JP3834484B2 - Image processing method, image processing apparatus, image forming apparatus, and computer-readable recording medium - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image processing method and an image processing apparatus for performing an area separation process for separating input image data into a plurality of areas including a character area and a photograph area, and more particularly to an image processing method and an image processing apparatus for separating color characters with high accuracy. The present invention also relates to an image forming apparatus and a computer-readable recording medium.
[0002]
[Prior art]
Currently, when reproducing input image data read from a document with mixed characters and photographs in an image processing apparatus such as a digital copying machine, areas such as character areas and photograph areas are identified by a process called area separation processing. The image quality is improved by performing processing suitable for various areas.
[0003]
In this region separation process, when a character region is identified, a method of detecting a portion showing a steep density change as a character edge region is generally used. For example, the density difference between the target pixel and its surrounding pixels is obtained, and if the value of the density difference is larger than a predetermined threshold, it is determined that the area is a character edge region. Examples include a method of detecting a character edge region by thresholding the result, and a method of detecting a character edge region by thresholding a maximum density difference in a local region.
[0004]
Also, the detected character edge area is determined as chromatic or achromatic, and if it is chromatic, it is suitable as a color character area, while if it is achromatic, it is suitable as a black character area. The image quality of the character area is improved by performing the above process. For example, after emphasizing filter processing for color character areas, halftone processing emphasizing resolving power is performed, and for black character regions, after increasing black amount and further emphasizing filtering, emphasis is placed on resolving power The process of performing the halftone process is generally performed.
[0005]
As the above technique, for example, an image processing apparatus described in Japanese Patent Laid-Open No. Hei 3-64263 performs image processing for switching processing contents such as color correction / black generation, spatial filter, halftone, etc., according to a character edge determination result and a color determination result. Presenting the device. Further, as a method of detecting a character edge, there is a method of detecting a character edge pixel by obtaining a density change in the vicinity of a pixel of interest by referring only to a G signal among RGB signals of an input image and thresholding the value. It is shown.
[0006]
[Problems to be solved by the invention]
When a method such as the image processing apparatus described in Japanese Patent Laid-Open No. 3-64263 is used, when character edges are detected, edge detection is performed using the same threshold value for both color characters and black characters. .
[0007]
In this prior art, when a color character edge is detected, only a very low value of the density difference is often obtained depending on the combination of the background color and the character color.
[0008]
FIG. 7 is an example of a document 100 that detects edge areas of color characters, and FIG. 8 is a diagram illustrating the density of a background 101 and characters 102 of the document 100. FIG. 9 is a diagram showing a change in density for each pixel in the x direction in the broken line portion 103. In the case of such a combination of the colors of the background 101 and the character 102, even if the color difference when viewed by mixing the three colors of CMY is large, when the color components are decomposed into each color component signal, a steep density change appears. Absent.
[0009]
Since there are many cases in which color characters are detected, it is necessary to significantly relax the threshold value if an edge is detected with high accuracy. However, when character areas are identified from a document containing a mixture of characters and photographs, if the edge detection threshold is relaxed, not only the edges of the character areas, but also photo areas with comparatively smooth changes in density. Will be erroneously detected as an edge.
[0010]
If the edge enhancement processing is performed on the detected edge with the threshold value relaxed, the photographic region is also unintentionally enhanced, resulting in a large deterioration in image quality. In particular, for the edges of achromatic colors, a black generation process is used to extremely increase the amount of black, so if such pixels appear in a part of the photographic area, a considerably conspicuous gap is generated and the image quality is greatly impaired. Cause.
[0011]
As described above, since the edge enhancement processing is different between the chromatic edge and the achromatic edge, if the edge is detected with the same threshold value, the image quality is deteriorated.
[0012]
An object of the present invention is to provide an image processing method, an image processing apparatus, an image forming apparatus, and a computer-readable recording medium capable of improving the reproducibility of color characters and improving the image quality of a photographic region.
[0013]
[Means for Solving the Problems]
  The present invention relates to an image processing method for performing region separation processing for separating input image data into a plurality of regions including at least a character region.
  The region separation process includes:When identifying a character area from input image data,
  A first step of determining whether the input image data is a chromatic color or an achromatic color;
  When it is determined in the first step that the input image data is an achromatic color, a threshold larger than a threshold selected when the input image data is determined to be a chromatic color is selected, The input image dataFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenAnd a second step of determining the image processing method.
[0014]
  According to the present invention,When identifying a character area from input image data,It is determined whether the input image data is a chromatic color or an achromatic color, and when the input image data is determined to be an achromatic color in the first step, the input image data is a chromatic color. A threshold value greater than the threshold value selected when determined is selected. The input image data using the selected threshold valueFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenSince the determination is made, it is possible to accurately detect the edge region of the color character and improve the reproducibility of the color character. This effect can further prevent erroneous detection of an achromatic edge region in the photographic region and improve the image quality of the photographic region.
[0015]
Further, the present invention is characterized in that a user can change the threshold value.
According to the present invention, since the user can change the threshold value, processing according to the user's preference can be performed.
[0016]
  The present invention also provides an image processing apparatus having an area separation processing unit that separates input image data into a plurality of areas including at least a character area.
  The region separation processing unitIdentify the character area from the input image data,
  A color determination unit that determines whether the input image data is a chromatic color or an achromatic color;
  A plurality of threshold values are stored in advance, and when the input image data is determined to be an achromatic color by the color determination unit, a threshold value selected when the input image data is determined to be a chromatic color is selected. A threshold setting unit for selecting a large threshold;
  Using the threshold selected by the threshold setting unit, the input image dataFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenAn image processing apparatus having a character edge determination unit for determination.
[0017]
  According to the present invention,When the region separation processing unit identifies a character region from input image data,A color determination unit determines whether the input image data is a chromatic color or an achromatic color, and a threshold setting unit that stores a plurality of threshold values in advance determines that the input image data is an achromatic color in the color determination unit If so, a threshold value larger than the threshold value selected when it is determined that the input image data is a chromatic color is selected. The character edge determination unit uses the threshold selected by the threshold setting unit to input the input image dataFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenAs a result of the determination, the edge region of the color character can be detected with high accuracy, and the reproducibility of the color character can be improved. This effect can further prevent erroneous detection of an achromatic edge region in the photographic region and improve the image quality of the photographic region.
[0020]
Further, the present invention is characterized in that the predetermined threshold is set for each color component of the input image data.
[0021]
According to the present invention, since the predetermined threshold value is set for each color component of the input image data, it is desirable to consider the characteristics of each color component signal or to change the detection level intentionally according to the purpose. In some cases, a desired edge detection result can be obtained.
[0022]
According to another aspect of the present invention, there is provided an image forming apparatus comprising: an image input device that reads a document to obtain image data; the image processing device described above; and an image output device that outputs processed image data. is there.
[0023]
According to the present invention, the image input device that reads the document to obtain image data, the image processing device described above, and the image output device that outputs the processed image data are provided. Since the edge area of a color character can be detected with high accuracy without erroneously detecting the edge area and the reproducibility of the color character can be improved, a high-quality image can be formed and output.
[0024]
  According to another aspect of the present invention, there is provided a computer-readable recording medium on which a program for causing a computer to execute an image processing method for performing an area separation process for separating input image data into a plurality of areas including at least a character area.
  When identifying a character area from input image data,
  A first step of determining whether the input image data is a chromatic color or an achromatic color;
  When it is determined in the first step that the input image data is an achromatic color, a threshold larger than a threshold selected when the input image data is determined to be a chromatic color is selected, The input image dataFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenA computer-readable recording medium storing a program for causing a computer to execute an image processing method having a second step of determining.
[0025]
  According to the present invention,When identifying a character area from input image data,It is determined whether the input image data is a chromatic color or an achromatic color, and when the input image data is determined to be an achromatic color in the first step, the input image data is a chromatic color. A threshold value greater than the threshold value selected when determined is selected. The input image data using the selected threshold valueFor each color component, change the density of the pixel of interest and the surrounding pixels around the pixel of interest.Feature valueAny one of the feature values obtained for each color componentThresholdGreater thanThe input image data is a character edge regionWhenSince the program is a storage medium for storing the program to be determined, the program is stored in a general-purpose computer such as a personal computer and a workstation via a recording medium such as a CD-ROM (Compact Disc-Read Only Memory) or downloaded from a network. Can be read and executed, and the region separation process can be performed on the image with high accuracy. Similarly, with a DSP (Digital Signal Processor) or the like, for a printer or digital copier that performs software processing, the program is read into a flash memory or a rewritable recording medium, and the image is accurately processed. Region separation processing can be performed.
[0026]
In addition, the present invention is characterized in that the user can change the threshold value used in the second step.
[0027]
According to the present invention, since the user can change the threshold value, a program for performing processing according to the user's preference can be provided.
[0028]
DETAILED DESCRIPTION OF THE INVENTION
FIG. 1 is a block diagram showing a configuration of an image forming apparatus 1 according to an embodiment of the present invention. The image forming apparatus 1 includes an image input device 10, an image processing device 20, and an image output device 30. The image input device 10 includes a CCD (Charge Coupled Device) line sensor, and converts the light reflected from the original into an electrical signal that is color-separated into R, G, and B (R: red, G: green, B: blue). Convert. The image processing apparatus 20 includes an A / D (analog / digital) conversion unit 21, a shading correction unit 22, an input processing unit 23, a region separation processing unit 24, a color correction unit 25, a black generation / under color removal unit 26, and a spatial filter. Unit 27 and halftone generation unit 28.
[0029]
A color image signal (RGB analog signal) that is input image data input from the image input device 10 is converted into a digital signal by the A / D conversion unit 21, and an illumination system of the image input device is converted by the shading correction unit 22. Various distortions generated in the imaging system and the imaging system are removed. Thereafter, the reflectance signal is converted into a density signal suitable for image processing in the input processing unit 23, and a CMY (C: cyan, M: magenta, Y: yellow) signal that is a complementary color of the RGB signal is generated. Next, a process for improving color reproducibility is performed in the color correction unit 25, and converted into a CMYK (K: black) 4-color signal by the black generation / under color removal unit 26.
[0030]
Further, the spatial filter unit 27 performs edge enhancement processing and smoothing processing by convolving the filter with respect to the CMYK signal, and the halftone generation unit 28 performs gradation reproduction processing for outputting an image. . Then, an output image is formed by an image output device 30 such as an electrophotographic or inkjet printer. The image output device 30 may be an image display device such as a liquid crystal display. In this case, the input processor 23 does not perform complementary color inversion of the RGB signals. Further, the black generation / undercolor removal unit 26 is not necessary.
[0031]
The region separation processing unit 24 includes a chromatic / achromatic determination unit 241, a threshold setting unit 242, and a character edge determination unit 243. In order to improve the reproducibility of black characters / color characters in a document in which at least a character region and a photo region are mixed, each pixel of the input image data has a chromatic color in the chromatic / achromatic determination unit 241 which is a color determination unit. The character edge determination unit 243 determines whether each pixel is an edge region of a character. In addition, a chromatic / achromatic signal is passed to the threshold setting unit 242 in order to switch the threshold used by the character edge determining unit 243 in accordance with the determination result of the chromatic / achromatic determining unit 241 for each pixel, and the signal is based on the signal. The optimum threshold is selected. The threshold value is delivered to the character edge determination unit 243 and used when detecting an edge. As a result, it is possible to accurately detect the edge area of the color character and prevent erroneous detection of the achromatic edge area of the photographic region, thereby improving the reproducibility of the color character and improving the image quality of the photographic region. it can.
[0032]
The output signal including the character edge signal and the chromatic / achromatic signal from the character edge determination unit 243 and the chromatic / achromatic determination unit 241 is output from the black generation / undercolor removal unit 26, the spatial filter unit 27, and the halftone generation unit 28. Each part is subjected to processing suitable for various areas. The above processing is controlled by a CPU (Central Processing Unit) not shown.
[0033]
Next, the region separation processing unit 24 will be described in detail.
(1) About the chromatic / achromatic determination unit 241
FIG. 2 is a block diagram illustrating a configuration of the chromatic / achromatic determination unit 241. The chromatic / achromatic determination unit 241 includes a maximum value calculation unit 241a, a minimum value calculation unit 241b, a difference unit 241c, and a comparator 241d, and determines whether the target pixel is a chromatic color or an achromatic color. And the determination result is output as a chromatic achromatic signal.
[0034]
First, the maximum value calculation unit 241a and the minimum value calculation unit 241b detect the maximum value and the minimum value of the C, M, and Y signals of the pixel of interest. Next, a difference value between the maximum value and the minimum value is obtained by the differentiator 241c. Then, the comparator 241d compares the difference value with the threshold value TH, and when the difference value is equal to or less than the threshold value TH, “ON” is output as a chromatic achromatic signal, and when the difference value is greater than the threshold value, “OFF” is output. Is done.
[0035]
That is, when the difference between the maximum value and the minimum value of the C, M, and Y signals in the target pixel is small, it is determined that the color is achromatic, and the chromatic achromatic signal is set to “ON”. On the other hand, if the difference is large, it is determined that the color is chromatic, and the chromatic / achromatic signal is “OFF”.
[0036]
(2) About the threshold setting unit 242
FIG. 3 is a block diagram showing the configuration of the threshold setting unit 242. As shown in FIG. The threshold setting unit 242 includes a selector 242a, and selects and outputs a threshold for detecting a character edge according to a chromatic achromatic signal indicating whether the pixel of interest is a chromatic color or an achromatic color. Process. The threshold value setting unit 242 holds two threshold value groups A (THc_mono, THm_mono, THy_mono) and threshold value group B (THc_color, THm_color, THy_color) that are set in advance, and is selected when the threshold value group A is achromatic. The threshold value and threshold value group B are made up of threshold values selected for a chromatic color. Either threshold group is selected according to the determination result of the chromatic / achromatic determination unit 241, and three threshold values (THc, THm, THy) corresponding to the respective color components are output to the character edge determination unit 243. . That is, the threshold group A is selected when the chromatic / achromatic signal is “ON”, and the threshold group B is selected when it is “OFF”. Then, the three output threshold values (THc, THm, THy) are individually delivered to the edge detection unit 243a provided for each color component of the character edge determination unit 243.
[0037]
Here, the preset threshold value group may be different values for the C, M, and Y color components, or may be the same value. For example, when the reading sensitivity of the CCD varies greatly depending on the color component, a different value can be provided in consideration thereof. Further, when it is not desired to detect an edge in a specific color component (for example, when an edge is not detected for yellow having a low density), a strict threshold (a large value) is set for the color component. It is also possible to define it. As described above, by enabling the user to change the threshold values of C, M, and Y, the degree of edge detection can be changed according to various applications.
[0038]
Furthermore, it is more effective to set a threshold value larger than the threshold value group B in the threshold value group A. As a result, a gradual threshold value (small value) is used for the chromatic edge region, so that the color character region can be accurately detected, and a strict threshold value (large value) for the achromatic edge region. ) Is used, it is possible to prevent the black edge of the photographic region from being detected unintentionally. If the edge region is detected in this way by switching the threshold value, the black edge of the photographic region is not enhanced even when the color character edge is enhanced when the edge enhancement process is performed. That is, while improving the reproducibility of color characters, it is possible to prevent image quality deterioration in the photographic area at the same time.
[0039]
(3) Character edge determination unit 243
FIG. 4 is a block diagram illustrating a configuration of the character edge determination unit 243. The character edge determination unit 243 includes an edge detection unit 243a that performs processing on C, M, and Y color components and an OR circuit 243b that performs a logical sum of the output signals.
[0040]
The edge detection unit 243a first forms a 3 × 3 pixel block centered on the target pixel using the two line memories 243c. Next, in the density difference determination unit 243d, the density difference between the pixel of interest and its neighboring pixels is obtained, and if any one of them is larger than the threshold value THc (or THm or THy), the output signal 'ON' is output. Otherwise, “OFF” is output. Note that the three threshold values THc, THm, and THy used at this time are values delivered from the threshold setting unit 242.
[0041]
An output signal from the edge detection unit of each color component is input to the OR circuit 243b, and a result obtained by performing a logical sum there is finally output as a character edge signal. That is, if an edge is detected in any one of C, M, and Y color components, it is determined that the pixel of interest is a character edge, and the character edge signal is “ON”; 'become.
[0042]
Note that the edge detection method is not limited to the above, and it may be detected using an edge detection filter such as a Sobel filter.
[0043]
FIG. 5 is a flowchart of the image processing method of the present invention. First, in step s1, the chromatic / achromatic determination unit 241 of the region separation processing unit 24 determines whether the pixel of interest that is input image data is a chromatic color or an achromatic color. In step s2, the threshold setting unit 242 determines whether the chromatic / achromatic signal is “ON”. If ON, the achromatic threshold group A is selected in step s3, and if OFF, the chromatic threshold group B is selected in step s4. In step s5, the character edge determination unit 243 determines whether the edge region is a character using the selected threshold value group, and outputs a character edge signal. The character edge signal and the chromatic / achromatic signal obtained as described above are delivered to the black generation / under color removal unit 26, the spatial filter unit 27, and the halftone generation unit 28, and based on these signals, each unit In FIG. 5, the optimum processing corresponding to each region is performed.
[0044]
In step s6, the black generation / under color removal unit 26 switches the black generation amount and the under color removal amount according to each region, thereby increasing the black amount of the black character region while maintaining the gradation of the photographic region. For example, if the amount of black generation is increased when the character edge signal = “ON” and the chromatic / achromatic signal = “ON”, the image quality of the black character region is improved.
[0045]
In step s7, the character reproducibility is improved by performing edge enhancement processing on the character region by the spatial filter unit 27. For example, when the character edge signal = “ON” and the chromatic achromatic signal “ON”, a strong enhancement filter is applied, and when the character edge signal = “ON” and the chromatic achromatic signal = “OFF”. Apply a weak enhancement filter. As a result, the black character edge can be strongly emphasized, and the color character edge can also be emphasized to the extent that the color does not change.
[0046]
In step s8, the output image quality is improved by switching the dither processing size in accordance with each region by the halftone generation unit 28. For example, when the character edge signal = 'ON', a 1 × 1 size dither process is performed, and when the character edge signal = 'OFF', a 3 × 3 size dither process is performed, thereby increasing the resolution of the character. The gradation of the area can be maintained.
[0047]
In the above, the configuration including the chromatic / achromatic determination unit 241, the threshold setting unit 242, and the character edge determination unit 243 is shown as the region separation processing unit 24. However, the present invention includes at least each of the above-described processing units. The halftone dot detection unit may be provided before the character edge determination unit 243, the chromatic / achromatic determination unit 241, or in parallel with these processing units. As a method for detecting halftone dots, the method described in “Image Electronics Society of Japan Proceedings 90-06-04” can be used. Details will be described below. The following determination is performed within a block of M × N (M and N are natural numbers) pixels centered on the pixel of interest, and this is used as the region identification signal of the pixel of interest.
[0048]
1. Average signal level (D) for the central 9 pixels in the block_ave) And binarize each pixel in the block using the average value. The maximum pixel signal level (D_max), Minimum pixel signal level (D_min) At the same time.
[0049]
2. In the halftone dot region, the halftone dot region is identified by utilizing the fact that the fluctuation of the image signal in the small region is large and the density is higher than the background. With respect to the binarized data, the number of change points from 0 to 1 in the main scanning and sub-scanning directions is obtained, and the number of change points from 1 to 0 is obtained._H, K_VAnd threshold T_H, T_YIf both of them exceed the threshold, the halftone dot region is set. In order to prevent misjudgment with the background, D_max, D_min, D_aveTo threshold B₁, B₂Compare with
[0050]
As another embodiment of the present invention, a computer-readable recording medium recording a program for causing a computer to execute an image processing method can be used. Thus, it is possible to provide a portable recording medium on which a program for performing the region separation process is recorded.
[0051]
In the present embodiment, as the recording medium, a memory (not shown) such as a ROM may be a program medium (recording medium) because processing is performed by a microcomputer. A program reading device may be provided as a storage device, and a program medium that can be read by inserting a recording medium therein may be used.
[0052]
In any case, the stored program may be configured to be accessed and executed by the microprocessor, or in any case, the program is read and the read program is not illustrated in the microcomputer. The program may be downloaded to a non-program storage area and executed. It is assumed that this download program is stored in the main device in advance.
[0053]
Here, the program medium is a recording medium configured to be separable from the main body, such as a tape system such as a magnetic tape or a cassette tape, a magnetic disk such as a floppy disk or a hard disk, and a CD-ROM / MO / MD / DVD. Semiconductors such as optical discs, IC cards (including memory cards) / optical cards, etc., or mask ROM, EPROM (Erasable Programmable Read Only Memory), EEPROM (Electrically Erasable Programmable Read Only Memory), flash ROM, etc. It may be a medium that carries a fixed program including a memory.
[0054]
In the present embodiment, the medium may be a medium that carries a program so as to download the program from the communication network by using a communication unit that can connect to a communication network including the Internet. When the program is downloaded from the communication network in this way, the download program may be stored in the main device in advance or installed from another recording medium.
[0055]
The recording medium is read by a digital color image forming apparatus and a program reading apparatus provided in a computer system, whereby the above-described image processing method (region separation method) is executed. Particularly in the latter case, it is easy to change the setting value according to the user's preference in the image processing method of the present invention.
[0056]
FIG. 6 is a diagram showing an image forming apparatus by a computer system 2 according to another embodiment of the present invention. The computer system 2 includes an image input device 40 such as a flatbed scanner, a film scanner, and a digital camera, a computer 50 that performs various processing such as image processing by loading a predetermined program, and a CRT that displays the processing results of the computer. It includes an image display device 60 such as a display and a liquid crystal display, a printer 70 that outputs the processing results of the computer to paper, a keyboard 81 for operating a program, setting values, and a mouse 82. Furthermore, a modem or the like as a communication means for connecting to a server or the like via a network is provided. When the computer 50 executes the program recorded on the recording medium, the same processing as that of the image processing apparatus 20 shown in FIG. 1 can be performed.
[0057]
When the computer system 2 executes the image processing method of the present invention, it becomes easy to arbitrarily change the threshold setting as described above, and it is set again according to the result displayed on the image display device. Processing according to user preference is possible. In order to change the threshold value, the threshold value is set by directly inputting a numerical value using the keyboard 81 or the mouse 82 or clicking a symbol representing the threshold value.
[0058]
【The invention's effect】
As described above, according to the present invention, it is possible to accurately detect the edge region of a color character and prevent erroneous detection of an achromatic edge region in a photographic region, so that the reproducibility of a color character is improved and the photographic region Image quality can be improved.
[0059]
Further, according to the present invention, the threshold value can be changed by the user, so that processing according to the user's preference can be performed.
[0060]
In addition, according to the present invention, a desired edge detection result can be obtained when it is desired to consider the characteristics of each color component signal or when the detection level is intentionally changed according to the purpose.
[0061]
Further, according to the present invention, it is possible to accurately detect the edge region of the color character without erroneously detecting the achromatic edge region of the photographic region and improve the reproducibility of the color character, thereby forming a high-quality image. Can be output.
[0062]
Further, according to the present invention, a general-purpose computer such as a personal computer and a workstation is read through a recording medium such as a CD-ROM (Compact Disc Read Only Memory) or downloaded from a network and executed. Thus, it is possible to perform the region separation process with high accuracy on the image. Similarly, with a DSP (Digital Signal Processor) or the like, for a printer or digital copier that performs software processing, the program is read into a flash memory or a rewritable recording medium, and the image is accurately processed. Region separation processing can be performed.
[Brief description of the drawings]
FIG. 1 is a block diagram showing a configuration of an image forming apparatus 1 according to an embodiment of the present invention.
FIG. 2 is a block diagram illustrating a configuration of a chromatic / achromatic determination unit 241. FIG.
3 is a block diagram showing a configuration of a threshold setting unit 242. FIG.
4 is a block diagram showing a configuration of a character edge determination unit 243. FIG.
FIG. 5 is a flowchart of an image processing method of the present invention.
FIG. 6 is a diagram showing an image forming apparatus by a computer system 2 according to another embodiment of the present invention.
FIG. 7 is a diagram illustrating an example of a document 100 that detects edge areas of color characters.
8 is a diagram illustrating the density of a background 101 and characters 102 of an original 100. FIG.
FIG. 9 is a diagram showing a change in density for each pixel in the x direction in a broken line portion;
[Explanation of symbols]
1 Image forming device
2 Computer system
10 Image input device
20 Image processing device
21 A / D (analog / digital) converter
22 Shading correction part
23 Input processing section
24 Region separation processing unit
25 color correction section
26 Black generation and under color removal part
27 Spatial filter section
28 Halftone generator 28
30 Image output device
241 Chromatic / Achromatic determination part
241a Maximum value calculation unit
241b Minimum value calculation unit
241c Differencer
241d comparator
242 Threshold setting unit
242a selector
243 Character edge judgment part
243a Edge detection unit
243b OR circuit

Claims (7)

In an image processing method for performing region separation processing for separating input image data into a plurality of regions including at least a character region,
In the region separation process, when a character region is identified from input image data,
A first step of determining whether the input image data is a chromatic color or an achromatic color;
When it is determined in the first step that the input image data is an achromatic color, a threshold larger than a threshold selected when the input image data is determined to be a chromatic color is selected, When a color change of the input image data for each color component is obtained as a feature amount and a change in density in a peripheral pixel existing around the target pixel , and when any of the feature amounts obtained for each color component is greater than a threshold, And a second step of determining that the input image data is an edge region of a character.   The image processing method according to claim 1, wherein a user can change the threshold value. In an image processing apparatus having an area separation processing unit that separates input image data into a plurality of areas including at least a character area.
The region separation processing unit identifies a character region from input image data,
A color determination unit that determines whether the input image data is a chromatic color or an achromatic color;
A plurality of threshold values are stored in advance, and when the input image data is determined to be an achromatic color by the color determination unit, a threshold value selected when the input image data is determined to be a chromatic color is selected. A threshold setting unit for selecting a large threshold;
Using the threshold selected by the threshold setting unit, a change in density in a pixel of interest and a peripheral pixel existing around the pixel of interest for each color component of the input image data is obtained as a feature amount , and the obtained for each color component An image processing apparatus comprising: a character edge determination unit that determines that the input image data is an edge region of a character when any of the feature values is greater than a threshold value.   The image processing apparatus according to claim 3, wherein the predetermined threshold is set for each color component of the input image data. An image input device for reading image data to obtain image data;
An image processing apparatus according to claim 3 or 4,
An image forming apparatus comprising: an image output device that outputs processed image data. In a computer-readable recording medium recording a program for causing a computer to execute an image processing method for performing an area separation process for separating input image data into a plurality of areas including at least a character area.
When identifying a character area from input image data,
A first step of determining whether the input image data is a chromatic color or an achromatic color;
When it is determined in the first step that the input image data is an achromatic color, a threshold larger than a threshold selected when the input image data is determined to be a chromatic color is selected, When a color change of the input image data for each color component is obtained as a feature amount and a change in density in a peripheral pixel existing around the target pixel , and when any of the feature amounts obtained for each color component is greater than a threshold, a computer-readable recording medium a program for the input image data to execute an image processing method and a second step of determining that a character of the edge region into the computer.   The computer-readable recording medium according to claim 6, wherein a user can change the threshold value used in the second step.

Images