JPS6255781A - Pattern matching method - Google Patents

Abstract

PURPOSE:To extract an area where the maximum degree of coincidence between patterns and to attain the accurate position detection, by defining a part where a small area has a contact with an uncollated area of a picture pattern as an invalid area and invalidating the reference point of collation when this reference point showing the maximum degree of coincidence exists in said invalid area. CONSTITUTION:A collation is carried out at the 1st reference point of collation and a comparison is performed immediately with the 1st pass reference value. Then no processing is carried out when the failure is decided and said comparison is carried out continuously until the processing is through for all 1st reference points of collation. While the 2nd collation processing is started at the 1st reference position of collation in the case of success. Then it is decided whether or not the position reaches the final 1st reference point of collation in the case of failure. When it is successful for the 2nd collation processing, the data on the point of recognition is stored and then it is decided whether or not a prescribed number of points of recognition are detected. If so, all processes are through. When the prescribed number of points of recognition are detected, the processing is discontinued at that time point. Thus the number of the 1st collating processes can be decreased and the processing speed is increased with a pattern matching method.

Description

DETAILED DESCRIPTION OF THE INVENTION Field of Industrial Application The present invention is directed to high-speed positioning of a specific pattern present in an image pattern obtained from an imaging device, which is necessary when, for example, mounting an IC component on a circuit board. detect, 2
The present invention relates to a pattern matching method used in a dimensional position detection method.

BACKGROUND OF THE INVENTION Conventional position detection methods using pattern matching can be roughly divided into the following: 1. After storing one frame of an image pattern obtained from an imaging device in an image pattern storage device such as a semiconductor memory, matching processing with a standard pattern is performed. Method.

2. A device that generates the coordinates of the position being scanned by the imaging device, and an image pattern storage device such as a semiconductor memory that has the minimum capacity necessary for matching with the standard pattern. A method of performing matching processing while importing image patterns.

It can be classified into two types.

Therefore, we will examine three items regarding these two pattern matching methods: processing speed, processing scalability, and cost.

First, regarding the processing speed, the first method is image pattern 1.
Since the collation process is performed after frames are loaded into the storage device, it generally requires processing time and is not suitable for real-time processing. The time required to import one frame of the image pattern into the storage device is Ti, and the time required to import one frame of the image pattern into the storage device is 1.
Assuming that the time required for matching the image pattern for one frame with the standard pattern 7 is Tp, the time "ml" required for pattern matching by the first method is calculated by the sum of T and Tp in equation (1). ”tnl = ”i” ”p −
"・It is expressed as (1).The second method performs the matching process while capturing the image pattern, so the processing time is short and suitable for real-time processing.The time required for pattern matching by the second method" m2 is equal to T and is expressed as in equation (2).

"m2"""i...
...-@) In the first method, in order to speed up the process, matching reference points are set roughly every few pixels on the image pattern, first matching is performed for one screen, and then those matching points are set roughly every few pixels on the image pattern. Based on the matching reference points with a sufficiently high degree of matching obtained from the results,
A pattern matching method with a hierarchical structure in which recognition points are searched for through detailed matching using a search method is often adopted.

Next, we will discuss the extensibility of processing. In the first method, the image pattern obtained from the imaging device is stored in the storage device, so the weighting of the operators can be freely set depending on the process such as filtering, which is the preprocessing for matching with the standard pattern. After completion of the matching process, it is possible to selectively extract a specific area of the image pattern again and perform the confirmation process based on the result. Furthermore, when performing matching processing, it is also possible to scan the alignment point between the image pattern and the standard pattern (hereinafter referred to as matching reference point), which serves as a reference for matching, in a direction perpendicular to the scanning direction of the imaging device. . Second
Although it is possible to perform preprocessing such as filtering and confirmation processing after matching processing in the method described above, the preprocessing is fixed and the weights of operators during filtering processing cannot be easily changed, and the preprocessing after matching processing is fixed. The confirmation process cannot be performed on the same screen where the verification result was obtained.

Finally, we will discuss the cost of realizing a pattern matching device using these proposed methods.

The first method requires more storage elements such as semiconductor IC memory than the second method in order to store the image pattern for one frame, and the second method requires the image pattern to be sent in real time. This method requires more logic ICs than the first method because it compares the data with a standard pattern. In the past, semiconductor IC memories were expensive, making it difficult to realize the first method at a low cost.However, in recent years, the degree of integration of semiconductor IC memories has increased rapidly, and the price per unit storage capacity has decreased, making it difficult to implement the first method at a low cost. The price has become cheaper than the logic IC that implements this method. Therefore, at present, it is possible to realize a pattern matching device at a lower cost by adopting the first method.

From the above, if the first method is adopted, a device with expandable functions can be realized at low cost, although it takes processing time, and if the second method is adopted, the functions are limited and costs are reduced. It can be said that it is possible to realize a device capable of high-speed processing, although it is somewhat expensive.

The present invention relates to a pattern matching method for performing two-dimensional position detection in real time using the first method described above. The reason why the first method, which is unsuitable for high-speed processing, was intentionally adopted is because the pattern matching process is highly scalable and flexible, as described above, and it can be realized at a lower cost than the second method. Moreover, the present invention
It is assumed that a high-speed processing method of the hierarchical pattern matching method using the above-mentioned coarse matching process and detailed matching process is adopted.

Conventionally, in the hierarchical pattern matching method that combines coarse matching processing and detailed matching processing to speed up the pattern matching processing, all of the first matching reference points that are coarsely provided every few pixels on the image pattern are The coordinates of P first matching reference points where the degree of match between the standard pattern and the first reference point 1 is equal to or higher than the first acceptance criterion value are held, and the coordinates of these P first reference points are stored. The second step is a detailed matching process for a small area set near the matching reference point.
The second matching reference point that gives the maximum matching degree among the second matching degrees obtained as a result of the matching processing is set as the recognition point. This is because the conventional pattern matching method is based on a one-point recognition process in which an image pattern and a standard pattern are matched to find a matching reference point that provides the maximum degree of matching.

Furthermore, when the hierarchical pattern matching method is applied to multi-point recognition processing, a small area is set near the matching reference point that passed the first matching process, and a plurality of second matching points provided within that area are set. A comparison process with a standard pattern will be performed at the reference point. The second step is to determine whether it is a recognition point or not.
The maximum value among the plurality of second matching degrees obtained as a result of the matching process is the predetermined reference value.
This is done based on whether it meets or exceeds the passing standard value.

Problems to be Solved by the Invention However, with the above configuration, for example, it is difficult to detect the positions of multiple IC components quickly and accurately within the processing time required when mounting IC components on a circuit board. That's difficult.

FIG. 2 shows a standard pattern 31 with a size of MXM, a comparison reference point 32 of the standard pattern 31, an image pattern 33 with a size of N x N, and first comparison points provided every n pixels on the image pattern 33. A reference point 34 is shown. The first matching process, which is a rough matching process, uses the standard pattern 31.
This is done by aligning the matching reference point 32 of the image pattern 33 with the first matching reference point 34 of the image pattern 33 and comparing the two patterns. Conventionally, this first matching process is performed on all of the first matching reference points 34, and then each of the first matching reference points that gave a degree of matching equal to or higher than the first acceptance standard value in the matching process for cylinder 1 is A second matching process, which is a detailed matching process, was performed on the second matching process. However, the number of first matching reference points is enormous, and the processing time required to match the standard pattern at all the first matching reference points alone is several times the time required to capture the image pattern. In the example of FIG. 2, the number of first matching reference points existing on the image pattern 33 is given by the following equation (1).

-M 1knee+1 )2 ・・・・・・(1)
The symbol [a] is a Gauss symbol and represents the largest integer not exceeding a. For example, if N=512, M=16, and n=4, the number of first reference points becomes about 15,600.

FIG. 3 shows three first matching reference points 36, 36, 37, and second matching processing areas 38, 39, 40, . . . at each reference point.
A matching reference point 41 where the degree of matching is maximum near the area shown in the figure, an area 42 where there is a matching reference point that gives a degree of matching exceeding the second acceptance criterion value, and a matching reference point having the second highest degree of matching in that area. Point 43 is shown. As is clear from the figure, the areas 38, 39, and 40 where the second matching process is performed are set so that adjacent areas overlap each other little by little.

Three areas 38 and 39 perform this second matching process.

When the comparison process with the standard pattern is performed in step 40, the degree of matching at the reference point 43 becomes maximum in any region. Since the matching reference point 43 is included in the region 42 of matching reference points that give a degree of matching that exceeds the second acceptance criterion value, three regions 38, 39, 4 in which the second matching process is performed are included.
In any of the matching processes at 0, the matching reference point 4
3 is detected as a recognition point. However, in reality, a true recognition point with a higher degree of matching exists at the lower right of the matching reference point 43. Therefore, the three first reference points 35
．． The recognition point 43 detected from 36.37 is an erroneous recognition point.

In view of the above-mentioned problems, the present invention provides a hierarchical pattern matching method for the purpose of quickly and accurately detecting a plurality of recognition points existing in an image (turn).

Means for Solving the Problems In order to solve the above problems, the pattern matching method of the present invention stores an image obtained from an imaging means as a digitized image pattern in a storage means, and stores the image pattern in the form of a digital image. In a pattern matching process in which a characteristic partial area is stored in advance as a standard pattern in a storage means different from the storage means, and the image pattern and the standard pattern are matched, the image pattern and the standard pattern are A matching reference point, which is a registration point of After performing the verification process,
If the first matching degree obtained as a result of the matching process is larger than a first reference value given in advance, a plurality of second matching reference points are set in the vicinity of the first matching reference point,
generation at a second interval narrower than the first interval, performs a second comparison process with the standard pattern at all of the plurality of second comparison reference points, and obtains the result of the second comparison. The second matching reference point with the highest matching degree among the plurality of second matching degrees is the one that has not yet been matched with the image pattern in the area where the plurality of second matching reference points exist. Only if it does not exist in the area facing the boundary with the area where it has not been performed and is larger than the second reference value given in advance, the second The present invention is configured to detect a plurality of recognition points existing on the image pattern by validating the matching reference.

Function First, for the sake of simplicity, the image pattern and standard pattern are @
The operation of this technical means will be explained with reference to the drawings, using a binary pattern of O'' or l'1'', where 1'01 represents black and 1'' represents white.

FIG. 4 shows a flowchart of a conventional hierarchical pattern matching method. First, a matching process 61 is performed on all the first matching reference points for a given image pattern, and then a passing point whose degree of matching is equal to or higher than the first passing reference value in the first matching process is detected 62. , a second matching process 63 is performed on the detected passing score. And as a result,
If a recognition point is detected, the recognition point data is stored 64. Of the four processes shown in FIG. 4, the one that requires the most processing time is the first matching process 51 at all first matching reference points. Moreover, with this processing method, all the first
The time required for the matching process 51 at the matching reference point is fixed and cannot be reduced at all. Therefore, in the hierarchical pattern matching method of the present invention, the first matching process is performed on all first matching processes based on the flowchart shown in FIG.
In order to speed up the processing, the comparison is not necessarily performed on the comparison reference points of . In FIG. 6, first, a matching process 65 is performed at the first matching reference point, and immediately
A rejection determination 56 of the first verification process is performed by comparing the result with the acceptance reference value of . If the result is a failure, no processing is performed, and a determination 57 is made as to whether or not the last first matching reference point existing on the image pattern has been reached, and all first matching reference points are 7. If the matching process 66 at the first matching reference point passes, the second matching process 58 is performed from that first matching reference position, The maximum value of the degree of matching obtained in is compared 59 with the second pass reference value, and in the case of failure, a determination 57 is made as to whether the final first matching reference point has been reached. If the second matching process 58 is passed, the recognition point data is stored 6o, and then a determination 61 is made as to whether or not a predetermined number of recognition points have been detected, and if so, all processing ends. However, if not, a determination 57 is made as to whether the final first reference point has been reached. In this way, in the present invention, when a predetermined number of recognition points are detected, the process is stopped at that point, thereby reducing the number of times the first matching process is performed and speeding up the process.

In addition, the matching process at the first matching reference point provided every n pixels is a rather rough process that is used to determine whether there is a possibility that a recognition point exists in the vicinity. Therefore, it is not necessary to match the entire area of the standard pattern with the image pattern, and it is sufficient to match a portion 63 of the standard pattern 62 with the corresponding image pattern, as shown in FIG. In this way, limiting the matching process at the first matching reference point to only the partial area 63 of the standard pattern 62 also helps speed up the process.

Next, in the present invention, in order to avoid erroneous recognition, if the matching reference point with the highest degree of matching obtained in the second matching process faces an area where no matching process has been performed, the matching will be even higher. Considering that there is a possibility that a matching reference point indicating the degree of matching will appear in the future, the matching degree at this matching reference point is invalidated. FIG. 7 is a diagram showing such an example, in which the verification at the first verification reference point 64 is passed, and the second verification process is performed on the small area 65. As a result, the second reference point 6
6, the degree of coincidence reaches its maximum at the matching reference point 67, but in fact, the matching degree reaches its maximum near this point at the matching reference point 67, and this matching reference point 67 is connected to the next first matching reference point 6.
8 is included in an area 69 in which a second matching process is further determined. Therefore, as shown in FIG. 8, corresponding to the directions υF1 and υA 72 in which the first reference point 7Q has moved, an unverified area is located in the small area 73 for the second verification. The facing area 74 is defined as an invalid area. Then, the matching reference point 75 that has the maximum matching degree in the area 73 where the second matching process is performed, which is determined from the first matching reference point 7o, is
The point will be on this invalid area 74, and in such a case, the matching reference point 76 with the highest degree of matching will not be selected. Then, as shown in FIG. 9, the matching reference point 78 that exists in the region 77 for performing the second matching determined from the next first matching reference point 76 and has the maximum matching degree is selected as the recognition point. This recognition point 78 is located next to the collation reference point 79 which was about to become an erroneous recognition point, and is not included in the invalid area 80 at this time.

In this way, in the small area where the second matching is performed, the area facing the unmatched area is defined as an invalid area, and if there is a matching reference point within this area that has the highest degree of matching, this matching reference point is Accurate recognition was ensured by not taking up the subject.

EXAMPLE Hereinafter, a pattern matching method according to an example of the present invention will be described with reference to the drawings. FIG. 1 shows a block diagram of a pattern matching method according to an embodiment of the present invention. In FIG. 1, a video signal 2 obtained from an imaging means 1 such as a television camera is binarized by a binarization means 3 to become an image pattern 4 and stored in an image pattern storage means 6. The image pattern storage means 5 is controlled by an image pattern control means 6, and the input/output of image patterns is performed by commands 8 from the central processing means 7. On the other hand, the standard pattern 9 is cut out from the image pattern storage means 5 at the time of teaching and held in the standard pattern storage means 10 prior to the pattern matching process. The standard pattern storage means 10 is controlled by a standard pattern control means 11, and the standard pattern is output according to a command 12 from the central processing means 7. The central processing means 7 also reads out pattern data 13 and 14 to be matched from the image pattern storage means 6 and the standard pattern storage means 10, respectively, when performing the matching process between the image pattern and the standard pattern, and performs a logical operation. It has the role of transmitting the command 8 to the image pattern control means 6 and the command 10 to the standard pattern control means so as to be input to the means 16, and the role of controlling each block in FIG. The two pattern data 13 and 14 input to the logic operation means 16 are
Therefore, matching is performed by negating the exclusive OR, and if the corresponding pixels in the two pattern data match, the matching result is 1''; otherwise, it is 0''.
become. Standard pattern is M! When it is composed of xM pixels, this logical operation is performed on M pixels at a time, and the result of the logical operation is M8 "Om-@1".
The data 16 is sent to the coincidence calculation means 17, where 1'
The number 111+ is calculated.

For a standard pattern consisting of M pixels x M pixels,
By repeating the above process M times, the matching process for the entire Sakaki pattern is completed.
Then, cumulative addition is also performed while calculating the number of M8 "o" and "1" data 16 (7) @ 1' (7) sent each time. In the case of the first matching process, the calculated degree of coincidence 18 is sent to the central processing means 7, where it is compared with the first acceptance criterion value. In the case of the second matching process, for example, when the area targeted for the second matching process consists of 6 x 5 second matching reference points, the matching process with the standard pattern is performed continuously at 26 matching reference points. The coincidence degree 19 calculated by the -growth calculation means 17 is all sent to the maximum-growth storage means 20, where it is compared with the maximum-growth,
Maximum-growth is stored. - When comparison with the maximum growth degree is performed 25 times following the calculation of the growth rate, the maximum growth rate 21 held in the maximum growth storage means 20 at that point is sent to the invalid area determination means 22. It will be done. The invalid area determining means 22 determines whether the matching reference point showing the maximum degree of conformity exists in the invalid area, and if it is included in the invalid area, resets the degree of coincidence to zero. The maximum degree 23 obtained as a result of the second matching process is sent to the central processing means 7, where it is determined whether or not a sufficient degree of coincidence has been obtained as a recognition point. When the recognition point is determined, the recognition point data 24 consisting of -composition and the X and y coordinates of the comparison reference point is stored in the detection position storage means 26, and when all processing is completed, the recognition point data 24 is stored in the detection position storage means 26. All the detected position data 26 stored in the means 26 is transmitted to the upper controller 27.

An outline of the operation of the pattern matching method configured as described above will be explained below using FIG. 10. In FIG. 10, a characteristic portion of an image pattern 91 having a size of N×N pixels is given in advance to a standard pattern 90 having a size of N×N pixels. First matching points 92 are set at every n pixels on the image pattern 91, and the first matching process starts at a matching reference point 93 which is the starting point.
From there, it moves from left to right in the horizontal direction toward the collation reference point 94, which is the end point, and advances overall from top to bottom. In the matching process shown in FIG. 1, the standard pattern 90 and the image pattern 91 are matched at each matching reference point, but the process is speeded up by matching only the partial area 96 of the standard pattern. ing. In FIG. 10, two recognition points 96 and 97 are indicated by cross symbols, and these recognition points are detected from first reference points 98 and 99, respectively. If the number of recognition points to be determined is two, the recognition point e7 is selected from the first reference point 99.
The process ends when this is detected. Therefore, for the first matching reference points 92 that exist in large numbers in the image butter 791, the first matching process is performed only on about half of the first matching reference points that are filled in black. Therefore, the time required for the first matching process can be reduced to approximately half that of when the entire screen is processed.
Pattern matching processing is sped up.

Next, using FIG. 11, a state in which a recognition point is detected after passing the first matching process is shown. A small area 101 consisting of 6×5 pixels is set around the matching reference point 100 that passed the first matching process. This area becomes the area where the second matching process is performed. In the second matching process, all of these 25 points are used as second matching reference points, and the standard pattern 10
Check with 2. At this time, the entire area of the standard pattern 102 that is different from the first matching process becomes the matching target area.

As a result of the second matching process, the maximum matching degree is obtained at the matching reference point 103, but since this matching reference point 103 exists outside the invalid area 104, the matching degree at this time becomes the maximum matching degree. , is compared with the second acceptance standard value and becomes a recognition point. When the second matching process is completed, the process returns to the first matching process, but the restart point of the first matching process at this time is the first matching standard next to the previous first matching reference point 100. The point becomes 106.

As described above, according to this embodiment, in the first matching process, only partial areas of the standard pattern are matched, and if a predetermined number of recognition points can be detected, the process is interrupted at that point. This speeds up the pattern matching process, and in the matching process limited to a small area, by setting an invalid area, it is possible to accurately extract the maximum point of matching and reduce misrecognition.

In addition, in the embodiment of the present invention, recognition points are detected in two stages of the first matching process and the second matching process, but depending on the size of the image pattern/standard pattern and the complexity of the pattern to be recognized, Alternatively, the process may be performed in two or more stages by increasing the setting interval of the first comparison reference points and performing several comparisons until the final comparison in which the comparison reference points are set for each pixel. FIG. 12 shows an example of three-stage matching.

Verification is performed one after another in the partial areas 111 of the standard pattern against the first verification reference points 110 provided every four pixels,
Assume that the test is passed at the verification reference position 112. Next, 3×3 second matching reference points 114 are set for every two pixels based on the first matching reference point 113 that passed the test. For the nine matching reference points, matching is performed using the partial area 115 of the standard pattern.

If the matching reference point 116 with the maximum matching degree as a result of the nine matching processes is not included in the invalid area 117, this maximum matching degree is compared with the second passing standard value. Passed. In the third matching process, which is the final stage matching process, 3×3 matching reference points 119 are provided at every other pixel so that the passing score 118 of the second matching process is centered. The nine matching reference points are matched with the partial area 12o of the standard pattern, and the matching reference point 121 with the maximum matching degree obtained as a result of nine matching processes has the third matching degree. It becomes a recognition point when it exceeds the passing standard value.

Effects of the Invention As described above, the present invention provides the above-mentioned method when performing matching on a small area in an image pattern consisting of a plurality of matching reference points and finding a matching reference point that has the maximum degree of matching in the small area. The part where the small area touches the unmatched area of the image pattern is defined as an invalid area, and when a matching reference point that shows the maximum matching degree exists in this invalid area, that matching reference point is invalidated to maximize the matching degree. It extracts the area and enables accurate position detection. In addition, the size of the matching area of the standard pattern to be matched with the image pattern is determined by the interval at which the matching reference points are set, and when a predetermined number of recognition points are obtained, processing is performed at that point. By interrupting and terminating the process, high-speed position recognition is possible.

[Brief explanation of drawings]

FIG. 1 is a block diagram showing the configuration of a pattern matching method that is an embodiment of the present invention, and FIG. 2 shows the sizes of a standard pattern and an image pattern, and the size of a first A diagram showing the reference points for comparison, Figure 3 is the first
Figure 4 is a flowchart showing the conventional hierarchical pattern matching algorithm, and the area where the second matching process is performed, which is set based on the matching reference point in the figure, and the false recognition points and true recognition points. Figure 6 is a flowchart showing the hierarchical pattern matching algorithm according to the present invention, Figure 6 is a diagram showing partial areas to be matched in the standard pattern, and Figure 7 is the second matching algorithm. A diagram showing that the matching reference point with the highest degree of matching in the process is not necessarily the maximum point. Figure 8 is a diagram showing the second matching processing area and invalid area. Figure 9 is a diagram showing the matching in the second matching process. Diagram 1 showing that the matching reference point where the degree is maximum is detected.
Figure 0 is a diagram showing that the process is interrupted and terminated when a predetermined number of recognition points are obtained, Figure 11 is a diagram showing that recognition points are detected through two-step matching, and Figure 12 The figure shows that recognition points are detected through three stages of matching. 5... Image pattern storage means, 7...
Central processing means, 10...Standard pattern storage means, 15...Logic operation means, 17...-
Growth calculation means, 20...Maximum growth storage means,
22... Invalid area determination means, 32...
Standard pattern side matching reference point, 34... Image pattern side matching reference point, 41... Point to be recognized, 42...
. . .A region where a sufficiently high degree of matching is obtained as a recognition point, 43 . . . Misrecognition point, 63 . . . Standard pattern partial region, 74 . . . Invalid region. Name of agent: Patent attorney Toshio Nakao and 1 other person No. 1
Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 pJ57 Figure 8 Figure 9 Figure 10 Figure 11 Figure 12 Procedure amendment August 27, 1985 Patent application No. 195115 No. 2 Name pattern matching method of invention 3 Relationship with the amendment person case Patent application Address 1006 Kadoma, Kadoma City, Osaka Name Name
(582) Matsushita Electric Industrial Co., Ltd. Representative Tani
Akio I 4 Agent 571 Address 1006 Oaza Kadoma, Kadoma City, Osaka Prefecture Matsushita Electric Industrial Co., Ltd. [Contact phone number (Tokyo) 437-1121 Tokyo Legal Affairs Branch]
-,'-"'6 Subject of amendment 6, Contents of amendment (1) ``This is done by the conventional... .”. (2) Correct "align the text" on the 18th line of the 9th page to "align the text". (3) Correct "Second light" in line 9 of page 16 to "Second light". (4) Insert the following statement between lines 14 and 15 on page 10. [Therefore, in order to shorten the time required for the first matching process at a large number of first matching reference points, when the first matching process is passed, the second matching process is immediately performed to detect the recognition point.] , the process is terminated when a predetermined number of recognition points is obtained. However, as described above, if it is attempted to detect recognition points while mixing the first verification process and the second verification process, a new problem arises in that the position of the recognition point cannot be detected accurately. ” (6) In the 9th line of page 10, “by the following formula (1)” is corrected to “by the following formula (3).” (6) Correct 1...(1)" in the 10th line of the 10th page to "...(3)". (7) The following statement will be inserted between lines 17 and 18 on page 11.

Claims (1)

[Claims] (1) The image obtained from the imaging means is stored in a storage means as a digitized image pattern, and a characteristic partial area of the image pattern is stored in advance as a standard pattern in a storage means separate from the storage means. In the pattern matching process of matching the image pattern and the standard pattern, matching reference points, which are alignment points of the image pattern and the standard pattern, are placed on the image pattern at a first interval. set as a matching reference point, perform a first matching process between the image pattern and the standard pattern at the first matching reference point, and obtain a first matching degree obtained as a result of the first matching process in advance. When the value becomes larger than the given first reference value, the first
A plurality of second matching reference points are generated in the vicinity of the matching reference points at second intervals narrower than the first interval, and all of the plurality of second matching reference points are aligned with the standard pattern. A second matching process is performed, and the second matching reference point at which the matching degree is the maximum among the plurality of second matching degrees obtained as a result of the second matching is the second matching point provided at the plurality of second matching points. If the reference point does not exist in the area facing the boundary with the area where the image pattern has not been matched yet, and the reference point is larger than the second reference value given in advance. , the second match with the maximum second match is selected.
A pattern matching method characterized in that a plurality of recognition points existing on the image pattern are detected by validating a matching criterion. 2 The comparison between the image pattern and the standard pattern does not always target the entire area of the standard pattern, but if the set interval of the matching reference points is greater than 1, only a part of the area of the standard pattern is compared. Claim No. 1
Pattern matching method described in section. 3. The pattern matching method according to claim 1, wherein when a predetermined number of recognition points is detected, the matching process is interrupted at that point.