JPH0670158A - Image processor - Google Patents

Abstract

PURPOSE:To prevent the forgery of the notes, the securities, etc., and also to improve the working efficiency of an image processor by deciding the fixed line width and then detecting whether the number of lines having the fixed width is larger than a prescribed level or not. CONSTITUTION:The thin lines and the isolated points are extracted with a logical operation (AND) carried out between the original binary data and the data carried out both thinning and thickening processing operations. Then an extracting circuit 109 tracks a contour to exclude the isolated points owing to their small loops. Thus only the thin line information exists. In this case, a fact whether a thin line exists or not can be decided based on the contour tracking result or by counting the data stored in a (bit map) memory 110. Finally it is decided whether the thin lines exist or not in a prescribed area at a fixed rate or mote. If so, an intaglio is decided and various image processing operations are carried out so that a normal image is not obtainable. Thus the forgery of a special original can be prevented.

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 discriminating special originals such as banknotes and securities and preventing forgery of the special originals. The present invention relates to an image processing device that surely determines whether a document is a special document by detecting it.

[0002]

2. Description of the Related Art As a conventional image processing apparatus for preventing forgery of banknotes and the like, there is an "image processing apparatus" disclosed in Japanese Patent Application Laid-Open No. 2-210591. This image processing apparatus includes a detection unit for detecting the position state of an original document, and a determination unit for extracting image data of a specific portion in the original document according to the detection by the detection unit and determining the degree of similarity with a pattern registered in advance. And a specific document is discriminated based on the similarity.

[0003]

However, in the conventional image processing apparatus as described above, since it is determined whether or not it is a bill based on the degree of similarity with a specific pattern registered in advance. , The configuration for improving the accuracy of pattern recognition becomes complicated (for example, the pattern recognition accuracy cannot be improved unless there is a large amount of information about the pattern to be registered in the memory in advance because it is determined only by the similarity). However, when there is noise information such as graffiti on a bill, there is a problem in that misrecognition often occurs and the recognition rate is low. Further, as a result of erroneously recognizing a normal document as a special document, defective copies are unnecessarily discharged, the apparatus is stopped, and the like, and there is a problem that work efficiency is poor.

The present invention has been made in view of the above, and is capable of accurately discriminating a special document such as a banknote with a simple structure, and using a image forming apparatus such as a copying machine to specialize a banknote, a securities, or the like. The purpose is to reliably prevent forgery of originals and improve work efficiency.

[0005]

In order to achieve the above-mentioned object, the image processing apparatus according to the present invention includes a data extracting means for extracting predetermined data from image data read from a document, and an extracting means by the data extracting means. Storage means for storing the predetermined data, shape detection means for detecting the shape of the predetermined data, the shape detected by the shape detection means is a line, and the width of the line is constant. (EN) An image processing apparatus provided with a line discriminating means for discriminating the above and a line number detecting means for detecting whether or not there are a predetermined number or more of lines having a constant width discriminated by the line discriminating means.

Data extracting means for extracting predetermined data from the image data read from the original, storage means for storing the predetermined data extracted by the data extracting means, and the shape of the predetermined data are detected. Shape detecting means; line determining means for determining whether the shape detected by the shape detecting means is a line; and a distance between the lines determined by the line determining means, and whether the line distance is constant. (EN) An image processing device provided with a line interval detecting means for detecting whether or not there is any.

[0007]

The image processing apparatus according to the present invention extracts predetermined data from image data read from an original, stores the extracted predetermined data, detects the shape of the predetermined data, and detects the shape. It is determined that the shape is a line and the width of the line is constant, and it is detected whether or not there are a predetermined number or more of the lines having the determined constant width.

Further, predetermined data is extracted from the image data read from the original, the extracted predetermined data is stored, the shape of the predetermined data is detected, and the detected shape is a line. Is determined, the interval between the determined lines is detected, and whether the line interval is constant is detected.

[0009]

[Embodiment 1] An embodiment of an image processing apparatus according to the present invention will be described below with reference to the drawings. In this embodiment,
Basically, line pattern extraction is executed as a method of detecting an intaglio so that there is halftone dot separation as a method of detecting a lithographic plate. That is, the intaglio printing technique is almost always used for special manuscripts such as bills and securities.
The present invention detects line information in intaglio printing to detect whether or not it is a special document such as a banknote, and executes operation control of copying processing based on the detection result.

The intaglio printing has the following three features. That is, the outline and the shadow of the object are represented by the symmetry with the 1st line → the main line. Line 2 → Add a slightly different angle to the lines to create a three-dimensional feel and texture. Line 3 → Add dots to create a more realistic feeling.

That is, it is possible to determine that the intaglio printing is performed by detecting the length of the image line. In the present embodiment, by extracting the image line data and detecting the width and length of the image line, it is determined that the document is intaglio printing, that is, a special document such as a bill. Since there is nothing else that constitutes an image by using the thin line of the banknote, this thin line is detected. In this embodiment, bills are discriminated when a predetermined number or more of them are within a predetermined area so that they can be distinguished from thin lines such as drawings and graphs.

FIG. 1 is a block diagram showing a schematic configuration of an image processing unit. In FIG. 1, 101 is an MTF for executing MTF correction (lens system blur correction) on data read by a reading sensor (not shown). A correction unit 102 is an RGBγ correction unit for converting logarithmic data into density data, a color correction unit 103 is for executing a primary density masking method (RGB → YMCK), and a scaling unit 104 is for performing a scaling process in the main scanning direction. A processing unit (variable-magnification processing in the sub-scanning direction is executed by a reading system), 105 is a create unit that executes various kinds of processing such as mirroring, slanting, shadowing, and hollowing, and 106 is a density data corresponding to a printer. YMCKγ to execute the γ correction
A correction unit 107 is a filter that executes a sharpening process and a smoothing process according to an original document, and a tone processing unit 108 is a gradation processing unit that executes a halftone process (dithering) for a printer.
Extracts predetermined area data from the R, G, B data signals input from the MTF correction unit 101, converts multivalued data into binary data, executes thin line and isolated point extraction, and performs contour tracking processing. Extraction circuit to be executed, 110 is extraction circuit 10
9 is a memory for storing the binary data output from 9.

The operation of the above configuration will be described. The MTF correction unit 101 performs MTF correction (blurring correction of the lens system) on the data read by the reading sensor, the RGBγ correction unit 102 converts logarithmic data into density data, and the color correction unit 103 performs the primary density masking method. (RGB → YMCK) is executed. After that, the scaling processing unit 104 performs scaling processing in the main scanning direction,
Further, after various processings such as mirroring, italicizing, shading, and hollowing are performed by the create unit 105, the YMCKγ correction unit 106 performs γ correction according to the printer on the density data, and the original document is filtered by the filter 107. Depending on the, sharpening processing and smoothing processing are executed. Furthermore, the gradation processing unit 1
08 performs halftone processing (dithering) and outputs image data. A predetermined area of the R, G, B data signals output from the MTF correction unit 101 is extracted by the extraction circuit 109, and the portion is output as binary data and stored in the memory 110.

Next, the detailed configuration and operation of the extraction circuit 109 shown in FIG. 1 will be described. As described above, the extraction circuit 109
In this case, signals other than the white background are extracted from the multi-valued data R, G, B. Here, the luminance signal may be binarized and may be a specific color. In addition, the memory 11
Reference numeral 0 is a bit map memory for writing the binary data input from the extraction circuit 109. After reading the output to the memory 110, the extraction circuit 109 executes the processing operation of the flowchart shown in FIG. 2 in order to extract the thin line and the isolated point.

That is, in the pattern of the thinning process (S201), when the data of the 5 × 5 circle portion shown in FIG.
If there is no data, erase the data. The pattern of the thickening process (S202) is as shown in FIG.
When at least the 5 × 5 circle data shown in (3) exists, the data is made to exist also in the central pixel.

Next, the original binary data and the data subjected to the thinning process (S201) and the thickening process (S202) are logically ANDed (S203) to extract thin lines and isolated points. To do. As described above, the thinning pattern and the thickening pattern are formed in different patterns in order to prevent the generation of unnecessary isolated points, and the same pattern or different patterns may be used as necessary.

Next, the extraction circuit 109 executes contour tracking. By this contour tracking, isolated points can be excluded because the loop is small. As a result, only the thin line information remains. The determination as to whether or not there is a thin line may be the result of contour tracing, or may be counting the data in the (bitmap) memory 110. Finally, it is judged whether a thin line is present in a predetermined area at a certain ratio or more, and if it is present, it is judged as an intaglio, and various image processing is performed so that a normal image cannot be obtained. ， Prevents forgery of special manuscripts.

In the present embodiment, the thin line has a width of 2 pixels or less, but the width can be set to any number by changing the processing parameters of the flowchart shown in FIG. When it is desired to exclude a width equal to or smaller than the width, removal of isolated points of n pixels may be further executed. Further, when detecting n pixels, fine line detection can also be performed using pattern matching.

FIG. 5 is a flow chart schematically showing the operation of the above embodiment. First, the bill flag is reset (S501). Next, as described above, thin lines and isolated points are extracted /
The contour tracking is executed (S502), and then it is determined whether or not there are a predetermined number or more of fine lines in the predetermined area (S50).
3). As a result, if it is determined that there are a predetermined number or more of thin lines in the predetermined area, it is determined that the original is not a special original such as a bill, and the bill flag is set (S504). On the other hand, if it is determined that there are not more than the predetermined number of thin lines in the predetermined area, it is determined that the document is a special document such as a banknote and the banknote flag is reset (S505).

[Embodiment 2] In the above embodiment, it is determined whether there are a predetermined number or more of fine lines in a predetermined area to determine whether the original is a special original such as a bill. However, in another embodiment according to the present invention, it is determined whether the document is a special document such as a bill by detecting the interval between the thin lines and determining whether the detected interval between the thin lines is constant. This utilizes the fact that in intaglio printed matter such as banknotes, the intervals between the plurality of thin lines used are not constant.

FIG. 6 is a flow chart schematically showing the operation of the second embodiment. First, the bill flag is reset (S601). Next, thin line / isolated point extraction / contour tracing is executed in the same manner as in the first embodiment (S602), and then it is determined whether or not the interval between the fine lines is constant (S603).
As a result, when it is determined that the intervals between the thin lines are not constant, it is determined that the document is a special document such as a banknote and the banknote flag is set (S604). On the contrary, when it is determined that the interval between the thin lines is constant, it is determined that the document is not a special document such as a banknote and the banknote flag is reset (S60).
5) It is.

As described above, according to the image processing apparatus of the present invention, the predetermined data is extracted from the image data read from the document, the extracted predetermined data is stored, and the predetermined data is stored. To detect a shape, determine that the detected shape is a line, and that the width of the line is constant, and detect whether or not there is a predetermined number or more of lines of the determined constant width. , Extracting predetermined data from the image data read from the original, storing the extracted predetermined data, and detecting the shape of the predetermined data,
It is determined that the detected shape is a line, the interval between the determined lines is detected, and whether or not the line interval is constant is detected. It is possible to discriminate whether the document is a document or not, it is possible to reliably prevent forgery of special documents such as banknotes and securities using an image forming apparatus such as a copying machine, and it is possible to improve work efficiency.

[Brief description of drawings]

FIG. 1 is a block diagram showing a schematic configuration of an image processing apparatus according to the present invention.

FIG. 2 is a flowchart showing a processing operation for extracting thin lines and isolated points by the extraction circuit shown in FIG.

FIG. 3 is an explanatory diagram showing a pattern of the thinning process shown in FIG.

FIG. 4 is an explanatory diagram showing a thickening pattern shown in FIG.

FIG. 5 is a flowchart showing a schematic operation (Example 1) of the image forming apparatus according to the present invention.

FIG. 6 is a flowchart showing a schematic operation (second embodiment) of the image forming apparatus according to the present invention.

[Explanation of symbols]

101 MTF Correction Unit 109 Extraction Circuit 110 Memory

Claims (2)

[Claims] 1. A data extracting means for extracting predetermined data from image data read from an original, a storage means for storing the predetermined data extracted by the data extracting means, and a shape of the predetermined data. A shape detecting means, a line determining means for determining that the shape detected by the shape detecting means is a line, and a width of the line is constant; and a line having a constant width determined by the line determining means An image processing apparatus comprising: a line number detecting means for detecting whether or not there are a predetermined number or more. 2. A data extracting means for extracting predetermined data from image data read from a document, a storage means for storing the predetermined data extracted by the data extracting means, and a shape of the predetermined data. Shape detecting means; line determining means for determining whether the shape detected by the shape detecting means is a line; and a distance between the lines determined by the line determining means, and whether the line distance is constant. An image processing apparatus, comprising: a line interval detecting means for detecting whether or not there is any.