JPS6380372A - Pattern recognition device - Google Patents

Abstract

PURPOSE:To execute logical operation at a high speed to recognize a specific pattern in a short time by designating specific picture elements of the pattern and subjecting only specified picture elements to logical operation and recognizing the pattern with a small number of operations. CONSTITUTION:Information of a reference picture element A and featuring picture elements B, C, and E is inputted to define picture elements A, B, C and E as specific picture elements of a pattern. Coordinates (X, Y) of specific picture elements to the reference picture element and their values P are set to the value of the picture element A. When the heading offset value of picture data is defined as SOFF, a heading offset value ROFF of objective picture data is obtained in accordance with an equation I where XH indicates the size in the horizontal direction. The number of picture elements on picture data is checked, and the following processing are skipped if the pattern is absent. Next, picture data is subjected to the operation in accordance with a formula II. In the next stage, the operation is performed in accordance with a formula III. Feature points B and C are subjected to the operation in accordance with the formula II, and results and the feature point E are subjected to the operation in accordance with the formula III, and results are transferred to an output area. These operations are executed in all areas.

Description

DETAILED DESCRIPTION OF THE INVENTION [Field of Industrial Application] The present invention relates to a pattern recognition device that recognizes a specific pattern from image data.

[Conventional technology]

A conventional pattern recognition device of this type is shown in FIG. In addition, FIG. 8 shows the results of the conventional pattern recognition device shown in FIG.
985, pp. 107-111, is a diagram showing a pattern recognition method called template matching. In FIG. 7, 1 is a template memory that stores template data, 2 is a storage device that stores drawing image data, and 3 is the template memory 1 and the storage device 2.
This is a calculation lid that measures the degree of coincidence of data stored in the .

Next, the operation will be explained. First, when recognizing the pattern shown in FIG. 8(a), the eighth
Prepare the template data shown in Fig.
The image data of the drawing stored in 12 is compared with the arithmetic unit 3. The arithmetic unit 3 checks whether pixels within the size of the template data in the image data (portion within the broken line in FIG. 8C) match the pixel values of the template data, and determines whether the patterns match. This operation moves the matching range in the image data one pixel at a time (arrow in Figure 8(c)).
, is performed on the entire image data, and the results are stored in the storage device 2.

[Problem that the invention seeks to solve]

Since the conventional pattern recognition device is configured as described above, the calculation of the number of pixels of template data is performed as many times as the number of pixels of image data.

If the template data is 82 x 82 pixels and the image data is 100 x 100 pixels, the number of calculations is approximately 1.
,000,000,000 times. Even if the 0 calculation device 3 can perform calculations 1.000,000 times per second, it will take 1000 seconds. As described above, there is a problem in that the processing takes time.

The present invention was made to solve the above-mentioned problems, and it is an object of the present invention to provide a pattern recognition device that can recognize a specific pattern from image data in a short time.

[Means for solving problems]

The pattern recognition device according to the present invention specifies a certain pixel having a characteristic value in a pattern to be recognized, obtains pixel data having that characteristic, stores it in a storage device, and executes the process using a central processing unit. A specific pattern is recognized by performing arithmetic processing. In addition, in the case of a pixel with multiple characteristics, an arithmetic function that skips multiple logical operations is added to the central processing unit to perform high-level logical operation processing.
The designation of a specific pixel in the pattern recognition device of the present invention is performed by performing logical operations only on the specified pixels, thereby recognizing turns with a small number of operations. A logical operation is performed on one word of pixels on the image data using the internal register of the image data, the pixel values on the image data are checked, and if a pattern does not exist, the process is skipped and moves on to the next pixel processing.

〔Example〕

An embodiment of the present invention will be described below with reference to the drawings. 1st
In the figure, 4 is a storage device that stores the calculation result of the binary image data of the drawing and the data of the pattern to be recognized, and 5 is the storage device that stores the recognition data in which a corridor is formed by 101 data of the pattern size to be recognized. temporary storage device, 6
is a central processing unit fH (abbreviated as CPU). In addition,
The central processing unit 6 has a function of performing high-speed logical operations on areas specified in bit units and other areas, and executes the above operations at approximately several Mbytes/second.

Next, the operation will be explained. First, in the flowchart of FIG. 2, initial settings are performed in step 7. Binary image data such as a drawing, a reference pixel of a pattern to be recognized, pixel values characteristic of the pattern, and coordinates for the reference pixel are input into the storage device 4. Further, an area for calculation result data is secured in the storage device 4 according to the size of the image data and initialized to 11'. Below, Figure 3 (
This will be explained assuming that the pattern a) is recognized. In this case, in step 7, as shown in FIG. 3(b), information on the reference plane amateur and characteristic pixels B, C, and E is input.

Then, let A, B, C, and E be specific pixels of the pattern.

In step 8, the coordinates (X,
Y) and its value P are set to the values of the reference plane amateur.

Next, in step 9, a region to be subjected to logical operations is set based on coordinates (X, Y). That is, the one-dimensional distance (difference in offset value) between the target image data and the image data when the image data is arranged as a one-dimensional memory is determined. If the start offset value of the image data is 5OFF, the start offset value ROFF of the target image data is ROFF = 5OFF - (XHxY) +X
−−・・−・It is obtained by (1). Here XH is the fourth
The horizontal size 44 of Figure 3) is shown.

In step 10-a, it is determined whether the value of the original data (image data) is "0" or not, and if it is '01, the logical product is skipped and the process branches to step 14. If it is not '0', the logical operations of steps 11 and 12 are executed for the number of feature points, and the number of pixels (number of features) on the image data is checked.

Further, in step 10, the value of P is determined and pr.

That is, if P=1, the process moves to step 11, and if P=0, the process moves to step 12.

In step 11, the following logical operation is performed on the image data.

R←CRopp”)C3opp)−”0°”(2) Here, (SOFF) is the content of the image data (starting offset value of the image data), (ROFF) is the content of the target image data, and R is the calculation result. The register to store, . represents logical product.

This calculation will be explained with reference to FIG.

FIG. 4(a) is a diagram showing image data, FIG. 4(a) is a diagram illustrating a logical operation between image data and target image data, and FIG.

Regarding the logical operation in Figure 4 6), feature point B in Figure 3 (b)
This will be explained using the case of For the sake of simplicity,
An explanation will be given on a two-dimensional memory, and then an explanation will be given on operations on a -dimensional memory.

First, the coordinates of feature point B with respect to reference pixel A are (XB-Y
B) and the value is 111, so S(x×XB, y+
When YB ) and S (x, y) are superimposed, it becomes as shown in Fig. 4, etc.). 41 is image data of S (x, y), 42
indicates S (X+XB, y+YB) image data. The pixel (xo
-yo), then S (x o +XB * 76 +Y
B) becomes 1111. Therefore, if the specific pixel (x, y) on the pattern is 111, then S (x+X = 3'+
There is a possibility that the reference pixel of the pattern exists at the pixel where Y) is 111.

Superimposing the image data 41 and 42 is equivalent to performing a logical product of the image data 43 and 41 with a coordinate shift of (XB, YB) based on the image data 41. Considering this as a logical operation on the -dimensional memory, image data 45...starting offset value 5OFF to 3
The 2-bit data and the target image data 46...32-bit data from the start offset value ROW are ANDed.

In step 12, the following logical operation is performed.

R←(ROFF) Fist R (3) R is a register that stores the calculation result, and (ROFF) indicates the inverted contents of the target image data.

This calculation will be explained with reference to FIG. Figure 5 (a) is a diagram showing image data, the town in Figure 5 is S (x+X, y+
Regarding Y), Figure 3 is a diagram explaining E of G), Figure 5
Figure (c) is a diagram showing the calculation results. Since the coordinates of pixel E with respect to reference pixel A are (XE - YE) and the value is "01," S (X+XB, y+Yg) and 5 (x-
If you overlap y), it will look like Figure 5 et al). 51 is S(x
, y), 52 is S (x+XB = 7+YE)
shows.

The pixel (xo
h )'o ) then S (XO+XB -)'o+YE
) becomes 10”.

Therefore, if a specific pixel (x, y) on the pattern is "0", it is possible that the reference pixel of the pattern exists at the pixel (x, y) on the image data where S (x+X = )'+Y) is @ge. There is sex.

Similarly to step 11, using the image data 51 as a reference (
The logical product of the image data 53 and 41 shifted by the coordinates (XE, YE) is executed.

The calculations in steps 11 and 12 are repeated for the number of target image data. In FIG. 3, et al., the calculation in step 11 is performed for the feature points B and C, and the calculation in step 12 is performed for those results and the feature point E, and the results are transferred to the output area. The above calculation is executed for the entire area.

Figure 6 shows pattern recognition using this design.

That is, from the image data of FIG. 6(a), FIG. 3(a)
) patterns. The result of performing the logical operation on feature point B is shown in Figure 6(c), the result of performing the operation on feature point C is shown in Figure 6(c), and the result of performing the operation on feature point E is shown in Figure 6(). The calculation result shown in d) is obtained, and the pixel in which the reference pixel of the pattern 3) exists remains, and the pattern is recognized. However, in this patent, since the calculations for feature points B, C, and E are performed using registers, the situations in Figure 6 (b) and (c) are not output, and the processing result in (d) is obtained. It will be done.

To specify a specific pixel on a pattern, select a pixel that is characteristic of the pattern in relation to the image data.

The calculations of equations (2) and (3), steps 11 and 12, are performed at high speed by the central processing unit 6, which is capable of data calculations on variable length fields.

In the case of image data of 1000 x 1000 pixels, even if the computing power of the central processing unit 6 is 4 Mbytes/sec, the computing time for one specific pixel on the pattern is approximately 0.0
If the number of pixels designated on the pattern is 10, the calculation time will be approximately 0.3 seconds. Even if all 32×32 pixels are designated as specific pixels, the calculation time is about 30 seconds. Processing time can be shortened by specifying specific pixels of a pattern and performing high-speed logical operations.

In the above embodiment, the calculation output results from the central processing unit are stored in the storage device, but if they are stored in the storage device for display on the display device, the calculation results can be immediately displayed on the display device. be done.

In addition, although only the logical product was performed as a logical operation on the image data, in order to maintain margin in pattern recognition, it was executed by finding the ones that hold n out of m feature points (n6
m) I can. Further, regarding this processing, since the number of logical operations between image data increases, the number of operations of internal registers increases, and the speed of the storage layer can be increased. (For example, the operation speed of the internal register is approximately 32 Mbytes/second.) [Effects of the Invention] As described above, according to the present invention, a specific pixel of a pattern is specified and a logical operation is performed only on the specified pixel. By doing so, pattern recognition can be performed with a small number of calculations, so that a specific pattern can be recognized in a short time by executing high-speed logical calculations.

[Brief explanation of the drawing]

FIG. 1 is a block diagram showing the configuration of a pattern recognition device according to an embodiment of the invention, FIG. 2 is a flowchart showing the operation of the pattern recognition device according to an embodiment of the invention, and FIGS. 3(a) and (b) ), Figures 4(a) to (e). 5th part) to (c) and FIGS. 6(a) to (d) are explanatory diagrams showing the operation of a pattern recognition device according to an embodiment of the present invention, and FIG. 7 shows the configuration of a conventional pattern recognition device. The block diagrams shown in FIG. 8) to (c) are explanatory diagrams showing the operation of a conventional pattern recognition device. In the figure, 4 is a storage device, 5 is a temporary storage device, and 6 is a central processing unit. Patent applicant Mitsubishi Electric Corporation Figure 1 Figure 6: Nakao: Actual calculation processor 5\ device Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7

Claims (2)

[Claims] (1) A storage device that stores the binary image data of the drawing and data of specific pixels of the pattern to be recognized, and a logical operation between data in an area specified in bits of the storage device and data in other areas. A temporary storage device for storing positional information of a specific pixel of a pattern to be recognized and a register inside the central processing unit described later while controlling an area specified in bit units of the storage device and other areas and types. A pattern recognition device equipped with a central processing unit that performs logical operations on pixels of one word on image data at once, and skips the number of pixels on the image data when no adjustment pattern exists. (2) If there are multiple pixels with characteristic values in the pattern to be recognized, a calculation function is added to the central processing unit that skips multiple logical operations, and the number of elements in the image data is increased. The pattern recognition device according to claim 1, characterized in that the pattern recognition device is configured to check the pattern recognition device.