JPH09186864A - Processor and method for image processing - Google Patents

Abstract

PROBLEM TO BE SOLVED: To precisely recognize an image from image data after half-tone processing with high precision by providing an specified input means and an inverse half-tone processing means respectively. SOLUTION: An inputted RGB digital image signal 1 is converted by an RF(reproduction) converter 2 into a YMCK digital image signal, and the converter 2 performs conversion from an RGB color space to a YMCK color space, and performs UCR(ground color removal) and a masking process for correcting characteristics of toner. Therefore, the YMCK image data outputted from the RF converter 2 are data which appear to have decreased in image contrast under the influence of, specially, the UCR. Namely, a γ table 7 operates to remove the influence of various characteristics of the RF converter 2 (or RF conversion by image processing software) and reproduce the original RGB digital image data. Further, the averaging process by an averaging unit 6 operates to reduce the influence of a dither process from image data after the dither process.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to an image processing apparatus and a method thereof, for example, an image processing apparatus and a method thereof for recognizing the identity between an image represented by input image data and a specific image.

[0002]

2. Description of the Related Art In the past, color printing could only be performed by a specialized printing company, but with the widespread use of color copiers and color printers, anyone can easily perform color printing. High-quality full-color prints are now readily available.

However, while these devices have become popular,
Technology is required to prevent counterfeiting of manuscripts (hereinafter referred to as "specific manuscripts") that should not be reproduced due to legal restrictions such as banknotes and securities, etc. Is becoming. In this technique, reference data is created in advance from image information of a specific document, and it is determined based on the reference data whether the input image is the specific document. Most of these technologies attempt to prevent forgery by developing input image data on a memory, performing pattern matching or fuzzy inference on the memory, and extracting feature points of a specific document. .

On the other hand, in order to output a full-color image with a printer having a small number of gradations per pixel, generally, image processing such as dither processing and error diffusion processing for increasing the number of apparent gradations is performed. These processes are based on the area gradation method, and are a method of increasing the number of expression gradations in the low spatial frequency of the image. When the area gradation method is used, the resolution of the output image tends to decrease. However, since recent printers have dramatically improved the resolution, even if the area gradation method is used, the output that has degraded so much Never be.

FIG. 1 is a block diagram showing an example of the configuration of a printer that performs dither processing. Image data 101 in the RGB color space input from a host computer (not shown) is a production converter (hereinafter referred to as "RF converter"). ) 102, it is converted into image data in the YMCK color space which is the color space of the printer. The RF converter 102 performs conversion from the RGB color space to the YMC color space, and also performs undercolor removal (hereinafter referred to as “UCR”) and masking processing for correcting characteristics such as toner. Then, the YMCK image data is input to the dither processing circuit 103 and subjected to dither processing. The dithered YMCK image data is returned to the printer engine 104.
Is input to, and the Y, M, C, and K color component images are superimposed and output as a print output 105.

Since the printer is an image forming apparatus that forms a color image by the subtractive color method, YMCK or YMC converted image data is finally input to the printer engine 104 regardless of the color space of the input data. . In addition, the image processing software running on the host computer enables RF
Conversion may be performed, and in that case, image data in the YMCK color space is directly input to the printer. Therefore, in order to recognize whether or not the image to be printed at present is the specific original in the printer unit, the YM
It will need to be done in CK or YMC color space.

[0007]

However, the above-mentioned technique has the following problems.

In the RGB color space, the luminance information can be linearly approximated as it is, but the YMCK data needs to be approximated by the log conversion, and the YCR data is compressed in amplitude by the UCR process. There is. Further, since the correction for correcting various characteristics of the printer engine is added, the relationship between the YMCK image data to be printed out and the original luminance information in the RGB space is a non-linear relationship. Further, when the area gradation method is used, it is necessary that the relationship between the input and the output is linear, and it becomes difficult to faithfully reproduce the image if a non-linear process is inserted therebetween.

FIG. 2 is a diagram showing a general relationship between the luminance signal and the density signal. In the following, the RF conversion will be simplified and explained only by the luminance-density conversion.

Generally, the characteristics of conversion from RGB to YMCK are shown in FIG.
It becomes as shown in. The horizontal axis is the normalized RGB luminance signal value, and the vertical axis is the normalized YMCK density signal value.
For example, when the brightness signal value is 0.3, the corresponding density signal value is 0.5.

If the conversion from RGB to YMCK has the characteristics shown in FIG. 2, assuming that four pixels having a luminance signal value of 0.3 as shown in FIG. The output of the converter is as shown in Fig. 6 (b). This signal is input to the dither processing circuit and subjected to dither processing of 2 × 2 pixels,
The representative values of the density values 0 and 1 as shown in FIG. 6 (c) are replaced. When this signal is printed out, it becomes as shown in Fig. 6 (d), and the average value of the densities of the entire printout is 0.5, so the density value of each pixel is 0.5 Is expressed by area gradation.

When recognizing a specific pattern and restoring the luminance information from such a dithered signal, the non-linear luminance-density conversion shown in FIG. 2 is applied to the dithered signal. Therefore, it is not satisfied that the relationship between the input and the output is linear, which is a condition when using the above-described area gradation method. That is, restoring the luminance information from the dithered signal means obtaining the data shown in FIG. 3 (e) from the data shown in FIG. 3 (c) using the conversion characteristic shown in FIG. The average brightness value in FIG. 3 (e) is 0.5, which is different from the average brightness value 0.3 in FIG. 3 (a).

Therefore, in a printer system or the like which uses area gradation processing such as dither processing or error diffusion, there is a problem that the recognition ability of a specific image is extremely deteriorated, or even recognition becomes impossible.

SUMMARY OF THE INVENTION The present invention is intended to solve the above problems, and an object of the present invention is to provide an image processing apparatus and method capable of performing highly accurate image recognition from halftone processed image data. To do.

[0015]

The present invention has the following configuration as one means for achieving the above object. An image processing apparatus according to the present invention includes an input unit for inputting halftone-processed image data, an inverse halftone processing unit for subjecting the halftone-processed image data to an inverse halftone process, and the inverse halftone process. And a recognition unit that recognizes whether or not the image represented by the generated image data is a specific image.
Further, processing means for performing color space conversion and correction processing on the input image data, halftone processing means for performing halftone processing on the image data subjected to the color space conversion and correction processing, and the halftone processing. Inverse halftone processing means for subjecting the image data to inverse halftone processing, inverse processing means for subjecting the inverse halftone processed image data to inverse processing of the color space conversion and correction processing, and the inverse processed image data And an output unit that controls the output of the image data that has been subjected to the color space conversion and correction processing based on the recognition result obtained by the recognition unit. .

The image processing method according to the present invention comprises an input step of inputting image data subjected to halftone processing, an inverse halftone processing step of performing inverse halftone processing on the image data subjected to halftone processing, and the inverse processing step. A recognition step of recognizing whether or not the image represented by the halftone-processed image data is a specific image.

Further, a processing step for performing color space conversion and correction processing on the input image data, a halftone processing step for performing halftone processing on the image data subjected to the color space conversion and correction processing, and the halftone processing. The inverse halftone processing step of performing inverse halftone processing on the image data, the inverse processing step of performing inverse processing of the color space conversion and correction processing on the image data subjected to inverse halftone processing, and the inverse processed image data It is characterized by including a recognition step of recognizing the image represented, and an output step of controlling the output of the image data subjected to the color space conversion and correction processing based on the recognition result obtained in the recognition step.

[0018]

DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, an image processing apparatus according to an embodiment of the present invention will be described in detail with reference to the drawings.

[0019]

First Embodiment FIG. 4 is a block diagram showing a configuration example of an image processing apparatus according to an embodiment of the present invention.

In FIG. 1, a control unit 21 composed of a CPU, ROM, RAM, I / O, etc. controls the entire apparatus according to a control program stored in ROM in advance. In addition, the operation panel 20
Is provided with a keyboard and a touch panel for inputting operator's instructions to the control unit 21, a display such as an LCD for displaying the operating state and operating conditions of the apparatus by the control unit 21, and the like.

Now, the RGB digital image signal 1 input from a host computer (not shown) is converted into an RF converter 2
Is converted into YMCK digital image signal 3. The RF converter 2 performs conversion from the RGB color space to the YMC color space, and also performs masking processing for correcting characteristics such as UCR and toner. When the YMCK digital image signal is directly input by the image processing software running on the host computer, the RF converter 2 is set from the operation panel 20 or the like so as to pass the input signal as it is.

The YMCK digital image signal output from the RF converter 2 is input to the dither processing circuit 3 and subjected to dither processing, and then input to the printer engine 4 and the averaging circuit 6. The printer engine 4 forms a color image based on the image data from the RF converter 2 and outputs a print output 5.

On the other hand, the image data input to the averaging unit 6 is subjected to averaging processing and then input to the γ table 7 composed of a ROM or the like. The γ table 7 nonlinearly converts the input density data into luminance data, and the digital image data converted by the γ table 7 is input to the image recognition circuit 8. The image recognition circuit 8 stores reference data created from image information of a specific document, performs pattern matching and fuzzy inference based on the reference data, and recognizes the image of the specific document as an input image. . This recognition result is output as a signal Det, and the control unit 21 determines based on this signal Det whether or not the image of the specific document is to be printed, and if it is determined that the image of the specific document is being printed, , Process control such as stopping the print operation of the printer engine 4 or not fixing,
The image data is deformed into, for example, a black solid image so as to prevent the faithful print output of the specific original document and prevent the faithful print output of the image of the specific original document.

Here, since the RF conversion performs various processes such as color space conversion, UCR, masking, and correction of engine characteristics, the output YMCK image data is apparently contrasted with the image due to the influence of UCR. Is a reduced data. That is, the γ table 7 works to remove the influence of various characteristics of the RF converter 2 (or RF conversion by the image processing software) and reproduce the original RGB digital image data. Further, the averaging process performed by the averaging device 6 works to reduce the influence of the dither process on the image data after the dither process.

FIG. 5 is a diagram for explaining the operation of the averaging device 6, showing the output image data of the dither processing circuit 3, P (x, y)
Indicates each pixel.

Since the dither processing is a method of expressing one gradation by a plurality of pixels included in a matrix, the averaging processing unit of the averaging device 6 must be larger than or equal to the matrix size. In other words, the dither matrix size is n × m pixels and the averaging unit processing unit is
Given N × M pixels, the relationship of N ≧ n (≧ 2) and M ≧ m (≧ 2) is required. If this is not satisfied, the effect of the averager 6 will be reduced.

The range from P (1,1) to P (N, M) shown in FIG. 5 is the minimum unit of the averaging process, and the average value Pave of the block is calculated by the following equation. Pave = ΣΣP (x, y) / (N × M) (1) However, the first Σ operation is y = 1 to M, and the second Σ operation is x = 1 to N.

By obtaining the average value Pave of each block in this way, it is possible to eliminate the influence of dither processing, so that it is possible to perform nonlinear conversion thereafter. That is, the γ table 7 that performs the non-linear conversion can obtain the image data that is close to the input image data, so that the recognition accuracy of the specific image by the image recognition circuit 8 can be improved.

As described above, according to the present embodiment, it is possible to accurately recognize the image of the specific original from the YMCK or YMC image data subjected to the RF conversion. It is possible to prevent printing that is faithful to the input image data by interrupting the printing.

[0030]

Second Embodiment Hereinafter, an image processing apparatus according to a second embodiment of the present invention will be described. In the second embodiment,
The same components as those in the first embodiment are denoted by the same reference numerals, and detailed description thereof will be omitted.

FIG. 6 is a block diagram showing an example of the arrangement of an image processing apparatus according to the second embodiment of the present invention. The difference from the configuration of the first embodiment shown in FIG. 2 is that, instead of the averaging device 6, a low-pass filter (LPF) 9 for band-limiting the input image data in a two-dimensional space is provided. . LP
Since F9 passes the low-frequency component of the image space and suppresses the high-frequency component, it is possible to reduce the influence of the dither processing circuit 3, and as with the first embodiment, the dither-processed image data is used. Even if there is, the specific image can be accurately recognized. The pass band of LPF9 needs to be lower than the dither band, and if this is not satisfied, the effect of LPF will be reduced.

[0032]

[Other Embodiments] Even if the present invention is applied to a system including a plurality of devices (for example, a host computer, an interface device, a reader, a printer, etc.), an apparatus (for example, a copying machine) Machine, facsimile machine, etc.).

An object of the present invention is to provide a storage medium storing a program code of software for realizing the functions of the above-described embodiments to a system or an apparatus, and to provide a computer (or a CPU or MPU) of the system or the apparatus.
Needless to say, this can also be achieved by the PU) reading and executing the program code stored in the storage medium. In this case, the program code itself read from the storage medium implements the functions of the above-described embodiment, and the storage medium storing the program code constitutes the present invention. Examples of the storage medium for supplying the program code include a floppy disk, a hard disk, an optical disk, a magneto-optical disk, a CD-ROM,
CD-R, magnetic tape, non-volatile memory card, ROM, etc. can be used.

Moreover, not only the functions of the above-described embodiments are realized by executing the program code read by the computer, but also the OS (operating system) running on the computer based on the instructions of the program code. It is needless to say that this also includes a case where the above) performs a part or all of the actual processing and the processing realizes the functions of the above-described embodiments.

Further, after the program code read from the storage medium is written in the memory provided in the function expansion card inserted in the computer or the function expansion unit connected to the computer, based on the instruction of the program code, It goes without saying that a case where the CPU included in the function expansion card or the function expansion unit performs some or all of the actual processing and the processing realizes the functions of the above-described embodiments is also included.

Further, in the above-described embodiment, the example in which the dither processing is used as the area gradation method has been described, but the same is true for the halftone processing based on the area gradation principle such as the error diffusion method. It goes without saying that the effect can be obtained.

The inverse halftone processing is not limited to averaging and low-pass filtering, and it is sufficient if the image data before the halftone processing can be substantially restored, and it is easy to recognize the image even if it is not completely restored. It is enough if it can be converted back to the data of.

[0038]

As described above, according to the present invention,
It is possible to provide an image processing apparatus and method capable of performing highly accurate image recognition from image data that has undergone halftone processing.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a configuration example of a printer that performs dither processing,

FIG. 2 is a diagram showing a general relationship between a luminance signal and a density signal,

FIG. 3 is a diagram for explaining brightness-density conversion and dither processing;

FIG. 4 is a block diagram showing a configuration example of an image processing apparatus according to an embodiment of the invention.

5 is a diagram for explaining the operation of the averaging device shown in FIG. 4,

FIG. 6 is a block diagram showing a configuration example of an image processing apparatus of a second embodiment according to the present invention.

Claims (11)

[Claims] 1. Input means for inputting halftone processed image data, inverse halftone processing means for subjecting the halftone processed image data to inverse halftone processing, and the inverse halftone processed image data. An image processing apparatus comprising: a recognition unit that recognizes whether or not the image represented by is a specific image. 2. Processing means for performing color space conversion and correction processing on input image data, halftone processing means for performing halftone processing on the image data subjected to the color space conversion and correction processing, and the halftone Inverse halftone processing means for performing inverse halftone processing on the processed image data, inverse processing means for performing inverse processing of the color space conversion and correction processing on the image data subjected to inverse halftone processing, and the inverse processing A recognition unit that recognizes the image represented by the image data, and an output unit that controls the output of the image data that has been subjected to the color space conversion and correction processing based on the recognition result obtained by the recognition unit. A characteristic image processing device. 3. The inverse halftone processing means performs averaging processing on the input image data.
Alternatively, the image processing apparatus according to claim 2. 4. The image processing apparatus according to claim 3, wherein the halftone processing is dither processing, and an averaging unit of the averaging processing is equal to or larger than the dither processing unit. 5. The inverse halftone processing means performs low-pass processing on the input image data.
The image processing apparatus according to claim 1 or claim 2. 6. The image processing apparatus according to claim 1, wherein the halftone processing is area gradation processing. 7. The image processing according to claim 2, wherein when the recognition unit recognizes the image of the specific document, the output unit does not output the image data processed by the processing unit. apparatus. 8. The image processing apparatus according to claim 2, wherein the color space conversion is conversion from a luminance color space to a density color space. 9. The image processing apparatus according to claim 2, wherein the correction processing includes UCR, masking, and density correction processing. 10. An input step of inputting halftone-processed image data, an inverse halftone processing step of subjecting the halftone-processed image data to inverse halftone processing, and the inverse halftone-processed image data. An image processing method, comprising: a recognition step of recognizing whether or not the represented image is a specific image. 11. A processing step of performing color space conversion and correction processing on input image data, a halftone processing step of performing halftone processing of the image data subjected to the color space conversion and correction processing, and the halftone processing. An inverse halftone processing step of performing inverse halftone processing on the image data, an inverse processing step of performing inverse processing of the color space conversion and correction processing on the image data subjected to inverse halftone processing, and the inverse processed image data An image processing method comprising: a recognition step of recognizing an image to be represented; and an output step of controlling an output of the image data subjected to the color space conversion and correction processing based on the recognition result obtained in the recognition step. .