JPH0424749B2 - - Google Patents

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention provides a multi-window pattern discrimination device that extends a template matching method that discriminates patterns based on the degree of matching of an unknown pattern with a standard pattern (template); Especially regarding its improvement.

[Conventional technology]

As is clear from the various proposals that have been made for multi-window pattern discrimination devices, multiple observation areas of the target pattern, that is, multiple window areas, are set within one screen field of view, and a predetermined image is displayed within each window. The quality of the pattern is determined by measuring the feature amount and comparing the feature amount with a predetermined threshold value (judgment standard) for each window, and then calculating the correlation of the feature amount for combinations between predetermined windows. The quality of the pattern is determined by comparing this correlation calculation value with another criterion.

Figure 4 shows a pattern discrimination device previously proposed by the applicant (hereinafter referred to as the applied pattern discrimination device).
FIG. In the figure, 1 is a discrimination target object pattern, and 2 is an industrial television (ITV).
An imaging device such as a camera, 3 a binarization circuit, 4 a screen division circuit, 5 a CRT monitor, 6 an image memory,
7 is an image position detection correction circuit, 8 is a window generation circuit, 9 is an AND gate, 10 is a feature extraction circuit,
11 is a feature data memory, 12 is a discrimination circuit, 13
is a panel setting section, 14 is a control section, 15, 15a~
15d is a memory control circuit, 16, 16a to 16d
is a control information memory.

The operation will be explained.

The target pattern 1 is transported within the field of view of the TV camera 2 by a transport device (not shown). TV
The camera 2 sequentially scans the image information of the target pattern and converts it into an electrical signal. This signal is suitably amplified, then binarized by a binarization circuit 3, and divided into a predetermined number of pixels by a screen division circuit 4. The image pattern signal binarized in pixel units is stored in the image memory 6, and the relative position (edge) of the image pattern within the camera field of view is detected as two-dimensional coordinates by the image position detection and correction circuit 7. . This position data is given to the window generation circuit 8, thereby correcting the window generation timing. In AND gate 9, image memory 6
and the window position data from the window generation circuit 8, and image data corresponding to the window area is extracted. The feature extraction circuit 10 is composed of a known two-dimensional local memory, two-dimensional local logical operation circuit, counter, etc., and extracts predetermined geometric feature quantities (area, perimeter, etc.) from image data. Since the input to the feature extraction circuit 10 is controlled by the window area,
Feature amount data for each window area is extracted and stored in the feature amount data memory 11. Discrimination circuit 1
In step 2, the contents of the feature amount data memory 11 are compared with predetermined discrimination threshold data for discrimination, and the results are output. Control information memory 16a, 16b, 16
c and 16d each have binarization threshold information A ₁
~An, position correction or reference position information B ₁ ~Bn, window information C ₁ ~Cn, discrimination threshold information D ₁ ~Dn
A plurality of types of data are stored, and writing or reading thereof is performed via memory control circuits 15a, 15b, 15c, and 15d, respectively. The panel setting section 13 sets and changes each of these pieces of information, and the control section 14 receives data and instructions from the panel setting section 13 or a signal S from the outside, and controls each control information memory 16a, 16b, 16c, 16.
The information to be read from the memory control circuit 15a,
15b, 15c, and 15d. The memory control circuits 15a, 15b, 15c, and 15d are the control unit 1
4, the memories 16a, 16b, 1
Extract the prescribed information from 6c and 16d as appropriate, and
The signal is distributed to the value conversion circuit 3, image position detection correction circuit 7, window generation circuit 8, and discrimination circuit 12, respectively. Therefore, in this pattern discrimination device, the above-mentioned binarized information, position correction (reference position) information,
Window information (window shape, size),
By arbitrarily combining control information consisting of discrimination threshold information for each target pattern or target screen, pattern discrimination can be performed under optimal conditions. Cases in which such a discrimination method is required include: (a) For example, when an object has a complex shape pattern, if you try to judge the entire object as one screen, the resolution of the camera will decrease. quantization errors may occur, making accurate judgment impossible. Therefore, one object is divided into multiple screens to enlarge the object.
When it is desirable to appropriately combine the above control information for each screen to make a determination. In addition, 1
As a method of dividing one object into a plurality of screens, it is possible to move at least one of the object or the TV camera by a predetermined amount, or to provide a plurality of TV cameras.

(b) If windows are provided at multiple locations for one object and the conditions within the windows are detected, the binarization threshold information must be adjusted in order to properly extract the binarized images in each window. However, in cases where one type of binarization threshold information cannot handle multiple windows,
Even if the window information is successfully extracted, the edges (edges of the image) that should be subjected to position correction cannot be detected.

etc. are possible.

The relationship between window information and position correction information will now be explained with reference to FIG. In the figure, 21 is a position detection section, 22 and 24 are subtracters, 23 and 25 are adders, and 26 is a setting section, and these constitute the image position detection correction circuit 7 in FIG. Ru. Further, 8 is the same window generating circuit as in FIG.

Now, consider the case where a window of size Nxs and Nys is generated with points Xs and Ys as reference points relative to the origin Po on the screen. At this time, since the position of the detected edge of the target pattern is not always Xs, Ys, it is necessary to perform correction according to the detected values X, Y, and this is done using image position detection correction. It is a circuit. That is, the position detection unit 21 in FIG. 5 detects the X and Y coordinates indicating the edge of the target pattern. The subtracters 22 and 24 subtract the detected values X and Y from the reference values Xs and Ys,
Adders 23 and 25 add values Nxs and Nys that determine the size of the window to these values to obtain values Nx and Ny to be given to the window generation circuit 8. That is, Nx and Ny can be respectively expressed as Nx=X-Xs+Nxs Ny=Y-Ys+Nys. In this way, a window area of a predetermined size can be formed at a predetermined position. Therefore, as shown in Fig. 6, for example, the object pattern OB ₁ whose edges are at the reference points Xs and Ys
Of course, a predetermined window starting from the reference point is formed not only for the target pattern _OB2 whose edge is shifted from the reference point. Although it is assumed here that a rectangular window is formed, the shape can be selected as appropriate.

[Problem that the invention seeks to solve]

However, with the above-described method of detecting the edge of a binarized image and correcting the position of the window, there are cases in which the position correction cannot be applied as described below. FIG. 7 is a reference diagram for explaining the example.

The figure shows an example in which the target pattern OB is divided into nine screens PR ₁ to _{PR 9.} Assuming that the edges of the target pattern are detected for each screen, the screens PR ₁ to PR ₄ , for PR ₆ to _{PR 9} , at least one of the X and Y coordinates indicating the edge of the target pattern is always detected, but for screen PR ₅ , no information indicating the edge is detected, so position correction is not possible. There is a problem that it cannot be hung.

Further, the above position correction (reference position) information needs to be set for each screen, and even if the information is the same for each screen, it needs to be set for each screen. Therefore, setting operations are not only cumbersome and require a considerable amount of time, but also setting errors are likely to occur.

Therefore, an object of the present invention is to provide a pattern discrimination device in which position correction information can be easily set.

[Means for solving problems]

Position correction for a given partial screen (reference position)
A transfer means is provided for transferring the information as position correction information of another partial screen to a corresponding storage means.

[Effect]

If the position correction information of a screen that has already been set may be used for a screen for which position correction information has not been set, the transfer means transfers the position correction information to the corresponding storage means and sets the position correction information.

〔Example〕

FIG. 1 is a flowchart showing an embodiment of the present invention.

Screen switching (reference) is performed by inputting a screen number using a key in the panel setting section (panel key), and the control information memory or its address is selected. Whether or not to use the position correction information of the screen that has already been set for the switched screen is determined by the same instruction from the panel keys, and the flowchart branches accordingly to ○A and ○B (see).
If you do not want to use it, enter the position correction (reference position) information using the panel keys (reference) and store it in the corresponding information memory (reference).If you want to use it, enter the screen number to be used. do(
(Reference), and stores the position correction information in the corresponding information memory or its predetermined address (Reference).
The above setting operations are performed sequentially for each screen, and continue until the settings for all screens are completed (
reference). Note that input information from the panel keys can be displayed on the CRT monitor 5 (see FIG. 4) if necessary.

FIG. 2 is a reference diagram for explaining the method of diversion of position correction information, and FIG. 3 is a time chart for explaining the operation when diversion of position correction information is automatically carried out.

Now, the target pattern OB shown in Figure 3
Considering the case where the screen is divided into two parts PR and PR', the edge detection value of the image OB cannot be obtained for the screen PR', so for example, if we decide to use the position correction information of the screen PR, screen
The above-mentioned setting operation is performed for PR', and the same position correction information as screen PR is set in the corresponding information memory.

The above is a case where the position correction information is diverted by setting operations each time, but it can also be done automatically as shown in FIG.

That is, in response to the screen PR judgment start signal _S1 given from the control unit 14 in FIG. 4, the image position detection and correction circuit 7 detects the edge of the target pattern,
The corresponding position correction information Xs, Ys is automatically determined at time t ₁ and stored in the information memory 16B, while a window area of a predetermined size is formed based on this and the Image data within the area is determined. Next, the screen PR' determination start signal _S2 is given, and when it is confirmed that an instruction to divert the screen PR position correction information has been issued, the screen PR position correction is performed at a predetermined time point _t2 . Information can be read from the memory 16b, thereby forming a window area and determining image data. In this case as well, the location information of which screen is to be used is first determined by inputting the screen number from the panel keys, and the information continues to be used until the screen designation is canceled.

By doing this, you only need to perform the setting operation once and the rest can be done automatically.

〔Effect of the invention〕

According to the present invention, since position correction information regarding a certain screen can be used on another screen, it is not only possible to perform position correction on any screen, but also the use of such information can be made by changing the panel settings. This can be easily done by key operation on the unit, which simplifies operator operations, reduces setting errors by the operator, and shortens setting time.As a result, the discrimination accuracy of the pattern discrimination device is improved. This provides various advantages such as the ability to

[Brief explanation of drawings]

Fig. 1 is a flowchart showing an embodiment of the present invention, Fig. 2 is a reference diagram for explaining how the position correction information is used, and Fig. 3 shows the operation when the position correction information is automatically used. A time chart to explain, Fig. 4 is a block diagram showing a pattern discrimination device for which the application has been applied, Fig. 5 is a block diagram showing a specific example of an image position detection correction circuit, and Fig. 6 explains why position correction is necessary. FIG. 7 is a reference diagram showing an example in which the target pattern is divided into a plurality of screens. Code explanation, 1...Target pattern, 2...Television camera, 3...Binarization circuit, 4...Screen division circuit, 5...CRT monitor, 6...Image memory, 7
... Image position detection correction circuit, 8 ... Window generation circuit, 9 ... AND gate, 10 ... Feature extraction circuit, 11 ... Feature data memory, 12 ... Discrimination circuit, 13 ... Panel setting section, 14 ... ...control unit,
15, 15a to 15d...Memory control circuit, 1
6, 16a to 16d...control information memory, 21...
...Position detection unit, 22, 24...Subtractor, 23, 2
5... Adder, 26... Constant setting section.

Claims (1)

[Scope of Claims] 1. An imaging system that divides one target pattern into a plurality of parts, images the parts, and extracts partial images; and binarization means that binarizes the imaging signal at a predetermined threshold level; a position correction means for detecting the edge of the target pattern portion in each partial screen and calculating an amount of correction thereof from a predetermined reference position; a window forming means for forming a predetermined window area based on the correction amount;
a discriminating means for extracting an image feature amount of a target pattern portion within the window and comparing it with a predetermined criterion to make a discrimination; and the binarization threshold information, reference position information, window information, and criterion information. a memory means for storing a plurality of types of information, a memory selection means for reading out each piece of stored information based on a predetermined instruction and providing it to the corresponding means, and an instruction for giving a predetermined instruction to the memory means. and a transfer means for transferring the reference position information regarding a predetermined partial screen to the corresponding storage means as the reference position information for another partial screen, A pattern discrimination device characterized in that it can be used on a screen. 2. The pattern discrimination device according to claim 1, wherein the transfer means includes an input means and a display means, and transfers information in an interactive manner.