JP2001167267A - Image processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To perform recognition processing for preventing the forgery of paper money or securities. SOLUTION: Concerning the image processor having a function for recognizing a specified original in an image, with which resolution is lowered by performing density conversion, the recognition rate of the specified original is improved. Image reading is performed for reading the image by scanning the original, the density conversion of the read images is performed by plural density converting means 211-21n, one of output images from these plural density converting means is selectively switched by a selector 214 and it is recognized by a feature amount comparing part 217 whether the specified original is included in the selected output image or not.

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 for performing recognition processing for preventing forgery of bills, securities, and the like.

[0002]

2. Description of the Related Art In recent years, as the image quality of a color image processing apparatus such as a full-color copying machine has been improved, the risk of forgery of originals (hereinafter referred to as "specific originals") such as banknotes and securities whose copying is prohibited has increased. I have. In order to prevent such an action, a full-color copying machine is equipped with a forgery prevention device that recognizes a specific document from image data obtained by reading the document.

As a method of recognizing a specific document, there is a method disclosed in Japanese Patent Application Laid-Open No. Hei 6-251128, for example. In this method, after data with reduced resolution is formed, recognition processing of a specific document is performed by performing edge extraction and pattern matching. Thus, when recognizing a specific document based on the image data of the read document,
The recognition rate of a specific document may decrease due to a difference in the reading characteristics of the image reading devices from one device to another or the state of the image reading device when reading the document.

[0004]

SUMMARY OF THE INVENTION An object of the present invention is to improve the recognition rate of a specific document in an image processing apparatus having a function of recognizing a specific document with respect to an image whose resolution has been lowered by performing density conversion. That is.

[0005]

According to the first aspect of the present invention, there is provided image reading means for reading an image by scanning a document,
A plurality of density conversion means for performing density conversion of the image; a control means for selecting and switching one of output images of the plurality of density conversion means; and a specific original in the output image selected by the control means. And a recognition means for recognizing whether or not it is included.

According to a second aspect of the present invention, in the first aspect of the present invention, the recognizing means performs the recognizing process a plurality of times, during which the control means switches the output image of the density conversion at least once. It is characterized by.

In a third aspect of the present invention, in the second aspect of the present invention, the image processing apparatus further comprises storage means for storing the image read by the image reading means.
After the first time, the density conversion and the recognition processing are performed on the output image from the storage means.

According to a fourth aspect of the present invention, in the first aspect of the present invention, there is provided an image processing means for performing image processing on a read image, and an image forming means for forming an image based on the processed image. And control means for changing the control so that normal image formation is not performed when the specific document is recognized by the recognition means.

[0009]

According to a first aspect of the present invention, there is provided an image processing apparatus comprising: means for performing a plurality of density conversions; and control means for selecting one of output images of the plurality of density conversion means. The user can select the converted image.

[0010] In the image processing apparatus according to the second aspect,
Recognition processing is performed a plurality of times, during which the control unit switches the output image of the density conversion.

In the image processing apparatus according to the third aspect,
The image processing apparatus includes a storage unit that stores an image, and performs the density conversion and the recognition process on the image from the storage unit in the second and subsequent times in the plurality of recognition processes.

[0012] In the image processing apparatus according to the fourth aspect,
There is provided control means for controlling so that a normal image is not formed when the specific document is recognized by the recognition means.

(Embodiment) A one-drum digital full-color copying machine will be described as an example of an image processing apparatus to which the present invention is applied. FIG. 1 is a block diagram of a digital full-color copying machine showing an embodiment of the present invention. A scanner 100 scans an original, converts the original into digital image data, and outputs RGB data. The image processing unit 200 performs a process such as a filter or color correction on the RGB data input from the scanner, and outputs any one of CMYK signals to the printer. In the case of the one-drum system, any one of the CMYK components is sent to the printer 300. Therefore, in the case of black and white, the image processing of K only is performed once, and in the case of color, the image processing is performed four times in total. The printer 300 forms an image according to output data from the image processing unit 200. One printout is completed by a total of four image formations of only K for black and white and CMYK for color. Operation unit 50
Reference numeral 0 denotes an input device for the operator to select a copy mode, set the number of copies, and the like, and includes various keys and a touch panel on a display unit. The display unit 600
This is a display device for displaying a setting state, giving a setting instruction to a user, and the like. The ADF 700 is disposed above the scanner, and sequentially transports documents on a document table to the scanner. The system control unit 400 is configured by a microcomputer or the like, and outputs a signal for controlling the operation of the entire apparatus according to a program stored in advance in a ROM or the like.

Next, the configuration of the first embodiment of the image processing section 200 shown in FIG. 1 will be described with reference to FIG. In the configuration shown in FIG. 2, the image memory is not used, and therefore, in order to perform the recognition processing a plurality of times, the original is scanned by the number of times. The scanner 100 outputs R, G, and B digital signals obtained by reading the document. The density converter 201 converts R, G, and B reflected light data from the scanner into density data using a look-up table. The filter unit 202 performs an operation from the pixel of interest and its surrounding pixels, and performs image correction such as smoothing and edge enhancement. The color correction unit 203 performs color correction (masking) to remove the turbid component of the color separation filter of the scanner and the turbid component of the colorant, and outputs a signal that has been subjected to under color removal processing (UCR processing). The selector 204 selects one of C, M, Y, and K under the control of the IPU control unit, and outputs it to the gradation correction unit. The gradation correction unit 205 is a printer 3
The density is corrected using a look-up table in accordance with the characteristic of “00”. The gradation processing unit 206 performs gradation processing such as dither processing and outputs C, M, Y, and K signals.
In the printer 300, C, M, Y, K
Upon receiving the signal, a color image is formed. IPU control unit 2
Reference numeral 20 controls the entire image processing unit, sets parameters of each processing unit, and the like. The recognition processing unit 210 determines whether or not a specific document is included from the data of the document read by the scanner. If it is determined that the specific document is included, the result is determined by the IPU control unit. Output to

Next, the configuration of the recognition processing unit 210 shown in FIG. 2 will be described with reference to FIG. Recognition processing unit 210
, Either image data read by the scanner 100 or image data stored in the memory is input. The input image is processed by a plurality of density conversion units 211 and 21.
2,. . . 21n (density conversion units 1, density conversion units 2,..., Density conversion units n) perform different density conversion processes, and output the image data after the density conversion to the selector. The selector 214 selects and outputs one of a plurality of image data after density conversion according to the setting from the recognition control unit. The feature amount extraction unit 215 extracts the feature amount of the image from the image data selected by the selector. The feature amount holding unit 216 holds dictionary data of feature amounts of a specific document. The feature amount comparison unit 217 compares the dictionary data of the feature amount held in the feature amount holding unit 216 with the feature amount extracted from the input image, and outputs the result to the recognition control unit. The recognition processing unit 218 controls a selector, sets parameters of each processing unit, outputs a comparison result from the feature amount comparison unit to the IPU control unit, and the like.

Next, a method of density conversion in the density conversion unit in the recognition processing unit will be described with reference to FIGS. The density conversion method includes (1) the nearest neighbor interpolation method (FIG. 4), (2) linear interpolation method (FIG. 5), and (3) convolution method (FIG. 6).

In the nearest neighbor interpolation method of (1), the pixel closest to the virtual point is set as the pixel value of the virtual point. In FIG. 4, the value of the virtual point f is b or c depending on the distance x of the virtual point from one pixel before the virtual point.

In the linear interpolation method (2), the pixel value of the virtual point is calculated by linearly interpolating the data of each pixel before and after the virtual point. In FIG. 5, when the distance of the virtual point from one pixel before the virtual point f is x, it can be calculated by the following equation. f = (1-x) * b + x * c

In the convolution method (3), a pixel value of a virtual point is calculated based on data of two pixels before and after the virtual point. In FIG. 6, it can be calculated by the following equation. , F = k0 * a + k1 * b + k2 * c + k4 * d In this equation, k0, k1, k2, and k3 are coefficients determined by the distance from one pixel before the virtual point f to the virtual point,
Assuming that the distance of the virtual point from one pixel before the virtual point is x,
Table 1 below.

[0020]

[Table 1]

In the density conversion unit, first, the density conversion in the main scanning direction is converted by using the above-described method and the like, and the density conversion in the sub-scanning is performed in the same manner. Generate In addition, a method other than the above may be used as the method of density conversion.

Next, the flow of the operation of the recognition processing in the first embodiment of the image processing section 200 will be described with reference to the flowchart of FIG. First, a density conversion process to be performed is selected in the recognition processing unit (S1). Next, an image is read (S2). At this time, in the recognition processing unit, the selected image subjected to the density conversion is simultaneously generated, and the recognition processing is performed (S3). If the recognition is performed a plurality of times and the recognition has not been completed yet (S4-NO), the selection of the density conversion processing and the reading of the image are repeated again. When the recognition processing is completed a plurality of times (S4-YES), and as a result, when it is determined that the specific document is included in the input image (S5-YES), the output is stopped or the image is deleted. Then, normal output is not performed (S6). If it is determined that the specific document is not included (S5-N
O) Normal output is performed (S7).

Next, the configuration of a second embodiment of the image processing section 200 will be described with reference to FIG. In the configuration shown in FIG. 8, the image processing unit 200 includes an image memory 207 and an input selection unit 208 for holding the read image data, and the image is read only once by scanning the original, and thereafter, During the recognition process, image data is output from the image memory. Except for the image input part, the first
Since the third embodiment is the same as the first embodiment, the description other than the different parts will be omitted.

The scanner 100 outputs R, G, and B image data obtained by reading a document. This image data is simultaneously stored in the image memory. Image memory 207
Saves the read image when the image is read by the scanner, and outputs the second and subsequent images when performing the recognition processing a plurality of times. The input selection unit 208 selects and outputs either the output from the scanner or the output from the image memory under the control of the IPU control unit. That is, the image is output from the scanner when the image is read by the scanner, and the image is output from the image memory during the second and subsequent processes. Each process after the input selection unit is the same as in the first embodiment.

Next, the flow of the operation of the recognition processing in the second embodiment of the image processing section 200 will be described with reference to FIG. First, an image is read (S11). On this occasion,
At the same time, the image data is stored in the image memory. Also,
In the recognition processing unit, a density conversion process which is initialized in advance is selected (S12), and a recognition process (S14) is performed on the image (S13) after the density conversion. When the recognition is performed a plurality of times, the second and subsequent processes are (S1
5-NO), selection of density conversion processing, image output from the memory, and recognition processing are repeated for the output image from the image memory. When the recognition process is completed a plurality of times, and as a result, when it is determined that the specific document is included in the input image (S15-YES), the output is stopped or the image is deleted (S17), and the normal operation is performed. Output is not performed. If it is determined that the specific document is not included (S15-N
O) Normal output is performed (S18).

[0026]

According to the first aspect of the present invention, one of the outputs of a plurality of density conversion means is selected, and the output is subjected to a recognition process. The recognition process can be performed on the output, and the recognition rate of the specific document can be improved.

(Effect of Claim 2) Since the output images of the plurality of density conversion means are switched during the plurality of recognition processes, the recognition process is performed on a plurality of images having different image characteristics. Can be performed, and the recognition rate of the specific document can be improved.

(Effect of Claim 3) Since the image is stored in the storage device and the output from the image is subjected to the recognition processing a plurality of times after the second time, the image is read only once. It is possible to obtain the operation and effect of claim 2 even in an image processing apparatus having no image processing apparatus.

(Effect of Claim 4) When a specific document is recognized by the recognition means, control is performed so as not to form a normal image, thereby preventing counterfeiting of bills and securities. Can be.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating an example of a digital full-color copying machine to which the present invention is applied.

FIG. 2 is a block diagram for explaining a configuration of a first embodiment of the image processing unit 200 shown in FIG.

FIG. 3 is a block diagram illustrating a configuration of a recognition processing unit 210 illustrated in FIG. 2;

FIG. 4 is a diagram for explaining a density conversion method (nearest neighbor interpolation method) in a density conversion unit in the recognition processing unit.

FIG. 5 is a diagram for explaining another method (linear interpolation method) of the density conversion in the density conversion unit in the recognition processing unit.

FIG. 6 is a diagram for explaining another method (convolution method) of the density conversion in the density conversion unit in the recognition processing unit.

FIG. 7 is a flowchart for explaining an operation flow of a recognition process in the first embodiment of the image processing unit 200;

FIG. 8 is a block diagram illustrating a configuration of a second embodiment of the image processing unit 200.

FIG. 9 is a flowchart illustrating a flow of an operation of a recognition process in a second embodiment of the image processing unit 200;

[Explanation of symbols]

100: scanner, 200: image processing unit, 201: density conversion unit, 202: filter unit, 203: color correction unit, 20
4 selector 205 205 gradation correction unit 206 gradation processing unit 207 image memory 208 input selection unit 210
... Recognition processing unit, 220 ... IPU control unit, 300 ... Printer, 400 ... System control unit, 500 ... Operation unit, 600
... Display unit, 700 ... ADF.

──────────────────────────────────────────────────続 き Continued on the front page (51) Int.Cl. ⁷ Identification symbol FI theme coat ゛ (reference) // B41J 29/00 G06F 15/66 355C 5C076 15/70 460B 5L096 B41J 29/00 ZF term (reference) 2C061 AP04 AR01 HK11 HN22 2H027 DB02 EJ03 EK03 2H034 FA03 3E041 AA01 AA02 AA03 BA11 BB01 BC06 CA01 DB01 5B057 BA02 CA01 CA08 CA12 CA16 CB01 CB08 CB12 CB16 BA03 BA09 A03B02 A EA03 EA33 JA11

Claims (4)

[Claims] An image reading unit that scans an original to read an image; a plurality of density conversion units that perform density conversion of the image; and one of output images of the plurality of density conversion units. An image processing apparatus, comprising: a control unit that switches the output image and a recognition unit that recognizes whether a specific document is included in an output image selected by the control unit. 2. The apparatus according to claim 1, wherein the recognizing unit performs the recognizing process a plurality of times, and in the meantime, the control unit switches the output image of the density conversion at least once.
An image processing apparatus according to claim 1. 3. A storage unit for storing an image read by the image reading unit, and performing a density conversion and a recognition process on an output image from the storage unit in the second and subsequent times in a plurality of recognition processes. The image processing apparatus according to claim 2, wherein: 4. An image processing unit for performing image processing on a read image, an image forming unit for forming an image based on the processed image, and a normal document when the specific document is recognized by the recognition unit. The image processing apparatus according to claim 1, further comprising a control unit configured to change control so that image formation is not performed.