JP2001307112A - Image processor, image processing method and recording medium recorded with image processing program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To provide an image processing method and an image processor capable of quickly and highly accurately detecting a circular pattern in an image. SOLUTION: In the ins∥∥mage processing method for detecting the circular pattern in the image, the image is binarized, pixels having a prescribed binary value in an octagon are counted and whether an object is a target to be detected or not is judged by the count number of pixels having the prescribed value.

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 detecting a circular pattern in an image, an image processing method, and a recording medium storing an image processing program.

[0002]

2. Description of the Related Art In recent years, the functions and performance of color copying machines have been improved, and counterfeiting of banknotes and the like has become possible. Therefore, effective counterfeit prevention methods are being studied. One of the forgery prevention methods is a method in which a specific pattern is put in a pattern such as a bill, a scanned image is analyzed, and if a specific pattern is detected in the image, normal image generation is prohibited. .

One method of detecting a specific pattern is to detect a circular pattern. For example, Japanese Patent Laying-Open No. 11-108631 discloses a method of counting a specific pixel in a circular area in order to detect a circular pattern.

[0004]

However, in Japanese Patent Application Laid-Open No. H11-108631, the number of specific pixels in a circular area is counted, which is more complicated than the case of counting specific pixels in a rectangular area. There was a problem that is. In recent years, input devices that perform scanning and output devices that output image data as printed prints, for example, devices that can process image data having a large amount of information such as high-resolution data at high speed are becoming widespread. It is desired to cooperate with an output device to detect a specific pattern in real time.

An object of the present invention is to solve the above-mentioned problem, and to provide an image processing apparatus for detecting a circular pattern at high speed and with high accuracy. Further, the present invention provides
An object of the present invention is to provide an image processing method for detecting a circular pattern at high speed and with high accuracy. Still another object of the present invention is to provide a recording medium for recording an image processing program for detecting a circular pattern with high speed and high accuracy.

[0006]

In order to achieve the above object, an image processing apparatus according to the present invention is an image processing apparatus for detecting a circular pattern in an image.
Binarizing means for binarizing, counting means for counting pixels having a binarized predetermined value in an n-sided polygon (n ≧ 8), and counting of pixels having the above predetermined value counted by the counting means Determining means for determining whether or not the object is a detection target by a number.
For example, the n-sided polygon is an octagon or a hexagon. A pixel having a predetermined value is an ON pixel having a predetermined value of 1 or an OFF pixel having a predetermined value of 0.

An image processing method according to the present invention is an image processing method for detecting a circular pattern in an image, wherein the image is binarized and a predetermined binarized value in an n-sided polygon (n ≧ 8) is calculated. The number of pixels having the predetermined value is counted, and whether or not the pixel is a detection target is determined based on the number of pixels having the predetermined value. For example, the n-sided polygon is an octagon or a hexagon. A pixel having a predetermined value is an ON pixel having a predetermined value of 1 or an OFF pixel having a predetermined value of 0.

A recording medium on which an image processing program according to the present invention is recorded has a procedure for binarizing an image and an n-gon (n ≧ n).
8) A procedure for causing a computer to execute a procedure of counting pixels having a binarized predetermined value and a procedure of determining whether or not the pixel having the predetermined value is a detection target based on the counted number of pixels having the predetermined value. An image processing program for detecting a circular pattern in an image is recorded. For example, the n-sided polygon is an octagon or a hexagon. A pixel having a predetermined value is an ON pixel having a predetermined value of 1 or an OFF pixel having a predetermined value of 0.

[0009]

Embodiments of the present invention will be described below with reference to the drawings. FIG. 1 is a schematic configuration diagram of an image processing apparatus (hereinafter, referred to as a “system”) according to the present embodiment. As shown in FIG. 1, the system includes a central processing unit (hereinafter, referred to as a CPU), and is configured around a control device 1 that controls the entire system. The control device 1 includes a display 2 for displaying images, characters, and the like, a display for operations, and the like, and a keyboard 3 and a mouse 4 for performing various inputs, instruction operations, and the like. As a recording medium, a flexible disk 5a, a hard disk 6, and a CD-ROM 9a are used, and a flexible disk device 5b, a CD-ROM device 9b, and a hard disk device 6 are provided. Furthermore, a printer 7 for printing characters, image data, and the like, a scanner 8 for capturing image data, a speaker 10 for voice output, and a microphone 11 for voice input are connected.

FIG. 2 shows a block diagram of a control system of the present system. The CPU 201 is connected via a data bus 220 to
RO in which a program for controlling this system is stored
M203 is connected to RAM 204 for temporarily storing programs and data executed by CPU 201 for control. A circuit connected to the CPU 201 via the data bus 220 includes a display control circuit 205 for controlling the display 12 for displaying images, characters, and the like.
A keyboard control circuit 206 for controlling transfer of input from the keyboard 3; a mouse control circuit 207 for controlling transfer of input from the mouse 4;
Flexible disk device control circuit 208 for controlling b
A hard disk device control circuit 209 for controlling the hard disk device, a printer control circuit 210 for controlling output to the printer 22, a scanner control circuit 211 for controlling the scanner 24, and a CD-ROM for controlling the CD-ROM device 9b. A device control circuit 212; a speaker control circuit 213 for controlling the speaker 10;
And a microphone control circuit 214 for controlling the Further, a clock 202 for generating a reference clock necessary for operating the system is connected to the CPU 201, and an expansion slot 215 for connecting various expansion boards is connected via a data bus 220. .

In this system, an image recognition program is stored in the ROM 203. However, a part or all of this program is stored in an information recording medium such as the flexible disk 5a, the hard disk 6, and the CD-ROM 9a, and the program is read out from the information recording medium to the RAM 204 as necessary, and executed. Is also good. Further, the recording medium may be another information recording medium such as a magneto-optical disk (MO). Although the scanner 8 is used as the image data input device, other data input devices such as a still video camera and a digital camera may be used. In addition, a network board can be connected to the expansion slot 215 to receive programs and image data via the network.

FIG. 3 shows the CPU 201 in the present system.
5 is a flowchart showing a main routine executed by the user. The input image data processed by this system is R (red),
Each color of G (green) and B (blue) is 8 bits (256 gradations)
Is data having a density value of This image data is shown in FIG.
Are image data input by various input means as shown in FIG. This image data is subjected to pre-processing such as resolution conversion and scaling if necessary. In step S701, a binarization process for labeling pixels according to the color of a circular pattern (mark) to be detected is performed. This binarization processing means that if the density value of the color of the circular pattern (mark) of each pixel forming the image data is included in the preset “reference density range”, That is, a pixel having a density value is set as an ON pixel having a value of 1, and if not included, an OFF pixel having a value of 0 is set. Next, step S
At 702, the position of a circular pattern candidate is detected. The following steps are performed to check whether the detected circular pattern candidate is a circular pattern to be truly detected. In step S703, the vertical / horizontal size and aspect ratio of the detected circular pattern candidate are inspected. Next, in step S704, the presence or absence of a pixel having a predetermined value at a plurality of points on the circumference of the circular pattern candidate and a plurality of points outside the circumference is checked (hereinafter, a pixel having a predetermined value, that is, an ON pixel or an OFF A pixel is called a specific pixel). Next, in step S705, a density test is performed in which the specific pixels of the binarized circular pattern candidate are counted, and the count is compared with the count of the reference value. Step S7
05 will be described in detail later. Next, step S
At 706, circumferential and radial pattern matching between the circular pattern to be detected and the detected circular pattern candidate is performed in consideration of the rotation. Next, step S
In step 707, steps S703 to S706 are performed.
It is calculated whether or not the circular pattern candidate conforms to the circular pattern to be detected by the inspection performed in the above.

Next, a method of counting a specific pixel in the density test (S705 in FIG. 3) will be described. Specific pixels of the circular pattern are counted in an n-sided polygon (n ≧ 8). First, a method of counting a specific pixel in an octagon will be described with reference to FIG. In FIG. 4, the detection window is 16
It is a pixel × 16 pixels. When the circular pattern in the detection window is binarized by a predetermined color, it becomes as shown in the right diagram of FIG. FIG. 5 is a diagram for explaining a scanning method of the first third from the top for counting specific pixels of a circular pattern in an octagon. (A) On the first line, scanning starts at a position 5 pixels away from the left end and ends at a position 5 pixels away from the right end. From the second line to the sixth line,
Each time one line is scanned, the scanning range increases left and right by one line. That is, the scanning of the second line starts at a position four pixels away from the left end, and ends at a position four pixels away from the right end. (B) In the seventh to tenth lines, scanning is performed from the left end to the right end. (C) From the 11th line to the 16th line, every time one line is scanned, the scanning range is reduced by one line to the left and right. That is, the eleventh line scans from the left end to the right end, and the twelfth line starts scanning at a position one pixel away from the left end and ends scanning at a position one pixel away from the right end. Finally, on the 16th line, scanning starts at a position 5 pixels away from the left end, and ends at a position 5 pixels away from the right end.

Next, a method of counting a specific pixel in a hexagon will be described with reference to FIG. In FIG. 6, the detection window is 20 pixels × 20 pixels. When the circular pattern in the detection window is binarized by a predetermined color, FIG.
It becomes like the figure on the right. FIG. 7 is a diagram illustrating an upper half scanning method for counting specific pixels of a circular pattern in a hexagon. On the first line, 8 from the left end
Scanning starts at a position separated by a pixel, and ends at a position separated by 8 pixels from the right end. From the first line to the third line, each time one line is scanned, the scanning range increases left and right by two pixels. On the fourth line, the scanning range increases left and right by one pixel. From the fifth line to the ninth line, the scanning range increases left and right by one pixel every other line. On the tenth line, scanning is performed from the left end to the right end. This completes the upper half scan. The scanning range is reduced so that the lower half is symmetric with the upper half.

Next, the density test will be described. Here, as an example, a specific pixel within an octagon is counted and a density test is performed. FIG. 8 is a diagram for explaining a method of counting specific pixels in an octagon. FIG. 9 is a flowchart of the density test. FIGS. 10, 11, and 12 are flowcharts of image processing for counting specific pixels in the A portion, the B portion, and the C portion, respectively. A part, B part, C
The portions are the areas shown in FIG. First, the specific pixels in the portion A are counted (S90).
1). Next, the specific pixels in the B portion are counted (S90).
2). Next, the specific pixels in the C portion are counted (S90).
3). The count of the specific pixels in the portion A, the count of the specific pixels in the portion B, and the count of the specific pixels in the portion C will be described in detail later. Next, step S
The specific pixels counted in steps 901 to S903 are summed to obtain a total sum of the specific pixels in the octagon (S904). Next, a score is calculated based on how close the total count number of the specific pixel in the octagon obtained in step S904 is to the count number of the circular pattern to be detected (S905). Thus, the density test is completed, and the process returns to the flowchart of FIG.

The counting of the portion A (S901 in FIG. 9) will now be described with reference to the flowchart of FIG. First, in steps S1001 to S1005, initialization is performed. Specifically, the count A is set to 0 (S1001). Next, m is set to 5 (S1002). Next, n is set to 5 (S1
003). Next, y is set to yMin (S100
4). Next, x is set to xMin + m (S100
5). This completes the initial setting.

Next, it is determined whether or not (x, y) is a specific pixel (S1006). If (x, y) is a specific pixel, count number A = count number A + 1 (S1007). Next, in order to check the coordinates on the right side, x = x + 1 is set (S1008). Next, it is determined whether x> xMax-m, that is, whether (x, y) exceeds the right end (S1009). If not, the process returns to step S1006. If it exceeds the right end, m = m-1 is set (S1010), and y = y + 1 is set (S1011). Next, it is determined whether y> yMin + n, that is, whether (x, y) is out of the A portion (S1012). If (x, y) does not deviate from part A, the process returns to step S1005. If it is out of the area A, the counting of the area A ends and the process returns to the flowchart of FIG.

Next, using the flowchart of FIG.
The counting of the part (S902 in FIG. 9) will be described.
First, in steps S1101 to S1104, initialization is performed. Specifically, the count number B is set to 0 (S1101). Next, n is set to 5 (S1102). Next, y is set to yMin + n (S1103). Next, x is set to xMin (S
1004). This completes the initial setting.

Next, it is determined whether or not (x, y) is a specific pixel (S1105). If (x, y) is a specific pixel, count number B = count number B + 1 (S1106). Next, to check the coordinates on the right side, x = x + 1 is set (S1107). Next, it is determined whether or not x> xMax, that is, whether (x, y) exceeds the right end (S1108). If it does not exceed the right end, the process returns to step S1105. If it exceeds the right end, y = y + 1 is set (S1109). Next, y> yMin-n, that is, it is determined whether (x, y) is out of the B portion (S1110). If (x, y) does not deviate from part B, the process returns to step S1104. If it is out of the portion B, the counting of the portion B ends, and the process returns to the flowchart of FIG.

Next, using the flowchart of FIG.
The counting of the part (FIG. 9, S903) will be described.
First, in steps S1201 to S1204, initialization is performed. Specifically, the count number C is set to 0 (S1201). Next, n is set to 5 (S1202). Next, 1 is set to 5 (S120).
3). Next, y is set to yMax-n + 1 (S1
204). Next, x is set to xMin + 1 (S1
005). This completes the initial setting.

Next, it is determined whether or not (x, y) is a specific pixel (S1206). If (x, y) is a specific pixel, count number C = count number C + 1 (S1207). Next, in order to check the coordinates on the right, x = x + 1 is set (S1208). Next, it is determined whether or not x> xMax−1, that is, whether (x, y) exceeds the right end (S1209). If not, the process returns to step S1206. If it is beyond the right end, 1 = 1 + 1 is set (S1210), and y = y + 1 is set (S1211). Next, y> yMax, that is, it is determined whether (x, y) is out of the C portion (S1212). If (x, y) does not deviate from the portion C, the process returns to step S1205. If it is out of the portion C, the counting of the portion C ends, and the process returns to the flowchart of FIG.

Incidentally, even if the specific pixel is an ON pixel,
It may be an off pixel. Further, as described in FIG. 7, the specific pixels in the upper half of the hexagon are counted, and the upper half and the lower half are symmetrical with respect to the center of the upper half and the lower half. Can be used to count specific pixels. The shape is not limited to an octagon or a hexagon, and may be another polygon such as a 32 polygon. Further, in this embodiment, A
Although the specific pixels in the octagon are counted in the order of the part count, the B part count, and the C part count,
This order is not particularly limited, and the specific pixels may be counted in another order.

Therefore, in the image processing method according to this embodiment, when counting only specific pixels within the n (n ≧ 8) polygon, as compared with the case of counting specific pixels in the entire area within the rectangle, refer to FIG. Since the number of pixels is reduced, the processing time can be shortened. Further, for example, the area error between an octagon and a circle is only 4% while the area error between a rectangle and a circle is 22%, so that the accuracy is high. In addition, compared to the case where the specific pixels in the circular area are counted, the case where only the specific pixels in the n (n ≧ 8) polygon is counted can be simply processed.

[0024]

According to the present invention, it is possible to simply process a specific pixel in an n (n ≧ 8) polygon rather than to count a specific pixel in a circular area. Can be detected.

[Brief description of the drawings]

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

FIG. 2 is a block diagram mainly illustrating a control device of the image processing apparatus.

FIG. 3 is a flowchart of a main routine in the image processing apparatus.

FIG. 4 is a diagram illustrating a method for counting a specific pixel in an octagon.

FIG. 5 is a diagram illustrating a count range of a specific pixel within an octagon;

FIG. 6 is a diagram illustrating a method of counting a specific pixel within a hexagon.

FIG. 7 is a diagram illustrating a count range of a specific pixel within a hexagon.

FIG. 8 is a diagram illustrating a method of counting a specific pixel in an octagon.

FIG. 9 is a flowchart of a density test.

FIG. 10 is a flowchart of image processing for counting a specific pixel in a portion A of FIG. 8;

FIG. 11 is a flowchart of image processing for counting specific pixels in a B portion of FIG. 8;

FIG. 12 is a flowchart of image processing for counting a specific pixel in a C portion of FIG. 8;

[Explanation of symbols]

1 control device, 5b flexible disk,
6 hard disk, 7 printer, 8 scanner, 9b CD-ROM, 20 detection window,
22 partial image area 201 CPU, 203
ROM, 204 RAM.

Continued on the front page (72) Inventor Hirotomo Ishii 2-3-1-13 Azuchicho, Chuo-ku, Osaka-shi, Osaka F-term in Osaka International Building Minolta Co., Ltd. 5L096 AA02 AA06 EA35 EA43 FA04 FA15 FA54 FA70 GA28 GA40

Claims (15)

[Claims] 1. An image processing apparatus for detecting a circular pattern in an image, comprising: a binarizing means for binarizing the image; and a pixel having a predetermined value binarized in an n-sided polygon (n ≧ 8). An image processing apparatus comprising: a counting means for counting; and a judging means for judging whether or not a pixel is a detection target based on a count number of a pixel having the above predetermined value counted by the counting means. 2. The image processing apparatus according to claim 1, wherein the n-sided polygon is an octagon. 3. The image processing apparatus according to claim 1, wherein the n-sided polygon is a hexagon. 4. The image processing apparatus according to claim 1, wherein in the binary image, the pixel having the predetermined value is an ON pixel whose predetermined value is 1. 5. The image processing apparatus according to claim 1, wherein in the binary image, the pixel having the predetermined value is an off pixel whose predetermined value is 0. 6. An image processing method for detecting a circular pattern in an image, wherein the image is binarized, and a pixel having a binarized predetermined value in an n-sided polygon (n ≧ 8) is counted. An image processing method, comprising: determining whether a pixel is a detection target based on a count number of pixels having a value. 7. The image processing method according to claim 6, wherein the n-sided polygon is an octagon. 8. The image processing method according to claim 6, wherein the n-sided polygon is a hexagon. 9. The image processing method according to claim 6, wherein in the binary image, the pixel having the predetermined value is an ON pixel whose predetermined value is 1. 10. The image processing method according to claim 6, wherein in the binary image, the pixel having the predetermined value is an off pixel whose predetermined value is 0. 11. An image processing program for detecting a circular pattern in an image, comprising: a step of binarizing the image; and counting pixels having a predetermined binarized value in an n-sided polygon (n ≧ 8). A computer-readable recording medium which records a program for causing a computer to execute a procedure of performing the above and a procedure of determining whether or not the pixel is a detection target based on the count number of the pixel having the predetermined value. 12. The recording medium according to claim 11, wherein the n-sided polygon is an octagon. 13. The n-sided polygon is a hexagonal form.
A recording medium according to claim 1. 14. The recording medium according to claim 11, wherein in the binary image, the pixel having the predetermined value is an ON pixel whose predetermined value is 1. 15. The recording medium according to claim 11, wherein in the binary image, the pixel having the predetermined value is an off pixel whose predetermined value is 0.