JP2008187327A - Image processor and image forming apparatus equipped with the same - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To provide an image processor and an image forming apparatus capable of preventing a character image from being outputted in the state being buried in a background image with a simple configuration. <P>SOLUTION: When image data are accepted (S1), and when the image data are a color image, the image data are converted into monochromatic data (S3), and whether or not region designation by a user is present is judged (S4), and a character image region and a background image region are detected and specified (S7). Then, the density mean value X of the character image is calculated (S8), and the density mean value Y of the background image is calculated (S9). When a difference between the density mean value X of the whole character image and the density mean value Y of the whole background image exceeds a threshold, normal image processing such as color conversion and gamma conversion is carried out (S11). On the contrary, when a difference between the mean density values X and Y is the threshold or less, the normal image processing is executed (S12), and processing to increase the contrast of the character image and the background image is carried out based on the density mean value of the respective color components of the whole character image in image data adjustment processing (S13). <P>COPYRIGHT: (C)2008,JPO&INPIT

Description

  The present invention relates to an image processing apparatus that performs image processing on image data to be output, and an image forming apparatus including the same.

  A character image should normally serve to convey information. For this reason, it is important to avoid the character image being buried in the background. For this reason, various ideas have been conventionally made for extracting a character image from a background image.

For example, in the conventional technology, in a recognition target extraction device that extracts a recognition target region including characters from a processing target image, noise in the recognition target region is effective when there is little contrast difference or color tone difference between the character and the background. There is a technique for accurately extracting only character information by removing them (see, for example, Patent Document 1).
JP 2005-267480 A

  Furthermore, in addition to accurately extracting only character information, it is also important to prevent the character image from being output while being buried in the background. The reason is that when the character image is output on the paper surface while being buried in the background, the paper does not function as an information transmission medium and is discarded. For this reason, when an image is output, it is important that the character image is always not buried in the background.

  An object of the present invention is to provide an image processing apparatus and an image forming apparatus capable of preventing a character image from being output in a state where it is buried in a background image with a simple configuration.

  An image processing apparatus according to the present invention performs image processing on image data to be output. The image processing apparatus includes an area detection unit, a density calculation unit, and an image adjustment unit.

  The area detecting means detects an area occupied by the character image in the image data and an area occupied by the background image located around the character image.

  The density calculation means calculates a first density value indicating the density of the character image and a second density value indicating the density of the background image based on the detection result of the area detection means. Examples of the density value include numerical values expressed in 256 gradations from 0 to 255, but are not limited thereto.

  The image adjusting means is configured to increase the contrast between the character image and the background image based on the first density value when the difference between the second density value and the first density value is equal to or smaller than a predetermined value. Change the image density. When the character image and the background image are respectively color images, the density of both may be detected after the color image is converted into monochrome.

  An example of a technique for increasing the contrast between a character image and a background image is to reduce the density of the character image when the density of the character image is close to the upper limit of density. When the density of the character image is close to the upper limit of density, it is assumed that the density of the background image that approximates this is also relatively close to the upper limit of density, so by reducing the density of the character image, It becomes easy to stand out. On the other hand, when the density of the character image is close to the lower limit of density, the density of the character image can be increased. When the density of the character image is close to the lower limit of density, it is presumed that the density of the background image is also relatively close to the lower limit of density, so that the character image becomes conspicuous by increasing the density of the character image.

  According to the present invention, it is possible to prevent a character image from being output while being buried in a background image with a simple configuration.

  As shown in FIG. 1, the image forming apparatus 50 includes an image reading unit 12, an image forming unit 14, a display unit 16, an operation unit 18, an interface unit 20, a ROM 22, a RAM 24, an image processing unit 26, an image data adjusting unit 30, And a CPU 10.

  The image reading unit 12 reads an image of a document and converts it into image data. The image forming unit 14 executes an image forming process based on the given image data. The display unit 16 is configured to display information to be notified to the user. The operation unit 18 transmits a command based on a user input operation to the CPU 10. The interface unit 20 has functions necessary for communication with an external device. Here, the interface unit 20 is connected to a LAN to which a plurality of personal computers are connected. The ROM 22 stores a plurality of programs necessary for the operation of the CPU 10. The RAM 24 is a nonvolatile memory in which data is temporarily recorded. The image processing unit 26 performs image processing on image data to be output according to a predetermined procedure. The image data adjustment unit 30 changes the character image data in the image data. The CPU 10 comprehensively controls each unit of the image forming apparatus 50. In this example, the image processing unit 100 including the ROM 22, the RAM 24, the image processing unit 26, the image data adjusting unit 30, and the CPU 10 corresponds to the image processing apparatus of the present invention.

  A schematic configuration of the image data adjustment unit 30 will be described with reference to FIG. The image data adjustment unit 30 includes a preprocessing unit 32, a region detection unit 34, an image determination unit 36, and an image change unit 38. The preprocessing unit 32 changes the color image data to be output to monochrome gradation image data for contrast determination. The method for making a color image monochrome is not particularly limited, but it is preferable to make a color image monochrome without changing the gradation or brightness. In this example, the brightness A is calculated from the RGB components using the formula “A = R × 0.30 + G × 0.59 + B × 0.11”. For example, in the case of a similar color image, it is preferable that a contrast difference is reflected as a density difference.

  The area detection unit 34 recognizes a character image and a background image in a monochrome gradation image and stores their positions. The area detection unit 34 includes an optical character reader (OCR), and performs character recognition processing of image data related to an area to be subjected to image data adjustment processing using the OCR. A region of image data recognized as a character by character recognition processing is specified as a character image region. On the other hand, an area of image data that is not recognized as a character by the character recognition process is specified as a background image area.

  The image determination unit 36 determines the contrast between the character image and the background image. Specifically, it is determined whether the density difference between the character image and the background image is higher than a threshold value.

  The image changing unit 38 changes the image data so that the contrast between the character image and the background image increases when the difference in density between the character image and the background image is lower than the threshold value. Examples of this change in image data include a decrease in character image density, an increase in character image density, and a change in color tone of the character image.

  3 and 4 are flowcharts showing the operation procedure of the CPU 10 during image processing and image data adjustment processing. When receiving the image data (S1), the CPU 10 determines whether or not the received image data is a color image (S2).

  In the determination step of S2, if the image is a color image, the CPU 10 causes the pre-processing unit 32 to perform monochrome conversion of the color image (S3).

  Subsequently, the CPU 10 determines whether or not an area has been designated (S4). In the determination step of S4, when the setting command from the user regarding the area to be subjected to the image data adjustment processing is input, the process proceeds to step S6. In this case, only the designated area is designated as an image data adjustment process target (S6). On the other hand, in the determination step of S4, when the setting command from the user regarding the area to be subjected to the image data adjustment processing is not input, the process proceeds to S5. In this case, the entire area of the image is designated as an object for image data adjustment processing (S5).

  Subsequently, the CPU 10 executes a region detection process (S7). In step S <b> 7, the CPU 10 classifies the character image and the background image using the area detection unit 34. Here, the CPU 10 specifies an area of the character image, and specifies an area other than the character image area in the area to be subjected to the image data adjustment processing as the background area.

  Subsequently, the CPU 10 calculates a character image density value (S8). In step S8, the CPU 10 calculates the average density value X of the entire character image. Further, the CPU 10 calculates a background image density value (S9). In step S9, the CPU 10 calculates the average density value Y of the entire background image. Note that, here, the density average value X and the density average value Y are expressed by values in 256 steps from 0 to 255.

  Subsequently, the CPU 10 determines a density difference between the character image and the background image (S10). Here, the CPU 10 determines whether or not the difference between the density average value X of the entire character image and the density average value Y of the entire background image exceeds a predetermined threshold value. In S10, “30” is set as the threshold value.

  When the difference between the average density value X of the entire character image and the average density value Y of the entire background image exceeds the threshold value in the determination step of S10, the CPU 10 executes normal image processing on the image processing unit 26. (S11). Here, as normal image processing, “RGB → YMCK conversion”, UCR conversion, γ conversion, and the like are executed. After the image processing is completed, the CPU 10 supplies the image data after the image processing to the image forming unit 14. On the other hand, when the difference between the average density value X of the entire character image and the average density value Y of the entire background image is equal to or smaller than the threshold value, the CPU 10 causes the image processing unit 26 to perform normal image processing (S12). Thereafter, the image data changing unit 38 is further caused to execute image data adjustment processing (S13).

  The image data adjustment process will be described with reference to FIG. In the image data adjustment process, the CPU 10 calculates the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, and black component density average value Xk of the entire character image (S20). The yellow component density average value Xy, the magenta component density average value Xm, the cyan component density average value Xc, and the black component density average value Xk are expressed by 256-level values from 0 to 255.

  Subsequently, the CPU 10 determines whether any one of the yellow component density average value Xy, the magenta component density average value Xm, the cyan component density average value Xc, or the black component density average value Xk is equal to or greater than a threshold value. (S21). The threshold value in the determination step of S21 is set to a value of 70% of the maximum density.

  In the determination step of S21, if any of the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk is less than 70% of the maximum density, The CPU 10 increases the density of the character image (S22). Specifically, in step S22, the CPU 10 increases the yellow component density average value Xy, the magenta component density average value Xm, the cyan component density average value Xc, or the black component density average value Xk by 30%. As a result, as shown in FIG. 5A or FIG. 5B, the density of the character image increases, and the contrast between the character image and the background image increases.

  On the other hand, in the determination step of S21, any one of the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk is the maximum density. If it is 70% or more, the CPU 10 decreases the density of the character image (S23). In this example, in step S23, the CPU 10 sets the values of the yellow component density average value Xy, the magenta component density average value Xm, the cyan component density average value Xc, and the black component density average value Xk to 0, respectively. As a result, as shown in FIG. 5C or FIG. 5D, the character image becomes white and the contrast between the character image and the background image increases.

  6 to 8 are flowcharts showing other examples of operation procedures of the CPU 10 during image processing and image data adjustment processing. Steps S101 to S112 in FIG. 6 correspond to steps S1 to S12 in FIG. In FIG. 6, it is determined in step S113 whether or not the image data is a color image, and based on the determination result, one of two types of image data adjustment processes with different procedures is executed (S113). , S114, S115).

  The image data adjustment process in S114 will be described with reference to FIG. In the image data adjustment process of S114, the CPU 10 determines whether or not the character area density value X is equal to or greater than a threshold value (221). The threshold value in the determination step of S221 is set to a value of 70% of the maximum density.

  If the character region density value X is less than 70% of the maximum density in the determination step of S221, the CPU 10 increases the density of the character image (S222). Specifically, in step S222, the CPU 10 increases the character region density value X by 30%. As a result, as shown in FIG. 5A, the density of the character image increases and the contrast between the character image and the background image increases.

  On the other hand, if the character region density value X is 70% or more of the maximum density in the determination step of S221, the CPU 10 decreases the density of the character image (S223). In this example, the CPU 10 sets the character area density value X to 0 in step S223. As a result, as shown in FIG. 5C, the character image becomes white and the contrast between the character image and the background image increases.

  The image data adjustment process in S115 will be described with reference to FIG. In the image data adjustment processing of S115, the CPU 10 calculates the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, and black component density average value Xk of the entire character image (S120).

  Subsequently, the CPU 10 determines whether or not the yellow component density average value Xy is greater than or equal to a threshold value in order to determine whether or not the character image is yellow (S121). In the determination step of S121, a value obtained by multiplying the maximum value among the magenta component density average value Xm, the cyan component density average value Xc, and the black component density average value Xk by 100 is set as a threshold value.

  If the yellow component density average value Xy is equal to or greater than the threshold value in the determination step of S121, the CPU 10 determines the background image yellow component density average value Yy, the background image magenta component density average value Ym, and the background image cyan component density. The average value Yc and the black component density average value Yk of the background image are calculated (S125). Here, the yellow component density average value Yy of the background image, the magenta component density average value Ym of the background image, the cyan component density average value Yc of the background image, and the black component density average value Yk of the background image are 0 to 255. Of 256 levels.

  Subsequently, the CPU 10 determines whether or not the yellow component density average value Yy is equal to or greater than a threshold value in order to determine whether or not the background image is yellow (S126). In the determination step of S126, a value obtained by multiplying the maximum value among the magenta component density average value Ym, the cyan component density average value Yc, and the black component density average value Yk by 100 is set as a threshold value.

  In the determination step of S126, when the yellow component density average value Yy is equal to or greater than the threshold value, the CPU 10 proceeds to a later-described color tone changing step of S128. On the other hand, when the yellow component density average value Yy is less than the threshold value, in order to determine whether or not the background image is white, the background image yellow component density average value Yy, the background image magenta component density average It is determined whether the value Ym, the cyan component density average value Yc of the background image, and the black component density average value Yk of the background image are very small (S127). In this example, in the determination step of S127, the CPU 10 determines the yellow component density average value Yy of the background image, the magenta component density average value Ym of the background image, the cyan component density average value Yc of the background image, and the black component density of the background image. It is determined whether or not the average values Yk are all 5 or less.

  In the determination step of S127, the yellow component density average value Yy of the background image, the magenta component density average value Ym of the background image, the cyan component density average value Yc of the background image, and the black component density average value Yk of the background image are all 5. In the following cases, the process proceeds to the color tone changing step in S128, and in other cases, the image data adjustment process is ended as it is.

  In the color tone changing step of S128, the CPU 10 decreases the yellow component density average value Xy of the character image by 30% and increases the magenta component density average value Xm and the cyan component density average value Xc by 30%. As a result, as shown in FIG. 9A or 9B, the color tone of the character image changes, and the contrast between the character image and the background image increases.

  On the other hand, when the yellow component density average value Xy is less than the threshold value in the determination step of S121, the CPU 10 determines the yellow component density average value Xy, the magenta component density average value Xm, the cyan component density average value Xc, or the black component density. It is determined whether any one of the average values Xk is equal to or greater than a threshold value (S122). The threshold value in the determination step of S122 is set to a value of 70% of the maximum density.

  If any of the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk is less than 70% of the maximum density in the determination step of S122, The CPU 10 increases the density of the character image (S123). Specifically, in step S123, the CPU 10 increases the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk by 30%. As a result, as shown in FIG. 5A or FIG. 5B, the density of the character image increases, and the contrast between the character image and the background image increases.

  On the other hand, in the determination step of S122, any one of the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk is the maximum density. If it is 70% or more, the CPU 10 decreases the density of the character image (S124). In this example, in step S124, the CPU 10 sets the yellow component density average value Xy, magenta component density average value Xm, cyan component density average value Xc, or black component density average value Xk to 0. As a result, as shown in FIG. 5C or FIG. 5D, the character image becomes white and the contrast between the character image and the background image increases.

  FIG. 10 is a flowchart illustrating another example of the operation procedure of the CPU 10 during image processing and image data adjustment processing. Since steps S301 to S312 in FIG. 10 correspond to steps S1 to S12 in FIG. 3, the description thereof is omitted here.

  The CPU 10 displays an image related to the adjusted image data on the display unit 16 (S313). Subsequently, the CPU 10 determines whether or not the user approves the adjusted image (S314). If a user approval command is to be output via the operation unit 18 in the determination step of S314, the CPU 10 supplies the adjusted image data to the image forming unit 14. On the other hand, when the user's approval command is not input in the determination step of S314, the CPU 10 invalidates the adjustment of the image data (S315). At this time, the CPU 10 supplies the image data before adjustment to the image forming unit 14.

  The above description of the embodiment is to be considered in all respects as illustrative and not restrictive. The scope of the present invention is shown not by the above embodiments but by the claims. Furthermore, the scope of the present invention is intended to include all modifications within the meaning and scope equivalent to the scope of the claims.

1 is a block diagram showing a schematic configuration of a copying machine. It is a block diagram which shows the structure of an image data adjustment part. It is a flowchart which shows the operation | movement procedure of CPU at the time of an image process and an image data adjustment process. It is a flowchart which shows the operation | movement procedure of CPU at the time of an image data adjustment process. It is a figure which shows the state of the image before and behind adjustment. It is a flowchart which shows the other example of the operation | movement procedure of CPU at the time of an image process and an image data adjustment process. It is a flowchart which shows the other example of the operation | movement procedure of CPU at the time of image data adjustment processing. It is a flowchart which shows the other example of the operation | movement procedure of CPU at the time of image data adjustment processing. It is a figure which shows the other example of the state of the image before and behind adjustment. It is a flowchart which shows the other example of the operation | movement procedure of CPU at the time of an image process and an image data adjustment process.

Explanation of symbols

10-CPU
26-Image processing unit 30-Image data adjustment unit 32-Pre-processing unit 34-Region detection unit 36-Image determination unit 38-Image change unit

Claims (9)

An image processing apparatus that performs image processing on image data to be output,
An area detection unit for detecting an area occupied by a character image in image data and an area occupied by a background image located around the character image;
Density calculating means for calculating a first density value indicating the density of the character image and a second density value indicating the density of the background image based on the detection result of the area detecting means;
When the difference between the second density value and the first density value is less than or equal to a predetermined value, the contrast between the character image and the background image is enlarged based on the first density value. Image adjusting means for changing the density of the character image;
An image processing apparatus comprising:   When the difference between the second density value and the first density value is less than or equal to a predetermined value, and the first density value is greater than or equal to a predetermined threshold value, the image adjustment means The image processing apparatus according to claim 1, wherein:   When the difference between the second density value and the first density value is less than or equal to a predetermined value and the first density value is less than a predetermined threshold value, the image adjusting unit determines the density of the character image. The image processing apparatus according to claim 1, wherein the image processing apparatus raises the image. The density calculation means calculates the density of the character image and the density of the background image for each of yellow, magenta, cyan, and black color components,
The image processing apparatus according to claim 1, wherein the image adjustment unit adjusts the density of the character image for each color component based on a calculation result of the density calculation unit.   The image adjusting means adjusts the density of at least one of the magenta component and the cyan component of the character image when the density of the yellow component of the character image is a predetermined ratio or more with respect to the magenta component and the cyan component. The image processing apparatus according to claim 4.   The image adjusting means adjusts the density of at least one of a magenta component and a cyan component of the character image only when it is determined that the color of the background image is yellow or white. 5. The image processing apparatus according to 5.   The image according to any one of claims 1 to 6, wherein the area detection unit determines an area occupied by the background image based on an input from a user who designates an area to be a background image. Processing equipment. Display means for displaying the image after the change by the image adjusting means;
Based on a predetermined input operation from a user, a change invalidation unit that invalidates a change of a character image by the image adjustment unit;
The image processing apparatus according to claim 1, further comprising: The image processing apparatus according to any one of claims 1 to 8,
An image forming unit that executes an image forming process based on image data supplied from the image processing apparatus;
An image forming apparatus comprising:

Images