such as a density signal into a dot area ratio which is a characteristic value of an image output. Finally, a tone reproduction process, that is, a halftone generation process for dividing the image into pixels so as to reproduce the respective tones is performed.

The image area extracted as a black character or a color character in some cases by the region separation processing unit 20 is:
In order to enhance the reproducibility of black characters or color characters, the enhancement amount of the high frequency in the sharpness enhancement processing in the spatial filter processing unit 16 is increased. At the same time, the halftone generation processing is configured to select binarization or multi-value processing on a high-resolution screen suitable for high-frequency reproduction.

On the other hand, for the area determined to be a halftone dot by the area separation processing section 20, the spatial filter processing section 16 performs a low-pass filtering process for removing an input halftone dot component. At the same time, in the halftone generation processing, binarization or multi-value processing is performed on a screen that emphasizes tone reproducibility. The image data subjected to each of the above-described processes is
The image data is temporarily stored in a storage unit (not shown), read out at a predetermined timing, and input to the color image output device 2. The above processing is performed by a CPU (Central Processing Unit).

Next, the pixel discriminating process in the segmentation processing section 20, which is a feature point in the present embodiment, will be described in detail. Note that the segmentation processing unit 20 performs this processing using RGB image input data or a signal converted into CMY which is a complementary color of RGB. Then, based on the result of the area separation processing, the input gradation correction processing, the color correction processing, the black generation /
Processing such as undercolor removal processing, spatial filter processing, and gradation reproduction processing (halftone generation processing) is switched.

In the following description, a case will be described in which processing is performed using a signal obtained by inverting a complementary color to a CMY signal by a signal converter 21 described later.

First, as shown in FIG. 3, the area separation processing section 20 converts the RGB reflectance signal into a density signal and converts the RGB density signal into a complementary CMY signal from the RGB density signal. With respect to the obtained signal, for example, a determination block storage unit 22 that stores image data of a block including a plurality of n × m pixels such as 5 × 15, and for each image data of the determination block storage unit 22, A main scanning direction determining unit 23 as a main scanning direction determining unit that extracts image data in a main scanning direction including a pixel of interest, that is, a direction orthogonal to a scanning direction of the scanner and performs a region separation process;
A sub-scanning direction determining unit 24 that extracts image data in the sub-scanning direction including the pixel of interest, that is, the same direction as the scanning direction of the scanner, and performs a segmentation process;
Signal-based determination as signal-based determination means for determining each color signal based on the area separation results of the main scanning direction determining unit 23 and the sub-scanning direction determining unit 24 and the priority order of the results in the main scanning direction and the sub-scanning direction Unit 25 and final determination of pixels based on the result of the signal-specific determination unit 25 for each color signal, that is, a comprehensive determination unit as a comprehensive determination unit that determines a signal CMY including a plurality of color components by giving priority to the determination. 26.

The priority order is determined in advance for the area identification signals, which are the signals of the respective pixels, entering the above-mentioned signal-specific determination section 25 and the comprehensive determination section 26, and the signal-specific determination section 2 for each color is set.
... If the pixel determination results entering are different, the determination is made according to the priority order. For this priority,
Since the reliability of the determination result changes depending on the size and resolution of the image data in the main scanning direction and the sub-scanning direction stored in the determination block storage unit 22 and the threshold used in the area separation processing, the reliability of the determination result is determined based on the reliability of the determination result. It is desirable to set priorities. The size of the image data changes because the data in the main scanning direction and the sub-scanning direction, that is, the number of pixels differs depending on the size of the block stored in the determination block storage unit 22. The setting of the threshold will be described later.

Next, the specific configuration of the main scanning direction determining section 23 and the sub scanning direction determining section 24 in which each signal is divided into areas including the pixel of interest in the main scanning direction and the sub-scanning direction will be described. 1 will be described. That is, the main scanning direction determining unit 23 and the sub-scanning direction determining unit 24
Each has the same configuration. However, as shown in FIG. 4, the pixels used in the main scanning direction determination unit 23 are, for example, 5 × 15 and other n × m determination blocks including the pixel of interest stored in the determination block storage unit 22 in the main scanning direction. On the other hand, the pixels used in the sub-scanning direction determination unit 24 are pixels only in the sub-scanning direction of the n × m determination block including the target pixel.

First, as shown in FIG. 1, the main scanning direction judging section 23 and the sub-scanning direction judging section 24 include a minimum density value calculating section 31 for calculating a minimum density value and a maximum density value for calculating a maximum density value. Value calculation unit 32 and the minimum density value calculation unit 31
And a maximum density difference calculation unit 33 as a maximum density difference calculation unit that calculates a maximum density difference using the minimum density value and the maximum density value calculated by the maximum density value calculation unit 32; The total density busyness calculating section 34 as a total density busyness calculating means for calculating the sum of the absolute values, and the maximum density difference calculated by the maximum density difference calculating section 33 and the total density busyness calculating section 34 A determination area setting unit 35 as determination area setting means for separating the background density / printing paper (photograph) area and the character area / halftone area by comparing the total sum density busyness with each threshold value; A character / halftone determining unit 36 that determines whether a pixel of interest is a character or a halftone dot for a pixel determined to be a character / halftone region by the determination region setting unit 35, and a base region / printing in the determination region setting unit 35. Discriminated as paper area Target pixel to the pixel has a base-paper determination section 37 determines whether the base region or the photographic paper region.

The determination area setting section 35 calculates the maximum density difference of the pixel of interest by the
A maximum density difference threshold value setting unit 41 for setting a maximum density difference threshold value as a first threshold value for separating into a background area / photographic paper (photograph) area and a character area / halftone area; Sum for setting a total density busyness threshold value as a second threshold value for separating the result calculated by the density busyness calculation unit 34 into a background area / printing paper area and a character area / halftone dot area And a density busyness threshold value setting unit 42.

Further, the character / halftone judging section 36 determines whether the pixel of interest is a character or a halftone dot.
While a character / halftone judgment threshold value setting unit 43 for setting a character / halftone judgment threshold value as a threshold value of
The photographic paper determination unit 37 includes a base / photographic paper determination threshold value setting unit 44 for setting a base / photographic paper determination threshold value as a third threshold value for determining whether the target pixel is a background or photographic paper. Have.

The operation of the area separation processing for each of the main scanning direction determining section 23 and the sub-scanning direction determining section 24 having the above configuration will be described.
This will be described based on the flowchart shown in FIG. In addition,
In the description, an n × m block including the target pixel will be described. In addition, reference numerals indicating steps are described as “S”.

As shown in the figure, first, a minimum density value in an nxm block including a target pixel is calculated (S1), and a maximum density value is calculated (S2). Next, a maximum density difference is calculated using the calculated minimum density value and maximum density value (S3), and further, a sum of absolute values of density differences of adjacent pixels, that is, a total density busyness is calculated (S4). .

Next, the calculated maximum density difference is compared with the maximum density difference threshold value, and the calculated total density busyness is compared with the total density busyness threshold value (S5). And
When it is determined that the maximum density difference is smaller than the maximum density difference threshold value and that the total density busyness is smaller than the total density busyness threshold value, it is determined that the pixel of interest is the background / photographic paper area (S6). . On the other hand, if the above condition is not satisfied in S5, it is determined that the area is a character / halftone area (S7).

In the background and photographic paper area shown in S6, the calculated maximum density difference is compared with the background and photographic paper determination threshold (S8). If the maximum density difference is larger, the area is determined to be a photographic paper area (S1).
0).

On the other hand, in the character / halftone area shown in S7, the calculated total density busyness is compared with a value obtained by multiplying the maximum density difference by a character / halftone determination threshold (S1).
1) If the total density busyness is smaller, it is determined to be a character area (S12), and if the total density busyness is larger, it is determined to be a halftone area (S13).

FIGS. 6A to 6D show examples of pixel density distributions in characters, halftone dots, photographic paper photographs, and background areas.
It will be described based on. A distribution diagram based on the maximum density difference and the total density busyness for each region will be described with reference to FIG. In the figure, the area where the maximum density difference is equal to or less than the total density busyness indicates an area where the pixel does not exist without the total density busyness not being equal to or less than the maximum density difference.

First, as shown in FIG. 6 (a), the density distribution of the background area usually has a very small density change, so that both the maximum density difference and the total density busyness are very small. Are distributed. Therefore, when the maximum density difference is smaller than the background / print paper determination threshold value for the pixel determined as the background / print paper area, it is possible to determine that the pixel is a background pixel.

Next, the density distribution of the photographic paper area is shown in FIG.
As shown in (b), normally, the density changes smoothly, and the maximum density difference and the total density busyness are both small and slightly larger than the background area. are doing. Therefore, when the maximum density difference is larger than the background / printing paper determination threshold value for the pixel determined to be the background area / printing paper area, it can be determined that the pixel is the printing paper area.

The density distribution of the halftone dot area is shown in FIG.
As shown in (1), although the maximum density difference varies depending on the halftone dots, the ratio of the total density busyness to the maximum density difference increases because the total density busyness has a density change corresponding to the number of halftone dots. Therefore, the distribution is as shown in a region D shown in FIG. Therefore, when the total density busyness is larger than the product of the maximum density difference and the character / halftone determination threshold value, it is possible to determine that the pixel is a halftone pixel.

Finally, the density distribution of the character area is shown in FIG.
As shown in (d), although the maximum density difference is large and the total density busyness is also large, the total density busyness is smaller than the halftone dot region because the density change is smaller than in the halftone dot region. In particular, since the ratio of the total density busyness to the maximum density difference becomes small, the distribution becomes a region C shown in FIG. Therefore, when the total density busyness is smaller than the product of the maximum density difference and the character / halftone determination threshold value in a pixel determined to be a character / halftone area, it can be determined to be a character pixel. is there.

As described above, the maximum density difference and the total density busyness of the background area and the photographic paper photographic area are smaller than those of the character area and the halftone dot area. Therefore, by comparing the maximum density difference with the maximum density difference threshold value and comparing the total density busyness with the total density busyness threshold value, the target pixel is set to the background as shown in S5 to S7 of the flowchart shown in FIG. -It becomes possible to separate the photographic paper area from the character / halftone area.

In each of the threshold values set above,
By making the adjustment arbitrarily, a wider range of processing can be performed. For these threshold values, a plurality of expected values are stored in advance in a storage medium such as a ROM (Read Only Memory), and values stored in storage means such as a memory can be set by a switch or the like as necessary. You should do so.

According to the above-described method, the area separation processing section 20 performs the area separation processing, and based on the area separation result, the subsequent input tone correction processing, color correction processing, black generation / under color removal processing -Space filter processing, gradation reproduction processing (halftone generation processing), etc. are switched.

For example, when it is determined that a certain pixel of the input image data is a background area, in the input tone correction processing and the tone reproduction processing, the background is removed, the highlight is removed more, or the density is reduced. Or a correction curve that keeps the constant.

If the input image data is determined to be a character area, a correction curve for increasing the contrast is used in the input tone correction processing and the tone reproduction processing. Further, the color correction unit 14 performs a color correction process for clarifying saturation of color characters, and sets a larger amount of black generation in black generation / under color removal processing for black characters. . In the spatial filter processing, switching of parameters, such as setting a filter coefficient so as to emphasize an edge of a character and weaken the smoothing processing, is performed.

Further, when it is determined that the input image data is the photographic paper area, in the input gradation correction processing and the gradation reproduction processing, a correction curve that emphasizes highlights and a correction curve with increased gradation is used. Or used. The color correction unit 14
Then, color correction processing that emphasizes gradation is performed, and black generation /
In the under color removal processing, the amount of black generation is set to be small. In the spatial filter processing, switching of parameters such as setting of filter coefficients is performed so as to weaken the edge enhancement and weaken the smoothing processing.

Similarly, when it is determined that the input image data is a halftone area, in the input tone correction processing and the tone reproduction processing, emphasis is placed on highlights, and a correction curve with increased tone is used. Or used. Further, the color correction unit 14 performs a color correction process that emphasizes the gradation, and performs processes such as reducing black generation in the black generation / under color removal process. Further, in the interrogation filter processing, the emphasis of the edge is weakened, and a low-pass filter processing or the like for removing a halftone dot component is performed.

By the way, the above-described area separation processing method
The present invention can be applied to a method of determining the type of a document.

Here, in general, when determining the type of a document, low-resolution data that has been pre-scanned is often used, but in the present embodiment, information in the sub-scanning direction where the resolution is degraded is used. Invalidate, perform pixel determination using the determination result in the main scanning direction, count the number of determined pixels, and compare them with threshold values for a background area, a photographic paper area, a halftone area, and a character area prepared in advance. Thus, the type of the entire document is determined. Thereby, it is possible to prevent the accuracy from being deteriorated. The reason why the pre-scanned data has a low resolution is that the data in the sub-scanning direction is deteriorated when performing the pre-scan because the scan speed is higher than during the main scan.

More specifically, if the count of the number of pixels determined to be characters is more than a certain percentage (threshold) of the total number of pixels read from the input image (document), the document is a character document. .

The threshold values for the background region, photographic paper region, halftone dot region, and character region also vary greatly depending on the threshold value used in the region separation process. If, for example, both the character area and the halftone area satisfy the respective thresholds, the input image (document) can be determined to be a character / halftone image.

Further, since it is not necessary to make a determination for all the pixels in making the determination, the threshold value used in making the determination is made stricter, and the pixels that do not satisfy the threshold are not counted by using other pixels. By doing so, it is possible to further improve the accuracy. Needless to say, the threshold value of the count pixel number of each determination result is set to a low value accordingly.

In each process after the document type determination, when it is determined that the respective regions do not coexist, the process is the same as the above-described region separation process. On the other hand, when it is determined that the plurality of regions coexist, the respective processes are performed. The intermediate parameters of the area processing may be used, and the parameters of the area processing not determined in the document type determination processing may not be used.

For example, when it is determined that the input image is a character document, in the area separation processing, the area where the area is separated as a character and a line drawing is valid, and it is determined that the image is a continuous tone such as a halftone dot and photographic paper. However, for example, even if the document is a character document, it may be erroneously determined depending on the type of the document.

Then, in the input tone correction process and the tone reproduction process based on the result of the region separation process, a correction curve that removes a large amount of highlights and increases the contrast is used.

For color characters, color correction processing is performed with emphasis on saturation, while for black characters, the black generation amount is set to be relatively large in the black generation / under color removal processing. Further, for characters, switching of parameters such as setting of filter coefficients so as to emphasize edges by spatial filter processing and weaken smoothing processing is performed.

When it is determined that the input image is a text / photographic paper photo original, in each process, a process using intermediate parameters between the text original process and the photographic paper photo original process is performed. In the area separation processing, a part where the area is separated as a character, line drawing or photographic paper is valid, and a part where the area is separated such as a halftone dot is erroneously determined depending on the type of the original even if it is a character / photographic paper original, for example. In some cases, this is considered to be erroneous separation and is not reflected.

In the input tone correction process and the tone reproduction process, depending on whether a text document or a photographic paper photo document is to be emphasized, highlighting is performed by using an intermediate parameter between the photographic paper photo document process and the text document process. Removal and adjustment of contrast are performed, and color correction processing is performed so that the balance of saturation and gradation is not excessive. On the other hand, in the black generation / under color removal processing, the black generation amount may be adjusted so as not to affect the photographic paper photographic image.

As described above, according to the image processing apparatus 10 and the image processing method of the present embodiment, the area where the input image data read from the document is separated into a plurality of areas including the character area, the halftone area, and the photograph area At least a separation processing unit 20 is provided.

The area separation processing section 20 includes a decision block storage section 22 for storing a block composed of a plurality of pixels extracted from the input image data, and a plurality of pixels stored in the decision block storage section 22. The image data in the main scanning direction including the pixel of interest is extracted from the block of, and the feature amount is obtained.
The main scanning direction determining unit 23 that determines which of the photographic regions belongs to, and the image data in the sub-scanning direction including the target pixel is extracted from the block including a plurality of pixels stored in the determination block storage unit 22. And a sub-scanning direction determining unit 24 for determining whether the pixel of interest belongs to a character / halftone dot region or a background / photograph region.

The main scanning direction judging section 23 and the sub-scanning direction judging section 24 use the minimum density value and the maximum density value obtained from the respective image data in the main scanning direction or the sub-scanning direction to calculate the maximum value. A maximum density difference calculating section 33 for calculating the density difference, a total density busyness calculating section 34 for calculating the total density busyness by calculating the sum of the absolute values of the density differences between adjacent image data, The maximum density difference calculated by the calculation unit 33 and the total density busyness calculated by the total density busyness calculation unit 34 are used as feature quantities, and these feature quantities and a predetermined maximum density difference threshold and total density busyness are determined. A determination area setting unit 35 for classifying a pixel of interest into a character / halftone area or a background / photograph area based on a threshold value
Are provided.

In the image processing apparatus 10, as the image processing method, image data in the main scanning direction including the target pixel is extracted from a block composed of a plurality of pixels extracted from the input image data at the time of region separation processing. And obtaining a feature amount by extracting image data in the sub-scanning direction including a pixel of interest from a block composed of a plurality of pixels extracted from the input image data. The feature amount is a sum total of a maximum density difference that is a difference between a minimum density value and a maximum density value obtained from image data in each of the main scanning direction and the sub-scanning direction, and a sum of absolute values of density differences of adjacent image data. Density busyness, based on these feature amounts and a predetermined maximum density difference threshold and total density busyness threshold, sets the pixel of interest to a character / halftone area or a background / photograph area. It is classified as either.

That is, in each of the main scanning direction and the sub-scanning direction of the target image, the maximum density difference and the total density busyness which is the sum of the absolute values of the density differences of adjacent pixels are calculated. Based on the maximum density difference and the total density busyness, each pixel of the target image is determined to be a character / halftone area or a background / photograph area.

More specifically, the maximum density difference and the total density busyness threshold are used as the feature amount, and the area having the small maximum density difference and the total density busyness is determined based on the maximum density difference threshold and the total density busyness threshold. It is determined as an area. For this reason, the character / halftone area or the background / photograph area is determined for each pixel, so that a large character is not erroneously determined.
Therefore, by appropriately setting the maximum density difference threshold value and the total density busyness threshold value, it is possible to obtain a highly accurate determination result by a simple method.

As a result, it is possible to provide an image processing apparatus 10 and an image processing method capable of accurately determining an image type by a simple method when determining an image type of an input image and preventing an increase in circuit scale. it can.

In the image processing apparatus 10 and the image processing method according to the present embodiment, the determination
For a region determined to be a photographic region, the target pixel is separated into either a background region or a photographic region by comparing the maximum density difference with a predetermined background / photographic paper determination threshold value.

For this reason, by comparing the maximum density difference with a predetermined background / photographic paper determination threshold value for an area determined to be a background / photograph area, the target pixel is set to either the background area or the photograph area. By performing the separation, it is possible to switch the image processing with respect to the region separation result, and more favorable image reproduction is possible.

Further, in the image processing apparatus 10 and the image processing method according to the present embodiment, the character / character
For an area determined to be a halftone dot area, the target pixel is set to a character area or halftone dot by comparing the total density busyness with the product of the maximum density difference and a predetermined character / halftone determination threshold. Separate into any of the regions.

For this reason, by comparing the total density busyness with the product of the maximum density difference and a predetermined character / halftone judgment threshold value for the area determined to be a character / halftone area, By separating a pixel into either a character area or a halftone area, it is possible to switch the image processing for the area separation result, and more favorable image reproduction is possible.

In the image processing apparatus 10 and the image processing method according to the present embodiment, the segmentation processing section 20 assigns a priority to the results of the main scanning direction determination section 23 and the sub-scanning direction determination section 24. There is further provided a signal-specific determination unit 25 for providing a determination.

For this reason, the signal-by-signal determining section 25 determines the results of the main scanning direction determining section 23 and the sub-scanning direction determining section 24 by assigning priorities to the results. If the hardware such as the size of the scanner or the resolution of the scanner is changed, the priority can be changed accordingly.

Therefore, for example, when the judgment result is different between the main scanning direction and the sub-scanning direction, it is possible to take a flexible measure such as adopting a result having a larger information amount. Further, since it is possible to select, for example, to remove invalid information that has deteriorated in the sub-scanning direction in the pre-scan data, it is possible to easily apply the present invention to the document discrimination processing.

In the image processing apparatus 10 and the image processing method according to the present embodiment, the segmentation processing section 20 assigns a priority to the signal for each color component to the result of the signal-specific determination section 25. An overall judgment unit 26 for making a judgment is further provided.

For this reason, the comprehensive judgment section 26 sets the priority of the signal for each color component with respect to the result of the signal-specific judgment section 25 and makes a judgment. For example, it is possible to cope with, for example, a color character in which a pixel density value largely changes according to a color component signal. For example, in the case of a color character, depending on the color component, the character may not be determined as a character region but may be determined as a base region. Specifically, in the case of a yellow character on a white background, the signal is determined only by the yellow (Y) component signal-specific determination unit 25, and the cyan component (C) and magenta component (M) signal-specific determination units 25. In No. 25, it does not include a yellow component, and thus is determined to be a base. Therefore, in this case, if at least one of the plurality of color components is determined to be a character, it is finally determined to be a character.

Further, in the image processing apparatus 10 and the image processing method according to the present embodiment, the area separation processing section 20 is applied to the determination of the document type. That is, since the segmentation processing unit 20 performs the determination for each scanning direction, the image data in the sub-scanning direction, which is the useless information, Is easy to remove, and it is possible to extract the judgment result of the image data in the main scanning direction, which is effective information, and apply the result to the original discrimination. Therefore, it is possible to quickly determine a document by a simple method, and to perform optimal image processing on an input document image.

Further, the image forming apparatus of the present embodiment has an image processing device 10. For this reason, since the image forming apparatus can perform accurate discrimination by a simple method using the image processing apparatus 10, a high-quality image can be output. Further, since the configuration is simple, the processing speed is increased, the circuit scale is reduced, and the cost of the image forming apparatus is reduced. Further, by applying the present invention to the determination of the document type, an image forming apparatus having an excellent user interface can be provided.

Therefore, there is provided an image forming apparatus capable of accurately determining an image type by a simple method regardless of a black-and-white document or a color document when determining the image type of an input image, thereby preventing an increase in circuit scale. can do.

[0110]

As described above, according to the image processing apparatus of the present invention, the area separating means stores the block composed of a plurality of pixels extracted from the input image data, The image data in the main scanning direction including the target pixel is extracted from the block composed of a plurality of pixels stored in the section, and the feature amount is obtained. A main scanning direction determining unit that determines whether the image data belongs to a plurality of pixels stored in the determination block storage unit. Sub-scanning direction determining means for determining whether a pixel belongs to a character / halftone dot area or a background / photograph area; and the main scanning direction determining means and the sub-scanning direction determining means, Maximum density difference calculating means for calculating the maximum density difference using the minimum density value and the maximum density value obtained from the respective image data in the main scanning direction or the sub scanning direction, and the absolute value of the density difference between adjacent image data. Total density busyness calculating means for calculating the total density busyness by calculating the sum; and the maximum density difference calculated by the maximum density difference calculating means and the total density busyness calculated by the total density busyness calculating means. A determination area setting means for classifying a pixel of interest into a character / halftone area or a background / photograph area based on the degree and a feature amount and a predetermined first threshold and a second threshold. Are provided.

Therefore, the maximum density difference and the total density busyness are used as the feature amounts, and the area where the maximum density difference and the total density busyness are small is determined by the first threshold value and the second threshold value.
Since it is determined as a photo area and a character / halftone area or a base / photo area is determined for each pixel, erroneous determination is not performed even for large characters. Therefore, by appropriately setting the first threshold value and the second threshold value, it is possible to obtain an accurate determination result by a simple method.

As a result, when the image type of the input image is determined, it is possible to provide an image processing apparatus capable of accurately determining the image type by a simple method and preventing an increase in circuit scale. .

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, a third density predetermined as a maximum density difference is determined for an area determined as a background / photograph area by the determination area setting means. By comparing the target pixel with a threshold value, the pixel of interest is separated into a base region and a photograph region.

Therefore, by separating the pixel of interest into either a background region or a photographic region, it is possible to switch the image processing for the region separation result, and it is possible to achieve an effect of enabling better image reproduction. .

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, the total density busyness and the maximum density difference are determined for an area determined as a character / halftone area by the determination area setting means. The target pixel is separated into either a character region or a halftone dot region by comparing the product of the target pixel with a predetermined fourth threshold value.

Therefore, by separating the pixel of interest into either a character area or a halftone area, it becomes possible to switch the image processing for the result of the area separation, and it is possible to obtain a better image reproduction effect. Play.

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, the area separating means determines the priority by giving a priority to the results of the main scanning direction determining means and the sub-scanning direction determining means. Is further provided.

Therefore, when hardware such as the size of a determination block serving as a determination area and the resolution of a scanner is changed, the priority can be changed accordingly.

Therefore, for example, when the determination result is different between the main scanning direction and the sub-scanning direction, it is possible to take a flexible measure such as adopting a result having a larger information amount. Further, since it is possible to select, for example, to remove invalid information deteriorated in the sub-scanning direction in the pre-scan data, it is possible to easily apply the present invention to the document discrimination processing.

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, the region separating means sets a priority order for a signal for each color component with respect to a result of the signal-by-signal determining means to make a determination. The apparatus further includes comprehensive determination means for performing the determination.

Therefore, the comprehensive determination means determines the result of the signal-by-signal determination means by assigning priorities to the signals for each color component, so that even if the pixels are the same as in a color original, The pixel density value greatly changes depending on the component signal. For example, it is possible to cope with color characters.

Further, according to the image processing apparatus of the present invention, in the above-described image processing apparatus, the area separating means determines a document type.

Therefore, since the area separating means makes a determination for each scanning direction, the degraded image data in the sub-scanning direction, which is data read by pre-scanning, is not used. It is easy to remove the determination result of the image data, and it is possible to extract the determination result of the image data in the main scanning direction, which is effective information, and apply the result to the document determination.

Therefore, it is possible to quickly determine a document by a simple method, and it is possible to perform an optimum image processing on an input document image.

Further, an image forming apparatus according to the present invention includes the above-described image processing apparatus in order to solve the above problems.

Therefore, the image forming apparatus can perform accurate discrimination by a simple method using the above-described image processing apparatus, so that a high-quality image can be output. In addition, the processing speed is fast because of the simple configuration,
The circuit scale is also reduced, and the cost of the image forming apparatus is reduced. Further, by applying the present invention to the determination of the document type, an image forming apparatus having an excellent user interface can be provided.

Accordingly, when the image type of the input image is determined, the image type can be accurately determined by a simple method and an image forming apparatus capable of preventing an increase in circuit scale can be provided.

Further, according to the image processing method of the present invention, as described above, the image data in the main scanning direction including the target pixel is extracted from the block composed of a plurality of pixels extracted from the input image data at the time of the region separation processing. Extracting the image data in the sub-scanning direction including the pixel of interest from a block composed of a plurality of pixels extracted from the input image data, and obtaining the characteristic data. The feature amount is a sum of a maximum density difference which is a difference between a minimum density value and a maximum density value obtained from image data in the main scanning direction and the sub-scanning direction, and an absolute value of a density difference between adjacent image data. A method for classifying a pixel of interest into a character / halftone area or a background / photograph area based on these feature amounts and predetermined first and second threshold values. It is.

Therefore, the maximum density difference and the total density busyness are used as the feature amounts, and the area having the small maximum density difference and the total density busyness is set as the background by the first threshold value and the second threshold value.
It is determined as a photograph area. For this reason, the character / halftone area or the background / photograph area is determined for each pixel, so that a large character is not erroneously determined. Therefore, by appropriately setting the first threshold and the second threshold,
It is possible to obtain an accurate determination result by a simple method.

Since the determination is performed for each scanning direction, the determination result of the image data in the sub-scanning direction, which is useless information, is compared with the deteriorated image data in the sub-scanning direction, which is data read by pre-scanning. It is easy to remove, and it is possible to extract the determination result of the image data in the main scanning direction, which is effective information, and apply the result to the document determination.

As a result, when determining the image type of the input image, it is possible to provide an image processing method capable of accurately determining the image type by a simple method and preventing an increase in circuit scale. .

Further, according to the image processing method of the present invention, in the above-described image processing method, the maximum density difference is compared with a predetermined third threshold value for an area determined as a background / photograph area. This is a method of separating the pixel of interest into either a background region or a photograph region.

Therefore, by separating the pixel of interest into either the background region or the photographic region, it is possible to switch the image processing for the region separation result, and it is possible to obtain an effect of enabling better image reproduction. .

Further, according to the image processing method of the present invention, in the above-described image processing method, a total density busyness and a maximum density difference are determined in advance for an area determined to be a character / halftone area. By comparing the product with the threshold of 4,
This is a method of separating a target pixel into either a character area or a halftone area.

Therefore, by separating the pixel of interest into either a character area or a halftone area, it is possible to switch the image processing for the result of the area separation, and it is possible to achieve a better image reproduction. Play.

Further, the image processing method of the present invention is a method according to the above-described image processing method, further comprising the step of determining the classification results in the main scanning direction and the sub-scanning direction by assigning priorities and making a determination. .

Therefore, priorities are set for the classification results in the main scanning direction and the sub-scanning direction, and the judgment is made. Therefore, the hardware such as the size of the judgment block serving as the judgment area and the resolution of the scanner is changed. In such a case, the priority can be changed accordingly.

Therefore, for example, when the judgment result is different between the main scanning direction and the sub-scanning direction, it is possible to take a flexible measure such as adopting a result having a larger amount of information. Further, since it is possible to select, for example, to remove invalid information deteriorated in the sub-scanning direction in the pre-scan data, it is possible to easily apply the present invention to the document discrimination processing.

[Brief description of the drawings]

FIG. 1 illustrates an embodiment of an image processing apparatus according to the present invention, and is a block diagram illustrating a configuration of a main scanning direction determination unit and a sub-scanning direction determination unit in a region separation processing unit.

FIG. 2 is a block diagram illustrating an overall configuration of an image forming apparatus including the image processing apparatus.

FIG. 3 is a block diagram illustrating a configuration of a region separation processing unit in the image processing apparatus.

FIG. 4 is an explanatory diagram showing block settings of a region separation process in the image processing apparatus.

FIG. 5 is a flowchart illustrating an area separation processing method in the image processing apparatus.

6A is an explanatory diagram illustrating a density distribution in a background region, FIG. 6B is an explanatory diagram illustrating a density distribution in a photographic paper region, FIG. 6C is an explanatory diagram illustrating a density distribution in a halftone dot region,
(D) is an explanatory view showing a density distribution in a character area.

FIG. 7 is an explanatory diagram showing distributions of a maximum density difference and a total density busyness in each of a base region, a photographic paper region, a halftone dot region, and a character region.

[Explanation of symbols]

REFERENCE SIGNS LIST 1 color image input device 2 color image output device 10 image processing device 20 region separation processing unit (region separation unit) 21 signal conversion unit 22 determination block storage unit 23 main scanning direction determination unit (main scanning direction determination unit) 24 sub-scanning direction Judgment unit (sub-scanning direction judgment unit) 25 Judgment unit for each signal (judgment unit for each signal) 26 Comprehensive judgment unit (comprehensive judgment unit) 31 Minimum density value calculation unit 32 Maximum density value calculation unit 33 Maximum density difference calculation unit (Maximum density) Difference calculation means) 34 Total density busyness calculation unit (Total density busyness calculation means) 35 Judgment area setting unit (Judgment area setting means) 36 Character / halftone dot judgment unit 37 Base / photographic paper judgment unit 41 Maximum density difference threshold setting Unit 42 Total density busyness threshold setting unit 43 Character / halftone judgment threshold setting unit 44 Base / photographic paper judgment threshold setting unit

 ──────────────────────────────────────────────────続 き Continued on the front page F term (reference) 5C077 LL17 MP06 MP08 PP27 PP33 PP38 PP43 PP47 PP48 PP65 PP68 PQ08 PQ20 RR11 TT06 5C079 LA06 MA02 MA11 NA01 NA09 NA27 NA29 5L096 AA02 AA03 BA07 BA17 BA18 FA14 FA43 FA44 FA45 FA46 GA06

Claims (11)

[Claims] 1. An image processing apparatus comprising at least an area separating means for separating input image data read from a document into a plurality of areas including a character area, a halftone area, and a photograph area, wherein the area separating means comprises: A determination block storage unit that stores a block composed of a plurality of pixels extracted from image data; and a main scanning direction image data including a pixel of interest from a block composed of a plurality of pixels stored in the determination block storage unit. And a main scanning direction determining means for determining whether the pixel of interest belongs to a character / halftone dot region or a background / photograph region, and a plurality of pixels stored in the determination block storage unit. The image data in the sub-scanning direction including the pixel of interest is extracted from the block of pixels to obtain a feature amount. A sub-scanning direction determining unit that determines whether the sub-scanning direction belongs to the shift region.
A maximum density difference calculating means for calculating a maximum density difference using a minimum density value and a maximum density value obtained from respective image data in the main scanning direction or the sub-scanning direction; and an absolute value of the density difference between adjacent image data. Total density busyness calculating means for calculating the total density busyness by calculating the sum of the values; and the maximum density difference calculated by the maximum density difference calculating means and the sum calculated by the total density busyness calculating means. A determination area for classifying a pixel of interest into a character / halftone area or a background / photograph area based on the density busyness as a feature amount and a predetermined first and second threshold value based on these feature amounts. An image processing apparatus, comprising: a setting unit. 2. An area determined as a background / photo area by the determination area setting means is compared with a maximum density difference and a predetermined third threshold value to determine whether a pixel of interest is a background area or a photo area. 2. The image processing apparatus according to claim 1, wherein the image processing apparatus is separated into one of the following. 3. The method according to claim 1, wherein the determination unit sets a total density busyness and a product of a maximum density difference and a predetermined fourth threshold value for an area determined as a character / halftone area by the determination area setting unit. 3. The image processing apparatus according to claim 1, wherein the pixel of interest is separated into either a character area or a halftone area. 4. The area separating means further comprises a signal-by-signal determining means for determining a result of the main scanning direction determining means and the sub-scanning direction determining means by giving a priority. The image processing device according to claim 1. 5. The apparatus according to claim 1, wherein said area separating means further comprises comprehensive judgment means for judging the result of said signal-by-signal judgment means by assigning priorities to signals for each color component. Item 5. The image processing device according to Item 4. 6. The image processing apparatus according to claim 1, wherein the area separating unit determines a document type. 7. An image forming apparatus comprising the image processing apparatus according to claim 1. Description: 8. An image processing method for performing a region separation process on input image data into a plurality of regions including a character region, a halftone dot region, and a photograph region, wherein a plurality of pixels extracted from the input image data are included in the region separation process. Extracting the image data in the main scanning direction including the pixel of interest from the block consisting of: and calculating the feature amount; and extracting the image data in the sub-scanning direction including the pixel of interest from the block consisting of a plurality of pixels extracted from the input image data. Extracting the image data and calculating the characteristic amount. The characteristic amount is a maximum density which is a difference between a minimum density value and a maximum density value obtained from the image data in the main scanning direction and the sub-scanning direction. And the total density busyness, which is the sum of the absolute values of the differences and the density differences between adjacent image data, based on these feature amounts and predetermined first and second thresholds. , The pixel of interest text and halftone dot area or base,
An image processing method characterized in that the image is classified into any one of photo regions. 9. For a region determined to be a background / photograph region, the pixel of interest is separated into either a background region or a photograph region by comparing the maximum density difference with a predetermined third threshold value. The image processing method according to claim 8, wherein the image processing is performed. 10. For an area determined to be a character / halftone area, the target pixel is determined by comparing the total density busyness with the product of the maximum density difference and a predetermined fourth threshold value. 9. The image processing method according to claim 8, wherein the image is separated into one of a character area and a halftone area. 11. The image processing method according to claim 8, further comprising the step of giving a priority to the classification results in the main scanning direction and the sub-scanning direction and making a determination.