JP2000048201A - Picture processor - Google Patents

Abstract

PROBLEM TO BE SOLVED: To reduce a decision time for an output prohibited document and to make the picture processor applicable to a device which performs only reading scanning with a single document at a time. SOLUTION: A binarization part 21 cuts out a picture in a color area of a comparison decision object from color picture data as a binary picture and a pattern matching part 22 decides similarity between the cut out binary picture and a reference pattern. When the pattern matching part 22 decides that there is the similarity, a comparison decision part 27 compares the cut out binary picture with vector font data or stroke font data stored in a vector data memory storage part 25 and decides whether they coincide with each other 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 preventing the output of a document such as a bill or a security document whose copying or printing is prohibited.

[0002]

2. Description of the Related Art With the recent technical improvement of full-color copying apparatuses, the image quality of a copied image has reached a level where it is considered to be almost equal to that of an original image. Moreover, color copying is easy,
Because of the low cost, forgery of manuscripts whose copying and printing are prohibited, such as banknotes and securities, has become a social problem.
Accordingly, many devices for preventing such forgery have been developed.

A conventional example of this type is disclosed in, for example,
As described in Japanese Patent Application Laid-Open No. 143334, in a device that performs a plurality of reading scans on one document, the similarity of a copy-inhibited document is detected based on a predetermined criterion during the first reading, and the similarity is detected during the second reading. A method in which the similarity of a copy-forbidden document is detected based on another criterion, and the reference is changed for each of a plurality of readings, and whether or not the document is a copy-forbidden document is determined by comprehensive determination of the similarity detection for a plurality of times. Has been proposed.

[0004]

However, in the above-mentioned prior art, the reference is changed for each of a plurality of readings, and whether or not the document is a copy-inhibited document is determined by comprehensive determination of similarity detection a plurality of times. And it cannot be applied to an apparatus that performs only one reading scan for one document.

The present invention has been made in view of the above-described problems of the prior art, and can be applied to an apparatus which can reduce the time required to determine an output-inhibited document and performs only one reading scan for one document. It is an object of the present invention to provide an image processing apparatus capable of performing the above.

[0006]

In order to achieve the above object, a first means is a clipping means for clipping an image of a color area to be compared and judged as binary image from input color image data, and the clipping means. Determining means for determining the similarity between the binary image cut out by the method and the reference pattern; storage means for storing the reference binary image to be compared with the comparison determination target as vector font data or stroke font data; When it is determined that there is similarity, the binary image cut out by the cutout means is compared with the vector font data or the stroke font data stored in the storage means to determine whether or not they match. And a comparing and judging means.

[0007] The second means is the first means, wherein the storage means is further provided with a reference 2 for comparison with an object to be compared.
The vector font data or the stroke font data of the non-image area of the value image is stored, and the comparing and judging means further includes a non-image area of the binary image cut out by the cutting means and a non-image area stored in the storage means. It is characterized in that vector font data or stroke font data in an image area is compared to determine whether they match.

A third means is that, in the first and second means, the storage means further stores a priority of vector font data or stroke font data, and the comparing and judging means further has a higher priority. It is characterized in that comparison is performed first from vector font data or stroke font data.

[0009]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a block diagram showing an embodiment of an image processing apparatus according to the present invention, FIG. 2 is a block diagram showing a binarizing unit in FIG. 1 in detail, FIG. 3 is an explanatory diagram showing an RGB color space, and FIG. 5 and 6 are explanatory diagrams schematically showing vector data stored in the vector data memory storage unit of FIG. 1, and FIG. 7 is a vector data memory storage of FIG. FIG. 8 is an explanatory diagram schematically showing a state in which vector data stored in a unit is rotated, FIG. 8 is an explanatory diagram showing a process of rotating vector data stored in a vector data memory storage unit in FIG. 1, and FIG. 2 is a flowchart for explaining an identification process of a comparison determination unit in FIG. 1.

The image processing apparatus shown in FIG. 1 is configured to output an identification result indicating whether or not a read original is an output-inhibited original based on an RGB digital image signal read by a color image reading unit (not shown). Have been. This apparatus can be used, for example, as a determination circuit of a color copying machine disclosed in Japanese Patent Application Laid-Open No. Hei 7-143334,
The present invention can also be applied to an apparatus that performs only one reading scan for one document.

The input RGB data is, for example, a signal read at 400 dpi in the main scanning direction and the sub-scanning direction.
A color image to be compared and determined in the original, which is applied to the binarization unit 21 shown in detail in FIG. 2, for example, vermilion Bank of Japan stamp data printed on a banknote is cut out. 2 shown in FIG.
In the value conversion unit 21, the R data and its upper limit are compared by a comparator 31R-1, and the output signal is R data <
High when at the upper limit. The R data and its lower limit are compared by the comparator 31R-2, and the output signal becomes high when R data> lower limit. And
Each output signal of the comparators 31R-1 and 31R-2 is A
The signal is applied to the AND gate 33 via the ND gate 32R.

Similarly, the G data and its upper limit are compared by the comparator 31G-1, and the output signal becomes high when G data <upper limit. The G data and its lower limit are compared by the comparator 31G-2, and the output signal becomes high when G data> lower limit. Then, each output signal of the comparators 31G-1 and 31G-2 is applied to the AND gate 33 via the AND gate 32G.

Similarly, the B data and its upper limit are compared by the comparator 31B-1, and the output signal becomes high when B data <upper limit. The B data and its lower limit are compared by the comparator 31B-2, and the output signal becomes high when B data> lower limit. Then, each output signal of the comparators 31B-1 and 31B-2 is applied to the AND gate 33 via the AND gate 32B.

Here, when the RGB data are both 8 bits, (R, G, B) is (0, 0, 0) as shown in FIG.
To (255, 255, 255). Also,
When (R, G, B) = (0, 0, 0), the color is black, and (R, G, B) = (255, 255, 25)
In the case of 5), the color is pure white. Therefore, when the target red mark is the color range a shown in FIG. 3, for example, detection can be performed under the condition of 100 ≦ R ≦ 160 20 ≦ G ≦ 40 10 ≦ B ≦ 30. The output signal (binary data) is high (red pixel, black pixel) when the above condition is satisfied, and low (non-red pixel, white pixel) when the above condition is not satisfied.

The binarized data is applied to a pattern matching section 22 and a buffer memory control section 23 as shown in FIG. The pattern matching unit 22 detects whether or not it is a red seal by, for example, matching the outer frame with a round red seal as shown in FIG. 4 and the character “day” therein with the reference pattern. In the case of the red seal, the detection signal b = 1 Is notified to the buffer memory control unit 23 and the comparison determination unit 27. The buffer memory control unit 23 writes the input binarized data into the buffer memory 24 having a capacity capable of storing the seal data, and in this case, overwrites so that the latest data is always held in the buffer memory 24.

When the detection signal b = 1 is input from the pattern matching unit 22, the buffer memory control unit 23 stops writing the input binary data to the buffer memory 24. That is, the pattern matching unit 22
The timing at which the detection signal b = 1 is output coincides with the timing at which all the red seal data is written to the buffer memory 24. When the buffer memory control unit 23 stops writing, all the red seal data are buffered. The state is stored in the memory 24.

The comparison / determination unit 27 detects the detection signal b = 1.
Is input, the seal data stored in the buffer memory controller 23 is compared with the seal data and the vector data (θ, l) of the seal stored in the vector data memory storage 25, and the identification result is output. I do. At this time, the vector data operation unit 26 outputs the vector data (θ,
The reading of l) and the rotation processing described later are performed.

The vector data memory storage unit 25 stores 13 Xs on the stroke of the character "day" shown in FIG.
Vector font data or stroke font data (hereinafter, vector data) at Y coordinate points "1" to "13" and their priority data "0" and "1" are stored as shown in FIG. As shown in (B), vector data of a non-image portion in the outer frame is stored. Here, the priority data “0” and “1” indicate whether or not the feature of the character is represented more. The priority of the priority data “0” is higher than “1”. Therefore, when performing the comparison, the comparison determination unit 27 first compares the XY coordinate points “1”, “3”, “7”, “9”, and “13” of the high priority data “0”. Also, XY of low priority data “1”
For the coordinate point, the X of the high priority data "0"
The comparison is performed when all the Y coordinate points match, and the comparison is not performed when any one does not match.

The inclination of the character stored in the vector data memory storage 25 is, as shown in FIG.
0. However, in practice, various angles are expected depending on how the original is placed on the contact glass of the scanner, the stamping angle of the red seal, and the like. Therefore, the XY coordinate points “1”, “3”,
When comparing “7”, “9”, and “13” first, the vector data operation unit 26 reads the vector data stored in the vector data memory storage unit 25 as shown in FIGS. Then, the rotation is performed according to the angle θ required by the comparison determination unit 27 and output to the comparison determination unit 27.

Next, the identification processing of the comparison / determination section 27 will be described with reference to FIG. First, the vector data at the XY coordinate point of the priority data "0" is read (step S1), and "0" is set as the rotation angle ANG of the vector data (step S2). Next, the vector data is rotated by the rotation angle ANG (step S).
3) Then, the data is compared with the data in the buffer memory 24 (step S4). If they do not match, the rotation angle ANG is set to ANG + n (step S5 → S
6) Then, the process returns to step S3 to repeat the above processing.

Then, all XY of the priority data "0"
The coordinate points are compared and rotated, and if they match, the process proceeds to step S7 and the following. If all do not match, the process proceeds to step S11 to determine that "the data in the buffer memory 24 and the vector data do not match".

In step S7 and subsequent steps, priority data "1"
Is read out (step S7), the vector data is rotated similarly to the priority data "0" (step S8), and then compared with the data in the buffer memory 24 (step S7).
9). Then, the comparison and rotation are performed for all the XY coordinate points of the priority data “0”, and when they all match, it is determined that “the data in the buffer memory 24 and the vector data match” (step S10 → S12). If even one of them matches, it is determined that "the data in the buffer memory 24 does not match the vector data" (step S10).
→ S11).

[0023]

As described above, according to the first aspect of the present invention, the binary image which is determined to have similarity and is cut out is compared with the vector font data or the stroke font data. It is possible to shorten the time required to determine the output prohibition document, and to apply the present invention to an apparatus that performs only one reading scan on one document.

According to the second aspect of the invention, the non-image area of the binary image is compared with the vector font data or the stroke font data of the non-image area. Further, the present invention can be applied to an apparatus that performs only one reading scan for one document.

According to the third aspect of the present invention, since the comparison is made first from the vector font data or the stroke font data having the higher priority, the time for determining the output prohibition document can be shortened. The present invention can also be applied to an apparatus that performs only one reading scan on a document.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating an embodiment of an image processing apparatus according to the present invention.

FIG. 2 is a block diagram illustrating a binarizing unit of FIG. 1 in detail;

FIG. 3 is an explanatory diagram showing an RGB color space.

FIG. 4 is an explanatory diagram schematically showing a comparison determination target.

FIG. 5 is an explanatory diagram schematically showing vector data stored in a vector data memory storage unit of FIG. 1;

FIG. 6 is an explanatory diagram schematically showing vector data stored in a vector data memory storage unit in FIG. 1;

FIG. 7 is an explanatory diagram schematically showing a state in which vector data stored in the vector data memory storage unit of FIG. 1 is rotated.

FIG. 8 is an explanatory diagram showing a process of rotating the vector data stored in the vector data memory storage unit of FIG.

FIG. 9 is a flowchart illustrating an identification process of a comparison / determination unit in FIG. 1;

[Explanation of symbols]

 Reference Signs List 21 Binarization section 22 Pattern matching section 23 Buffer memory control section 24 Buffer memory 25 Vector data memory storage section 26 Vector data calculation section 27 Comparison judgment section

Claims (3)

[Claims] 1. A cutout means for cutting out an image of a color area to be compared and judged as binary images from input color image data, and a judgment for judging similarity between a binary image cut out by the cutout means and a reference pattern. Means, a storage means for storing a reference binary image for comparison with a comparison determination target as vector font data or stroke font data, and when the determination means determines that there is similarity,
An image processing apparatus comprising: a binary image clipped by the clipping means; and a comparison determination means for comparing the vector font data or the stroke font data stored in the storage means to determine whether or not they match. . 2. The storage unit further stores vector font data or stroke font data of a non-image area of a reference binary image to be compared with a comparison determination target, and the comparison determination unit further includes the cutout unit Comparing the non-image area of the binary image cut out by the above with the vector font data or the stroke font data of the non-image area stored in the storage means to determine whether or not they match. Item 2. The image processing apparatus according to Item 1. 3. The storage unit further stores a priority of vector font data or stroke font data, and the comparison determining unit further compares the vector font data or stroke font data having the higher priority first. The image processing apparatus according to claim 1 or 2, wherein: