JP4016571B2 - Image processing apparatus and method - Google Patents

Description

[0001]
BACKGROUND OF THE INVENTION
The present invention relates to an image detection technique for detecting a specific pattern in an image.
[0002]
[Prior art]
In recent years, the functions and performance of color copiers have improved, and effective methods for preventing counterfeiting such as banknotes and securities have been studied. As one of the forgery prevention methods, there is a method in which a specific pattern is put in a pattern such as a banknote, a scanned image is analyzed, and if a specific pattern is detected in the image, normal image generation is prohibited. At that time, it is necessary to detect a specific pattern from the scanned image even when banknotes are placed in an arbitrary angle during image reading, or when there are local stains or scratches that occur during the circulation of banknotes, etc. There is.
[0003]
[Problems to be solved by the invention]
When reading an image with a scanner, the color of the read image changes depending on the scanning conditions. In addition, the input image data is affected by scanner deterioration, changes in environmental conditions, changes in stress conditions, and the like. For this reason, it is necessary to widen the color discrimination range when detecting a specific image. However, widening the discrimination range increases noise components and increases detection errors.
[0004]
An object of the present invention is to provide an image processing method and apparatus capable of accurately discriminating colors.
[0005]
[Means for Solving the Problems]
The image processing apparatus according to the present invention includes a first determination unit configured to determine that a plurality of pieces of color information of a pixel of interest are within a first range for the input image, and a plurality of different coefficients for the plurality of pieces of color information. A second determination unit that determines that the primary calculation result calculated over the second range is within the second range; a second determination unit that determines that the first determination unit is within the first range; Is determined to be within the second range, color discriminating means for determining that the target pixel is a specific color . Good Mashiku further based on the discrimination results by the color discrimination means, and a small element extracting means for extracting a small element, small elements extracted by the small element extraction means in a specific positional relationship with a specific shape And an arrangement identifying means for identifying the above.
[0006]
In the image processing method according to the present invention, for an input image, it is determined that the plurality of pieces of color information of the pixel of interest are within the first range, and then the plurality of pieces of color information are multiplied by different coefficients. When the calculated primary calculation result is determined to be within the second range, and then determined to be within the first range and determined to be within the second range, the target pixel is Judged to be a specific color . Good Mashiku further based on the color determination result, identifies whether to extract small element with a specific shape, the extracted small element in a specific positional relationship.
[0007]
The computer-readable recording medium according to the present invention determines that a plurality of pieces of color information of a pixel of interest are within a first range for an input image, and then uses different coefficients for the plurality of pieces of color information. When it is determined that the result of the primary calculation calculated by multiplying is within the second range, then determined to be within the first range, and determined to be within the second range, that records an image processing program target pixel is determined to be a specific color. Good Mashiku further based on the color determination result, identifies whether to extract small element with a specific shape, the extracted small element in a specific positional relationship.
[0008]
DETAILED DESCRIPTION OF THE INVENTION
Hereinafter, embodiments of the present invention will be described with reference to the accompanying drawings. In the drawings, the same reference symbols denote the same or equivalent.
[0009]
FIG. 1 shows a schematic configuration diagram of an image processing apparatus (hereinafter referred to as “system”) of 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 10 that controls the entire system. The control device 10 includes a display 12 that displays images, characters, etc., displays for operations, and the like, and a keyboard 14 and a mouse 16 that perform various inputs, instruction operations, and the like. As a recording medium, a flexible disk 18, a hard disk 20, and a CD-ROM 26 are used, and a flexible disk device 18b, a CD-ROM device 26b, and a hard disk device (not shown) are provided. Further, a printer 22 for printing characters, image data, etc., a scanner 24 for capturing image data, a speaker 28 for outputting sound, and a microphone 30 for inputting sound are connected.
[0010]
FIG. 2 shows a block diagram of the control system of this system. Via the data bus 202, the CPU 204 is connected to a ROM 204 that stores a program for controlling the system, and a RAM 206 that temporarily stores a program and data executed by the CPU 200 for control. Further, a circuit connected to the CPU 200 via the data bus 202 includes a display control circuit 208 for controlling the display 12 for displaying images or characters, and a keyboard control circuit 210 for controlling transfer of input from the keyboard 14. , A mouse control circuit 212 that controls the transfer of input from the mouse 16, a flexible disk device control circuit 214 that controls the flexible disk device 18b, a hard disk device control circuit 216 that controls the hard disk device, and an output to the printer 22 Printer control circuit 218 for controlling, scanner control circuit 220 for controlling scanner 24, CD-ROM device control circuit 222 for controlling CD-ROM device 26b, speaker control circuit 224 for controlling speaker 28, and microphone 30. Microphone There is a control circuit 226. Further, a clock 228 for generating a reference clock necessary for operating the system is connected to the CPU 200, and an expansion slot 230 for connecting various expansion boards is connected via the data bus 202. .
[0011]
In this system, an image detection program is stored in the ROM 204. However, a part or all of this program is stored in an information recording medium such as the flexible disk 18, the hard disk 20, and the CD-ROM 26, and the program is read from the information recording medium to the RAM 206 as necessary and executed. Also good. The recording medium may be another information recording medium such as a magneto-optical disk (MO). Further, although the scanner 24 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 230 to receive a program and image data via the network.
[0012]
This image processing apparatus determines whether a specific pattern in which a plurality of small elements have a specific arrangement relationship is included in the input image. FIG. 3 is a flowchart of specific pattern detection. First, image data having a plurality of color information for each pixel is input by the image input means (S10). Next, it is determined whether or not a pixel in the input image data has a specific color (S12). Next, a small element having a specific shape is determined from the color determination result, and the center of the small element is extracted (S14). Finally, it is identified whether the centers of the extracted small elements are arranged at a specific location (S16). Thereby, it is determined whether the specific pattern is included in the input image.
[0013]
Here, when the image is read by the scanner 24, the color of the read image changes depending on the scanning condition. In addition, the input image data is affected by scanner deterioration, changes in environmental conditions, changes in stress conditions, and the like. For this reason, it is necessary to widen the color discrimination range when detecting a specific image. However, widening the discrimination range increases noise components and causes many detection errors. Therefore, in the present embodiment, as described below, in order to widen the color discrimination range without increasing detection errors, not only the RGB brightness value range but also (RG) and (GB) ), (R−B), (R + G), (G + B), and (R + B) are defined as the range of the primary calculation result.
[0014]
FIG. 4 is a flowchart of the color discrimination process (FIG. 3, S12). First, image data is input after being separated into R, G, and B color components (S100). Next, with respect to the input data, the first determination unit determines whether each is in a specific color range (S102). For example, the maximum value and the minimum value of R, G, and B are defined in advance, and it is determined whether each image data of the pixel of interest is within this range. Only when all the conditions are satisfied, the detected color is determined.
[0015]
Specifically, in the flowchart of the first discriminating means shown in FIG. 5, the maximum values Rmax, Gmax, Bmax and the minimum values Rmin, Gmin, Bmin of R, G, B are defined in advance. It is initialized to 1 (S1020). i is a variable such as 1, 2,..., n. Next, it is determined whether or not the color range condition is satisfied for the input image data of the i-th target pixel (S1022). An example of the conditions is as follows.
Rmin ≦ Ri ≦ Rmax and Gmin ≦ Gi ≦ Gmax and (1)
Bmin ≤ Bi ≤ Bmax
If this condition is satisfied, it is determined as a detection color candidate (S1024). Next, i is incremented (S1026), and if the data processing for all the pixels has not been completed (NO in S1028), the process returns to step S1022, and the above-described processing is repeated.
[0016]
In the flowchart of FIG. 4, next, it is determined by the second determination means whether the input image is within the determination range of the conditional expression different from the conditional expression (1) (S104). If the determination is made using only the RGB maximum and minimum values, a color that is clearly different from the color to be detected (hereinafter referred to as noise) may be detected. Therefore, another conditional expression is set to eliminate this noise. The following conditional expression is an example. FIG. 6 is a flowchart of the second determination means. First, the variable i is initialized to 1 (S1040). i is a variable such as 1, 2,..., n. Next, it is determined whether RG, GB, and RB satisfy the following condition for the input image data of the i-th target pixel (S1042).
( RG ) min ≤ Ri-Gi ≤ ( RG ) max and
( GB ) min≤Gi-Bi≤ ( GB ) max and (2)
( RB ) min ≤ Ri-Bi ≤ ( RB ) max
If this condition is not satisfied, it is removed from the specific color candidate as noise (S1044). Next, i is incremented (S1046), and if the processing of all the pixel data has not been completed (NO in S1048), the process returns to step S1042, and the above-described processing is repeated.
[0017]
Finally, an AND operation is performed on the first determination unit and the second determination unit (S106). That is, the pixel of interest that has been determined as the detection color candidate by the first determination unit and that has been determined as the detection color candidate by the second determination unit is determined to be the detection color.
[0018]
The second determination unit will be further described. For example, assuming that yellow is detected in the R / G space, it is assumed that Rmax = 255, Rmin = 150, Gmax = 255, and Gmin = 150 as shown in FIG. In the case of yellow, the image data is R = 255, G = 255, and B = 0 (A). However, only conditional expression (1) allows R = 255, G = 150 color (A ′), R = 150, G = 255 color (A ″) will be detected. In the case of yellow, if the balance between R and G is lost, it approaches red or green, so if the balance is greatly lost, it is desirable to detect it as a different color. Therefore, another conditional expression (2) defines that the difference between the R value and the G value of the target pixel is within a certain value. Thereby, noise components such as A ′ and A ″ can be deleted.
[0019]
As a modification, as shown in FIG. 8, as a conditional expression (2), not only a simple difference in image data, but a primary calculation result obtained by multiplying each image data by a coefficient and calculating a sum or difference (more general By setting a range for the R, G, and B function calculation results, it becomes possible to set more detailed conditions. In FIG. 8, a, b, c, d, e, f, g, and h represent coefficients, and the stipple portion is a specific color detection range. FIG. 8 also shows the maximum value and minimum value conditions for the image data R and G themselves. Although only the R / G space is shown in FIG. 8, similar conditions are set for the G / B space and the R / B space.
[0020]
【The invention's effect】
A specific color can be determined even when input image data is affected by scanner deterioration, environmental condition changes, stress condition changes, and the like.
By narrowing the color discrimination range using a plurality of conditions, color detection errors can be reduced.
[Brief description of the drawings]
FIG. 1 is a schematic diagram of a configuration of an image processing apparatus according to the present invention. FIG. 2 is a block diagram centering on a control apparatus of the image processing apparatus. FIG. 3 is a flowchart of specific pattern detection. Flowchart of Processing [FIG. 5] Flowchart of First Discrimination [FIG. 6] Flowchart of Second Discrimination [FIG. 7] Diagram showing an Example of Color Discrimination Condition in R / G Space [FIG. 8] Showing another example of color discrimination condition for the [Color code]
10 control device, 18 flexible disk, 20 hard disk, 22 printer, 24 scanner, 26 CD-ROM, 200 CPU, 204 ROM.

Claims (6)

First discriminating means for judging that the plurality of color information of the target pixel is within the first range for the input image;
Second determination means for determining that a primary calculation result calculated by multiplying a plurality of color information by different coefficients is within a second range;
Color determining means for determining that the pixel of interest is a specific color when the first determining means determines that it is within the first range and the second determining means determines that it is within the second range. An image processing apparatus comprising: further,
Small element extraction means for extracting small elements having a specific shape based on the determination result by the color determination means;
The image processing apparatus according to claim 1 , further comprising: an arrangement identification unit that identifies whether the small elements extracted by the small element extraction unit have a specific arrangement relationship. For the input image, determine that each of the plurality of color information of the target pixel is within the first range;
Determining that the primary calculation result calculated by multiplying a plurality of color information by different coefficients is within the second range;
An image processing method for determining that a pixel of interest is a specific color when it is determined that the pixel is within a first range and within the second range. further,
Based on the color discrimination results, extract small elements with a specific shape,
The image processing method according to claim 3 , wherein the extracted small elements are identified as having a specific arrangement relationship. For the input image, determine that each of the plurality of color information of the target pixel is within the first range;
Determining that the primary calculation result calculated by multiplying a plurality of color information by different coefficients is within the second range;
A computer-readable recording medium for recording an image processing program that determines that a pixel of interest is in a specific color when it is determined that the pixel is within the first range and within the second range. The image processing program further extracts a small element having a specific shape based on a color discrimination result, and identifies whether the extracted small element is in a specific arrangement relationship. 5. The recording medium described in 5 .

Images