JP2988209B2 - Color shading pattern recognition device - Google Patents

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a color density pattern recognizing apparatus, and more particularly to a color image obtained from a color television camera or the like, which is suitable for recognizing the presence or absence of an object by applying pattern matching. The present invention relates to a color density pattern recognition device.

[0002]

2. Description of the Related Art Conventionally, as this type of color shading pattern recognizing apparatus, one shown in FIG. 2 is known. FIG.
In the conventional recognition device, a television camera 101, a digital RGB separator 102, an R color frame memory 10
3, G color frame 104, B color frame memory 105,
R color reference pattern 106, G color reference pattern 107, B
A color reference pattern 108, a sweep address generation circuit 109,
Cutout address generation circuit 110, address adder 11
1, an R color comparison circuit 112, a G color comparison circuit 113, a B color comparison circuit 114, an operation adder 115, an accumulator 116, a minimum value holding circuit 117, and a cutout address holding circuit 118.

When an image of an object to be recognized is obtained by the television camera 101, this color image is
The data is input to a GB separator 102, from which analog data is converted into RGB digital data at regular intervals and output. R color frame memory 103
Fetches and stores the R color digital data obtained from the separator 102 for one screen. The G color frame memory 104 captures and stores the G color digital data obtained from the separator 102 for one screen. The B color frame memory 105 captures and stores the B color digital data obtained from the separator 102 for one screen.

On the other hand, an R color reference pattern 106 stores R color reference pattern data for recognition. The G color reference pattern 107 stores G color reference pattern data for recognition. The B color reference pattern 108 stores B color reference pattern data for recognition. Each color of each of these reference patterns is an area of 16 × 16 pixels. The sweep address generation circuit 109 sequentially generates sweep addresses (16 × 16 addresses) for sweeping all pixels in the reference patterns 106 to 108. The cut-out address generation circuit 110 outputs R,
From an input image in each of the G and B color frame memories 103 to 105, a cutout address (5 × 5 area) for determining a search area for matching with the corresponding R, G, and B reference patterns is sequentially generated. ing. The address adder 111 adds the sweep address from the sweep address generating circuit 109 and the cut address from the cut address generating circuit 110, and calculates the recognition target pixel address of each of the R, G, and B color frame memories.

The R color comparison circuit 112 calculates the degree of mismatch between the target image data read from the R color frame memory 103 and the reference data output from the R reference pattern 106. The G color comparison circuit 113 calculates the degree of mismatch between the target image data read from the G frame memory 104 and the reference image data output from the G reference pattern 107. The B color comparison circuit 114 calculates the degree of mismatch between the target image data read from the B frame memory 105 and the reference image data output from the R reference pattern 108. The arithmetic adder 115 includes an R color comparing circuit 112
And the arithmetic units obtained from the G color comparison circuit 113 and the B color comparison circuit 14 are added. The accumulator 116 is reset to 0 immediately before the sweep address generating circuit 109 starts sweeping. During the sweeping of 16 × 16 pixels, the accumulator 116 accumulates the added value obtained from the arithmetic adder 115 and uses this as an evaluation value. Hold. The minimum value holding circuit 117 is reset to the maximum value immediately before the cutout address generation circuit 110 starts cutting out the search area, and thereafter, the sweep address generation circuit 109
Every time the sweep is completed, the minimum value held by the accumulator 11
The evaluation values obtained from step No. 6 are compared. If the evaluation value is smaller, the minimum value is replaced with the evaluation value, and a replacement pulse indicating the replacement is output. The cutout address holding circuit 118 holds the cutout address generated by the cutout address generation circuit 110 according to the replacement pulse obtained from the minimum value holding circuit 117.

Next, the operation of the above conventional example will be described with reference to FIG. First, a color shading pattern, which is a reference of a recognition target, is fetched. That is, the TV camera 1
01, among the digital grayscale image data obtained from the R-color frame memory 103, the G-frame memory 104, and the B-frame memory 105 by operating the digital RGB separator 102, data of each color of RGB serving as a reference pattern to be recognized is It is stored in advance as an R color reference pattern 106, a G color reference pattern 107, and a B color reference pattern 108.

As an operation after the reference pattern is stored, an operation of color shading recognition for finding a position where an image that best matches the reference pattern exists will be described.

[0008] This operation is performed in each frame memory 1 of RGB.
Large loop operation for sweeping a specified search area (5 × 5 area) while changing the cutout address to 03, 104, and 105, and a recognition area (16 × 16) cut out from each of frame memories 103 to 105 , And a small loop operation for comparing with the reference patterns 106, 107, and 108 of the corresponding colors. The small loop operation is included in the large loop operation.

First, prior to the large loop operation, the cut-out address generation circuit 110 sends a minimum value reset signal to the minimum value holding circuit 117 to set the initial minimum value to an appropriate value. Next, a large loop operation is started, and the cutout address generation circuit 110 sets a cutout address for inserting a rectangular area of 5 in the X direction and 5 in the Y direction from the start point specified in advance in each color frame memory 103, 10
It occurs in synchronization with 4,105. A small loop operation is performed on one of the cutout addresses.

Prior to the small loop operation, the sweep address generation circuit 109 sends an accumulator reset signal to the accumulator 116 to set the evaluation value of the accumulator 116 to the minimum value (0). Thereafter, a small loop operation is started, and the sweep address generation circuit 109 generates a sweep address for sweeping a 16 × 16 area. This sweep address is initially
Starting from the address indicating the pixel at the upper left corner of the reference patterns 106, 107, and 108 for each of the RGB colors, 16 ×
The reference pattern read address sweeps 16 areas, and each address is sequentially output. The RGB color reference patterns 106, 107, and 108 transfer the corresponding color reference image data to the RGB color comparison circuits 112, 113, and 114 in response to the reference pattern read address.

On the other hand, the sweep address output from the sweep address generating circuit 109 is added to the cut-out address by the address adder 111, and the added address becomes a frame memory read address, which is used for the RGB color frame memories 103, 104 and 105. The cut-out address is set as the pixel at the upper left corner, and is output one after another so as to sweep over a 16 × 16 area. The RGB color frame memories 103, 104, and 105 transfer the corresponding image data of each color to the RGB color comparison circuits 112, 113, and 114 in response to the frame memory read address.

RGB color comparison circuits 112, 113, 11
In step 4, the reference image data and the target image data are compared for each of the RGB colors, and the degree of inconsistency of each of the RGB colors, which is the comparison result, is output to the arithmetic adder 115. Arithmetic adder 1
Reference numeral 15 calculates the total value of the inconsistency of each of the RGB colors and outputs it to the accumulator 116. Accumulator 116 is used during small loop operation.
The total inconsistency from the adder 115 is accumulated. When the small loop operation is completed, the recognition evaluation value at the current sweep address has been obtained in the accumulator 116, and this value is transferred to the minimum value holding circuit 117. In the minimum value holding circuit 117,
The recognition evaluation value is compared with the held minimum value based on the evaluation strobe signal output from the sweep address generation circuit 109. If the evaluation value is smaller, the minimum value is replaced with the recognition evaluation value, and a replacement pulse is cut out to hold the address. Output to the circuit 118. In the cutout address holding circuit 118, the cutout address generation circuit 110
Is stored in accordance with the replacement pulse, and the cut-out address at which the recognition evaluation minimum value is obtained is stored.

After the above processing, the large-loop operation is continued with the cut-out address output from the cut-out address generation circuit 110 as the next value. When the sweeping of the 5 × 5 rectangular search area is completed according to the cutout address, the large loop operation ends, and the position and degree of the pattern most similar to the reference pattern are stored in the cutout address holding circuit 118 and the minimum value holding circuit 117. The obtained color shading pattern recognition is completed.

[0014]

However, in the above-mentioned prior art, when the brightness around the object to be recognized (hereinafter referred to as ambient brightness) changes, the reliability of recognition has been significantly reduced. This is compared to when the reference pattern is collected
For example, when the ambient lightness is low, although the degree of the density data of the target object image which is taken into the frame memories 103, 104, and 105 of the respective colors via the television camera 101 and the digital RGB separator 102 has decreased for each of the RGB colors. This is because the comparison with the reference patterns 106, 107, and 108 of each of the RGB colors is performed without any correction. In order to reduce the influence of the surrounding lightness change, a method using AGC (auto gain control) is conceivable. However, since it takes time until the image data is stabilized, the processing speed as a whole recognition may be reduced. Easily anticipated.

The present invention has been made to solve the above-mentioned problems of the conventional system, and is capable of recognizing the color and shape of an object at a high speed without being affected by a change in ambient lightness. It is an object to provide a pattern recognition device.

[0016]

According to the present invention, there is provided a memory for storing a reference pattern comprising R, G, and B digital images obtained by A / D conversion from a color image signal. A circuit for storing the average value of the Y (luminance) level of the reference pattern;
A circuit for extracting a pattern to be recognized composed of each gray-scale image based on an extraction address from each of the digital images B and Y, and dividing the average value of the Y level of the reference pattern by the average value of the Y level of the pattern to be recognized; And a circuit for calculating a brightness correction coefficient by using R, G, B
A circuit for multiplying the pixel data of each of the patterns to be recognized to obtain the square of the difference from the corresponding reference pattern, and adding these values for all the pixels to obtain an evaluation value. In this case, a cut-out address is obtained as follows.

[0017]

The present invention has the following functions and effects by the above-described configuration. That is, when a color image signal from a television camera or the like is converted into a digital signal, the luminance level of the entire reference pattern is the same as the reference pattern data composed of R, G, and B digital images based on the digital image of the three primary colors. The average value is stored. At the time of pattern recognition, a pattern to be recognized composed of four types of gray images of R, G, B, and Y is cut out from each of the digital images of R, G, B, and Y based on the cut-out address, and a reference stored in advance is stored. An optimum brightness correction coefficient is obtained from the average brightness (Y) level of the pattern and the average brightness level of the entire pattern to be recognized, and the optimum brightness correction coefficient is converted to pixel data of the pattern to be recognized for each of R, G, and B colors. Then, a difference value from each corresponding reference pattern is obtained, a square of a difference value of each color is obtained, and this is added for all pixels of all the R, G, B reference patterns to obtain an evaluation value. Then, a cutout address that minimizes this evaluation value is obtained. This significantly suppresses the occurrence of false recognition due to changes in ambient brightness,
In addition, the color and shape of the object can be recognized at high speed because of the complete digital operation.

[0018]

An embodiment of the present invention will be described below with reference to the drawings. FIG. 1 is a configuration diagram showing one embodiment of the present invention.

In FIG. 1, a television camera 11 is configured to obtain an image of an object to be subjected to pattern recognition, and outputs an analog color image signal from a color television 11 to a digital R, G, B separator 12. Have been. The digital RGB separator 12 converts analog data obtained from the television camera 11 into RGB digital data at regular intervals. The R frame memory 13 captures the R color digital data obtained from the digital RGB separator 12 for one screen, and stores this as digital data. The G color frame memory 14 captures the G color digital data obtained from the digital RGB separator 12 for one screen, and stores the data. The B color frame memory 15 captures the B color digital data obtained from the digital RGB separator 12 for one screen, and stores this data.
The Y frame memory 16 stores the digital RGB separator 12
The digital data of the luminance level obtained from is acquired for one screen and stored. That is, R,
The G, B frame memories 13, 14, 15 are configured as three-color frame memories, and the Y frame memory 16 is configured as a luminance frame memory.

The R color reference pattern generator 17 stores R color reference pattern data for recognition. The G color reference pattern generator 18 stores G color reference pattern data for recognition. The B color reference pattern generator 19 performs B
The color reference pattern data is stored. That is, each of the reference pattern generators 17, 18, and 19 is configured as reference pattern storage means, and each generator has an area of 16 × 16 pixels.

The sweep address generation circuit 20 has a sweep address (16 × 1) for sweeping all pixels in the reference pattern.
6 addresses). The cutout address generation circuit 21 determines a cutout address (5 ×) for determining a search area for matching with the corresponding R, G, B reference pattern from the input image in each of the R, G, B colors and the Y frame memory. 5 addresses). The addresses from the address generation circuits 20 and 21 are input to the address adder 22. Address adder 2
2 adds the sweep address from the sweep address 20 and the cut address from the cut address generating circuit 21 to calculate the R, G, B colors and the recognition target pixel address of the Y frame memory. Then, the pixels of each frame memory are sequentially swept according to this address.

The average value calculation circuit 23 is a Y frame memory 1
The average luminance of the target pattern in the recognized area is calculated from the image data of the luminance output from 6. The standard pattern Y level average value holding circuit 24 stores the average value of the luminance levels of the entire reference pattern of each color of RGB. The divider 25 divides the reference pattern average value output from the standard pattern Y level average value holding circuit 24 by the target pattern average luminance output from the average value calculation circuit 23, and outputs the result as an optimal brightness correction coefficient. The optimum brightness correction coefficient holding circuit 26 holds the optimum brightness correction coefficient output from the divider 25,
The held optimal brightness correction coefficient is used as a correction value as a multiplier 27,
28 and 29.

The R color multiplier 27 is an R frame memory 1
3 is multiplied by the optimum brightness correction coefficient output from the optimum brightness correction coefficient holding circuit 26,
Calculate R-color optimal brightness image data. Multiplier 28 for G color
Multiplies the target image data read from the G frame memory 14 by the optimum brightness correction coefficient output from the optimum brightness correction coefficient holding circuit 26 to calculate the G color optimum brightness image data. The B color multiplier 29 is used for the B color frame memory 15.
Is multiplied by the optimum brightness correction coefficient output from the optimum brightness correction coefficient holding circuit 26,
The color optimum brightness image data is calculated. Then, the calculated values of these multipliers are output to the subtractors 30, 31, and 32.

The R color subtractor 30 subtracts the R color reference data output from the R color reference pattern generator 17 from the R color optimum brightness image data output from the R color multiplier 27. The G color subtractor 31 converts the G color optimum brightness image data from the G color multiplier 28 into a G color reference pattern generator 1.
8 is subtracted from the G color reference data. The B color subtractor 32 subtracts the B reference data from the B reference pattern generator 19 from the B color optimum brightness image data from the B color multiplier 29. Then, the values calculated by these subtractors are output to the squarers 33, 34, 35, respectively.

The R color squarer 33 calculates the square value of the R color difference value from the R color subtractor 30. G color squarer 34
Calculates the square value of the G color difference value from the G color subtractor 31. The squarer 35 for B color receives the B signal from the subtractor 32 for B color.
Calculate the square of the color difference value. Then, the calculated value of each squarer is output to the arithmetic adder 36, respectively.

The arithmetic adder 36 is provided for each color squarer 33, 3
The total value of the difference values of the respective colors output from the colors 4, 35 is calculated, and the calculated value is output to the accumulator 37. The accumulator 37 is reset to 0 immediately before the sweep address generator 20 starts sweeping. During the 16 × 16 pixel sweep, the accumulator 37 accumulates the added value obtained from the arithmetic unit adder 35, and accumulates the evaluation value. And transfers the held value to the minimum value holding circuit 38. The minimum value holding circuit 38 is reset to the maximum value immediately before the cut-out address generation circuit 21 starts cutting out the search area, and thereafter, every time the sweep address generator 20 finishes the sweep, the minimum value held by the cut-out address generation circuit 21 is reset. The evaluation value obtained from the accumulator 37 is compared. If the evaluation value is smaller, the minimum value is replaced with the evaluation value, and a replacement pulse indicating the replacement is output to the address holding circuit 39. The cutout address holding circuit 39 holds the cutout address generated by the cutout address generation circuit 21 in response to the replacement pulse obtained from the minimum value holding circuit 38.

Next, the operation of the above embodiment will be described with reference to FIG. First, a color shading pattern, which is a reference of a recognition target, is fetched. That is, the TV camera 1
1. The digital RGB separator 12 is operated, and among the digital gray image data obtained by the R color frame memory 13, the G color frame memory 14, the B color frame memory 15, and the Y color frame memory 16, the reference to be recognized. The data of each of the RGB colors serving as the pattern is stored in the R color reference pattern, the G color reference pattern, and the B color reference pattern, and the Y level average value of the entire reference pattern is stored in the reference pattern Y level average value holding circuit 24 in advance.

As an operation after the reference pattern is stored, an operation of color shading recognition for finding a position where an image that best matches the reference pattern exists will be described below.

This operation is performed for each frame memory 1 of RGB.
A large loop operation for sweeping a designated search area (5 × 5 area in this embodiment) while changing the cutout addresses to the 3, 14, 15 and Y frame memories 16 and the cutout from each frame memory It consists of a small loop operation that sweeps the recognition area (16 × 16 area in this embodiment) and performs color shading recognition with the corresponding reference pattern of each color.
The small loop operation is included in the large loop operation.

First, prior to the large loop operation, the cut-out address generation circuit 21 sends a minimum value reset signal to the minimum value holding circuit 38, and sets the initial minimum value to an appropriate value. Next, a large loop operation is started, and the cut-out address generation circuit 21 starts to execute X from the start point designated in advance.
The cutout addresses for sweeping the rectangular area of 5 in the Y direction and 5 in the Y direction are stored in the respective frame memories 13, 14, 15, 1.
6 synchronously. A small loop operation is performed on one of the cutout addresses. Prior to the small rule operation, the sweep address generation circuit 20 sends an accumulator reset signal to the accumulator 37, and
The evaluation value of 7 is set to the minimum value (0).

Next, in a small loop operation, the sweep address generation circuit 20 generates a sweep address for sweeping a 16 × 16 area. This sweep address is initially R
Starting from the address indicating the pixel at the upper left corner of the reference pattern of each color of GB, it becomes a reference pattern read address for sweeping a 16 × 16 area, and this address is sequentially output. Then, the reference pattern generator of each of the RGB responds to the reference pattern read address,
The corresponding reference pixel data of each color is subtracted by each color subtractor 30,3.
1 and 32.

On the other hand, the sweep address is stored in the address adder 22.
Is added to the cutout address, and becomes the frame memory read address.
The cutout address is set to the pixel at the upper left corner of the pixels 3, 14, 15, and the Y frame memory 16, and is sequentially output to sweep a 16 × 16 area. At this time RGB
Each of the color frame memories 13, 14, 15 receives this frame memory read address, and transfers the corresponding image data of each color to the RGB color multipliers 27, 28, 29. At this time, at the same time, the luminance level data is read from the Y frame memory 16 and input to the average value calculation circuit 23.

The average value calculation circuit 23 calculates the average luminance of the target pattern in the entire 16 × 16 pixel area where the cutout address is the pixel at the upper left corner. On the other hand, the divider 25
Divides the average value of the reference pattern output from the standard pattern Y level average value holding circuit 24 by the average luminance of the target pattern output from the average value calculation circuit 23, and outputs this as an optimal brightness correction coefficient. The optimum lightness correction coefficient holding circuit 26 holds the optimum lightness correction coefficient output from the divider 25 until the sweep address generation circuit 20 generates an accumulator reset signal, and the RGB color multipliers 27 and 2.
8 and 29 are continuously transferred as the optimum brightness correction coefficient. Accordingly, the R, G, and B color multipliers 27, 28, and 29 output R
The optimal brightness correction coefficient is multiplied by the RGB target shape data from the RGB color frame memories to calculate the optimal brightness image data for each of the RGB colors. And the subtractors 30, 31, for each of the RGB colors,
At 32, the RGB color reference pattern generators 17, 18, and 19 output the RGB color optimum brightness image data output from the RGB color multipliers 27, 28, and 29, and output the RGB color reference pattern generators 17, 18, and 19.
Each color reference pattern is subtracted, and output as RGB color difference values. Squarers 33, 34, 35 for each color of RGB
Then, the square value of each of the RGB color difference values output from the RGB color subtractors 30, 31, 32 is calculated as the degree of mismatch. The arithmetic adder 36 calculates the total value of the inconsistency of each of the RGB colors, and outputs the calculated value to the accumulator 37.
The accumulator 37 accumulates the total inconsistency from the operation adder 36 during the small loop operation. When this small loop operation is completed, the accumulator 37 has obtained the recognition evaluation value at the current sweep address, and sends this value to the minimum value holding circuit 38. The minimum value holding circuit 38 compares the recognition evaluation value with the held minimum value based on the evaluation strobe signal output from the sweep address generation circuit 20, and replaces the minimum value with the recognition evaluation value when the evaluation value is smaller. At the same time, a replacement pulse is cut out and output to the address holding circuit 39. Then, the cut-out address holding circuit 39 holds the cut-out address output from the cut-out address generation circuit 21 in accordance with the replacement pulse, and stores the cut-out address at which the minimum recognition evaluation value is obtained.

After the above processing, the large-loop operation is continued with the cut-out address output from the cut-out address generation circuit 21 as the next value. And the cutout address is 5 × 5
When the sweeping of the rectangular search area is completed, the large loop operation is completed, and the position and degree of the pattern most similar to the reference pattern are determined by the cutout address 39 and the minimum value holding circuit 3.
8 and the target color shading pattern recognition is completed.

[0035]

As described above, according to the present invention, as is apparent from the above embodiment, by using the optimum lightness correction coefficient,
The occurrence of erroneous recognition is remarkably suppressed by the change in the surrounding brightness, and the movement and shape of the object can be recognized at high speed for complete digital calculation.

[Brief description of the drawings]

FIG. 1 is a block diagram of a color shading pattern recognition apparatus according to an embodiment of the present invention.

FIG. 2 is a block diagram of a conventional color shading pattern recognition device.

[Explanation of symbols]

 Reference Signs List 11 TV camera 12 Digital RGB separator 13 R color frame memory 14 G color frame memory 15 B color frame memory 16 frame memory 17 R color reference pattern generator 18 G color reference pattern generator 19 B color reference pattern generator 20 Sweep address Generating Circuit 21 Cutout Address Generating Circuit 22 Address Adder 23 Average Value Calculation Circuit 24 Reference Pattern Y Level Average Value Holding Circuit 25 Divider 26 Optimal Brightness Correction Coefficient Holding Circuit 27 Multiplier for R Color 28 Multiplier for G Color 29 B Color Multiplier for R 30 subtractor for R color 31 subtractor for G color 32 subtractor for B color 33 squarer for R color 34 squarer for G color 35 squarer for B color 36 arithmetic adder 37 accumulator 38 minimum value Holding circuit 39 Cutout address holding circuit

Claims (1)

(57) [Claims] 1. A memory for storing a reference pattern composed of R, G, and B digital images obtained by A / D conversion from a color image signal, and a circuit for storing an average value of Y (luminance) levels of the reference pattern. And R, G,
A circuit for extracting a pattern to be recognized composed of each gray-scale image based on an extraction address from each of the digital images B and Y, and dividing the average value of the Y level of the reference pattern by the average value of the Y level of the pattern to be recognized; And a circuit for calculating a brightness correction coefficient by using R, G, B
A circuit for multiplying the pixel data of each of the patterns to be recognized to obtain the square of the difference from the corresponding reference pattern, and adding these values for all the pixels to obtain an evaluation value. A color shading pattern recognizing device for obtaining a cutout address such that