WO1998012668A1

WO1998012668A1 - Test method and test apparatus using pattern matching

Info

Publication number: WO1998012668A1
Application number: PCT/JP1997/003283
Authority: WO
Inventors: Yasuyoshi Suzuki; Takehiro Sugimoto; Yoshihiko Nakakoji; Toru Inomoto
Original assignee: Komatsu Ltd.
Priority date: 1996-09-17
Filing date: 1997-09-17
Publication date: 1998-03-26
Also published as: KR19980024633A; TW344062B; JPH1091785A

Abstract

When the peripheral part of a glossy portion whose position and size are changed at random is masked, the masked part is judged accurately and easily, missearching caused by decrease of the score at the time of pattern matching is prevented, and the positioning detection accuracy at the time of pattern matching is improved. A plurality of objects to be tested are imaged. Then, one object among the imaged objects is selected as a reference pattern. Then the image of the reference pattern is compared with the image of the other objects and the variation in lightness data are calculated for each of the pixels corresponding to the same positions of the images of the other objects. Then the pixels at positions where the variation is lightness data exceeds a predetermined threshold value are obtained and a mask pattern consisting of the obtained pixels is set. After the pixels of which the mask pattern consists are removed, the image of the reference pattern is compared with the image of another object and the pattern matching is performed.

Description

Description Inspection method and inspection apparatus by pattern matching

The present invention relates to a method and an apparatus for checking whether or not a gap (gap) between metal terminals (pins) of a connector is appropriate by pattern matching. Background art

When inspecting whether or not the gap (gap) between these metal terminals is appropriate on a large number of images of the same shape, such as the metal terminals (pins) of the connector, pattern matching on the image Inspection is generally performed using the above method. In this case, it is necessary to determine a reference pattern in pattern matching. The determination of the reference pattern was performed as follows.

In other words, as shown in the top view of Fig. 5 (a), the operator selects a pair of metal terminals 2R, which are considered to be the most standard, from among a large number of metal terminals in the image of the upper surface of the connector body 1. Select 2 L by surrounding it with a rectangle and register it as reference patterns 6 R and 6 L (see Fig. 5 (c)). Then, pattern matching for matching the reference patterns 6 R and 6 L to another metal terminal 2 is executed on the XY plane. That is, the reference patterns 6R and 6L are moved on the XY plane, and the similarity (degree of coincidence) between the reference patterns 6R and 6L and the pair of metal terminals to be inspected is calculated as a score. It is determined that the pair of metal terminals 2R and 2L to be inspected exists at the peak location. In this manner, the position of the pair of metal terminals 2R and 2L to be inspected is detected, and the gap d between the pair of metal terminals 2R and 2L (see FIG. 5 (b)) is measured. Inspections are made to see if they are appropriate.

However, the pair of metal terminals 2R and 2L are imaged under epi-illumination as shown in FIG. 6 (a). For this reason, the end surface 2a of the metal terminal 2 shines. On the imaging screen, as shown in Fig. 6 (b), it is observed as a glossy part 2d with higher brightness than the surrounding area. The distal end surface 2a of the metal terminal 2 is usually a cut surface, so that its shape is physically unstable. For this reason, as shown in FIG. 7, the position and size of the glossy portion 2d change randomly on the image. Such a random change in the position and area of the glossy portion 2d causes the following inconveniences.

Due to the random change in the position and area of the glossy portion 2d, even if the metal terminal 2 to be inspected is a good product, the score of the similarity at the time of pattern matching is reduced. For this reason, in order to prevent false reports that the actual position of the metal terminal is erroneously detected, the score threshold for determining whether or not the shapes match should be set lower. However, in the case of connectors, there are often complicated patterns in the background, and if the score threshold value is set too low, there is a danger that the background pattern will be erroneously searched.

In the pattern matching, as described above, a position where the reference pattern most matches the shape of the inspection target to be detected is searched based on the peak of the score. However, since the shape of the glossy portion 2d of the metal terminal 2 to be inspected changes randomly, if the shape of the metal terminal 2 changes randomly, the positioning accuracy deteriorates.

In order to avoid this, as shown in Fig. 10, pixels 2e around the glossy part 2d where the size and position change randomly, that is, the pixels in the part where the brightness change is large, It is conceivable to perform pattern matching after masking and excluding this.

However, in practice, it is difficult for human eyes to accurately judge the portion 2e of a pixel whose brightness changes randomly. Also, the work of masking countless pixels one by one is extremely complicated. Disclosure of the invention

The present invention has been made in view of such circumstances, and when masking a portion around a glossy portion whose position and size change randomly, it is possible to accurately and easily determine the mask portion. In addition, it is possible to prevent erroneous searches from being caused by a decrease in the score in pattern matching, The purpose of the present invention is to enhance the accuracy of positioning detection at the time.

Therefore, in the main invention of the present invention, the inspection object is compared with the reference pattern of the inspection object, the degree of matching is calculated, and the shape of the inspection object is determined based on the calculated value of the degree of matching. In the inspection method by pattern matching that inspects

An imaging step of imaging each of the plurality of inspection objects,

A reference pattern setting step of setting one inspection object of the plurality of imaged inspection objects as a reference pattern;

A process of comparing the captured image of the reference pattern with the captured image of another inspection object to calculate a variation in brightness data for each pixel corresponding to the same part of the object; A mask pattern setting step of determining a pixel at a portion where the variation value is equal to or greater than a predetermined threshold and a value, and setting a mask pattern including the determined pixel;

Excluding the pixels constituting the mask pattern, and performing pattern matching by matching a captured image of the reference pattern with a captured image of another inspection object.

It has.

According to the present invention, a plurality of inspection objects are respectively imaged. Next, one of the plurality of imaged inspection objects is set as a reference pattern.

Next, the captured image of the reference pattern and the captured image of another inspection object are matched, and the variation of the brightness data is calculated for each pixel corresponding to the same part of the object. Next, pixels of a portion where the calculated value of the variation in the brightness data is equal to or greater than a predetermined threshold value are obtained, and a mask pattern including the obtained pixels is set. As described above, the peripheral portion of the glossy portion where the position and the size change randomly is accurately and easily determined as a pixel of a portion where the value of the variation of the brightness data exceeds a predetermined threshold value, and the portion is masked. Is done.

Then, after the pixels constituting the mask pattern are excluded, the captured image of the reference pattern and the captured image of another inspection object are matched, and pattern matching is executed. As a result, the score for pattern matching decreases. An erroneous search is prevented from occurring, and the accuracy of positioning detection in pattern matching is improved. BRIEF DESCRIPTION OF THE FIGURES

FIG. 1 is a flowchart showing a processing procedure in an embodiment of an inspection method or an inspection apparatus by pattern matching according to the present invention.

FIG. 2 is a flowchart showing another processing procedure in the embodiment of the inspection method or the inspection apparatus by pattern matching according to the present invention.

FIG. 3 is a perspective view showing a plurality of metal terminals housed in the connector main body. FIG. 4 is a side view showing the device configuration of the embodiment.

FIGS. 5A, 5B, and 5C are a top view, a side view, and an enlarged view of the top face of the metal terminal, respectively.

FIGS. 6 (a) and 6 (b) are a side view and a top view when illumination light is applied to the distal end surface of the metal terminal.

FIG. 7 is a diagram illustrating how the position and size of the glossy portion on the tip surface of the metal terminal change.

FIG. 8 is a diagram used to explain the processing contents of FIG.

FIG. 9 is a diagram used to explain the processing contents of FIG.

FIG. 10 is a diagram used to explain the processing contents of FIG.

FIG. 11 is a diagram used to explain the processing contents of FIG.

FIG. 12 is a diagram used to explain the processing contents of FIG.

FIG. 13 is a diagram used to explain the processing contents of FIG.

FIG. 14 is a diagram used to explain the processing contents of FIG.

FIG. 15 is a diagram used to explain the processing contents of FIG. BEST MODE FOR CARRYING OUT THE INVENTION

Hereinafter, an embodiment of an inspection method and an inspection apparatus by pattern matching according to the present invention will be described with reference to the drawings.

FIG. 3 is a perspective view showing the inspection target of this embodiment, A plurality of metal terminals (pins) 2, 2 ... housed are shown. In the present embodiment, the position of the pair of metal terminals 2R and 2L in the connector body 1 is detected by performing pattern matching, as shown in FIGS. 5 (a) and 5 (b). However, it is assumed that the gap d between the gold terminals 2R and 2L is measured to check whether the gap d is appropriate.

FIG. 4 is a side view showing the configuration of the inspection apparatus of the present embodiment. On an inspection table 5, a connector body 1 containing a plurality of metal terminals 2 to be inspected is placed. Above the metal terminal 2, a ring light source 4, which is an illumination for imaging that irradiates light toward the tip end surface 2 a of the metal terminal 2, is provided. Above the ring light source 4, a camera 3 that captures images of the tip surfaces 2a of the plurality of metal terminals 2 in the connector body 1 is provided. FIG. 1 is a flowchart illustrating an inspection process according to the present embodiment. Hereinafter, description will be made with reference to this flowchart.

First, as shown in Fig. 8, the operator is the most standard among the plurality of metal terminals 21, 22, 23, 24, 25, 26 ... in the image of the top surface of the connector body 1 (see Fig. 5 (a)). It is selected by surrounding the metal terminal 24 which seems to be a rectangle. Here, the tip surface 2a of each metal terminal is imaged under epi-illumination of the ring light source 4 (see FIG. 6 (a)). For this reason, the end surface 2a of the metal terminal 2 shines. On the imaging screen, that part is observed as a glossy part 2d with higher brightness than the surrounding area (see Fig. 6 (b)). _C And the tip 2a of the metal terminal 2 is usually a cut surface. Because of this, the shape is physically unstable. For this reason, as shown in FIG. 8, the position and the size of the glossy portion 2d vary from one metal terminal to another. As an operator, a rectangular area is set for the metal terminal 24 that is considered to have the most standard position and size of the glossy portion 2d from among the metal terminals having such variations. Then, the selected rectangular area is registered as a model 6 which is a reference pattern (step 101).

Next, as shown in Fig. 9, pattern matching is performed on the XY plane to match the model 6 to the metal terminals 21, 22, 23, ... (including the own metal terminal 24) (step 1 02).

In this way, the shape of Model 6 and the shape of each metal terminal are matched, and at that time, the image corresponding to the same location (the same part of the metal terminal) of Model 6 and each metal terminal 21, 22 ... The variation of the brightness data is calculated for each element. Then, a pixel 2e of a portion where the calculated value of the variation of the brightness data is equal to or more than a predetermined threshold value is obtained, and the pixel 2e is masked (see FIG. 10). As described above, the portion 2e around the glossy portion 2 where the position and size randomly change depending on the lighting condition is the portion 2e where the value of the variation in the brightness data is equal to or greater than the predetermined threshold It is accurately and easily determined as a pixel, and that part is masked. Here, the “value of the variation in the brightness data” can be obtained as a difference in brightness or as a variance value of brightness. Then, the mask pattern 8 composed of the obtained pixel 2e is set as shown in FIG.

Among the pixels 7 of the mask pattern 8 shown in FIG. 11, the pixel 2 e of the black portion is masked and excluded during pattern matching (step 103).

However, even with the mask pattern created in this way, important positional information, that is, the gap d, is included in the masked portion (the black portion) as shown in the 8 'mask pattern in Fig. 12. Position information, such as the origin P and the outer edge 2f, which are necessary to determine the position (see the origin PR and PL in Fig. 5 (c)).

Therefore, as shown in FIG. 14, a mask release pattern 9 for releasing the mask of the region 2 ′ f corresponding to the origin P and the edge portion 2f is created as shown in FIG. Alternatively, a mask release pattern 10 for releasing the mask of the area 2 h around the origin P may be created as shown in FIG.

Among the pixels 7 of the mask release patterns 9 and 10 in FIGS. 14 to 15, the pixels 2 ′ f and 2 h in the black-painted area are excluded from the mask pattern (step 1). 0 4).

When the pixel 2 ′ f in the area corresponding to 2 f is released from the mask pattern 8 ′ in FIG. 12 using the mask release pattern 9 created in this manner, finally, as shown in FIG. A mask pattern 8 in which only the randomly changing portion 2 e around d is a mask area is generated, and it is avoided that important positional information (around the origin P) is masked. Also, when the pixel 2h in the corresponding area is released from the mask pattern 8 'in FIG. 12 using the mask release pattern 10, the final area around the glossy portion 2d is finally obtained as shown in FIG. A mask pattern 8 is generated in which the randomly changing portion 2 e and the edge portion 2 g excluding the edge portion around the origin P are generated as a mask area, and important positional information (around the origin P) is masked. It is avoided (step 105). Then, after excluding the pixel 2 e (or 2 e and 2 g) of the mask area constituting the finally obtained mask pattern 8, the model 6 and each metal terminal are included in the captured image.

2 1, 22, ... Pattern matching is performed. As a result, an erroneous search is prevented from being caused by a decrease in the score at the time of pattern matching, and the position detection accuracy at the time of pattern matching is improved.

In the process shown in FIG. 2, the threshold value in step 103 can be set to an optimal value.

That is, as shown in FIG. 2, first, i indicating the number of times of repetition processing is initialized to 1, and thereafter, the same processing 1, processing 2, processing 2 as steps 101 to 105 in FIG. Process 3, Process 4 and Process 5 are sequentially executed (Steps 202 to 206) _{c In} Step 204, the threshold value of the brightness data variation value is temporarily set to a predetermined set value Thl Is set to

Then, using the mask pattern 8, the model 6 and each metal terminal 21 in the captured image

22, pattern matching is performed. That is, the similarity (degree of coincidence) between the model 6 and each of the metal terminals 21, 22,... Is calculated as a score, and the inspection target metal terminals 21, 22,. Is determined to be present (step 207). Then, it is determined whether or not the value (for example, the variance) of the peak value variation of each score for each of the metal terminals 21, 22,... Has become smaller than a predetermined set value Th2. (Step 208).

Here, if it is determined that the variation of the peak value of each score is smaller than the predetermined set value Th2, it is determined that the score distribution is stable and the pattern matching is performed accurately. Then, the value T hi provisionally set in the above step 204 is adopted as a threshold value for generating a mask pattern.

When the value of the variation of the peak value of each score is equal to or greater than the predetermined set value Th2. If it is determined that the score distribution is not stable and the pattern matching is not performed accurately, it is determined that the current number of repetitions i is less than or equal to the limit value n ( The determination in step 209 is YES), i is incremented by +1 (step 210), and the value Thl currently set in step 204 is reset so as to decrease by a predetermined amount (step 2). 1 1).

Next, a mask pattern is created using the threshold value T ′ hi thus reset (step 2 12), and a mask release pattern is created (step 2 13). Using the mask pattern, (After the mask release area is excluded by the mask release pattern), the pattern matching is executed again (step 207). Hereinafter, until the score distribution as a result of the pattern matching becomes stable (determination YES in step 208), the same processing is repeated while the threshold value Thl for creating the mask pattern is sequentially set to gradually decrease. Executed (steps 209 to 213, 207). Then, when it is determined that the value of the variation in the peak value of each score is smaller than the predetermined set value Th2 (determination YES in step 208), the score distribution is stable and the pattern matching is not accurate. Judging that this is a common practice, the currently reset value T 'hi is finally adopted as the threshold for generating the mask pattern. When the number of repetitive processes i becomes larger than the limit value n (determination NO in step 209), it is determined that an error has occurred, and the entire process is terminated.

In the above-described embodiment, the inspection target is the metal terminal of the connector. However, the present invention is not limited to this and can be applied to any inspection target such as an IC lead.

The following cases can be considered as modes for implementing the above-described embodiment.

That is, the processing contents of the above-described embodiment may be appropriately stored in a floppy disk and distributed to a user or an operator who performs an inspection by pattern matching. The storage medium to be distributed and distributed may be a storage medium other than a floppy disk, such as a hard disk, an IC card, or a CD-ROM.

As for the mode of distribution, a portable storage medium is distributed as described above. In addition to the aspects described above, a hardware using the software of the present embodiment and a development computer that develops the software of the present embodiment and accommodates the software are connected to a public line or the like. The communication system may be connected by a network so as to be freely communicable and distributed via these networks and the like.

In addition, when the software is distributed and distributed, an installer may be attached and distributed and distributed in order to install the software on hardware that uses the software (inspection equipment using pattern matching). The compressed data may be distributed and distributed. Industrial applicability

The present invention is applicable not only to electronic component inspection but also to any inspection object.

Claims

The scope of the claims

1. Inspection by pattern matching in which the inspection object is compared with the reference pattern of the inspection object, the degree of coincidence is calculated, and the shape of the inspection object is inspected according to the value of the calculated degree of coincidence. In the method,

An imaging step of imaging each of the plurality of inspection objects,

Performing a pattern matching by excluding pixels constituting the mask pattern, and comparing the captured image of the reference pattern with the captured image of another inspection object.

Inspection method by pattern matching equipped with.

2. If the pixels constituting the mask pattern set in the mask pattern setting step include the pixels of a specific portion of the object necessary for pattern matching, the pixels of the specific portion are removed. The inspection method by pattern matching according to claim 1, wherein a mask pattern composed of pixels is newly set.

3. Inspection by pattern matching in which the inspection object is matched with the reference pattern of the inspection object, the degree of coincidence is calculated, and the shape of the inspection object is inspected according to the value of the calculated degree of coincidence. In the method,

An imaging step of imaging each of the plurality of inspection objects,

A reference pattern setting step of setting one inspection object among the plurality of imaged inspection objects as a reference pattern;

The captured image of this reference pattern and the captured image of another inspection object are compared, A calculation step of calculating the variation of the brightness data for each pixel corresponding to the same part of the body, and obtaining a pixel of a part where the calculated value of the variation of the brightness data is equal to or more than a predetermined first threshold value A mask pattern setting step of setting a mask pattern composed of the obtained pixels;

After excluding the pixels constituting the mask pattern, the captured image of the reference pattern is compared with the captured image of another inspection object, and the pattern matching for calculating the degree of coincidence is performed. The process,

When the value of the variation in the degree of coincidence is equal to or greater than a predetermined second threshold, the first threshold is reset to a smaller value, and then the mask pattern setting step and the pattern matching are performed. And a step of sequentially repeating the execution step until the value of the variation in the degree of coincidence becomes smaller than the second threshold value.

Inspection method by pattern matching equipped with.

4. Inspection by pattern matching in which the inspection object is matched with the reference pattern of the inspection object, the degree of coincidence is calculated, and the shape of the inspection object is inspected according to the value of the calculated degree of coincidence. In the device,

Imaging means for imaging each of the plurality of inspection objects,

Reference pattern setting means for setting one inspection object of the plurality of imaged inspection objects as a reference pattern;

Calculating means for comparing a captured image of the reference pattern with a captured image of another inspection object to calculate a variation in brightness data for each pixel corresponding to the same part of the object; A mask pattern setting means for determining a pixel of a portion where the value is equal to or greater than a predetermined threshold and the value, and setting a mask pattern including the determined pixel;

Means for performing pattern matching by excluding the pixels constituting the mask pattern and then matching the captured image of the reference pattern with the captured image of another inspection object;

Inspection equipment with pattern matching equipped with

5. The pixels constituting the mask pattern set by the mask pattern setting means include pixels of a specific part of the object required for pattern matching. 5. The inspection apparatus by pattern matching according to claim 4, wherein, if so, the pixel of the specific portion is removed and a mask pattern including the pixel is newly set.

6. Matching between the inspection object and the reference pattern of the inspection object, calculating the degree of coincidence, and inspecting the shape of the inspection object according to the calculated value of the degree of coincidence by pattern matching. In the device,

Imaging means for imaging each of the plurality of inspection objects,

Calculating means for comparing a captured image of the reference pattern with a captured image of another inspection object to calculate a variation in brightness data for each pixel corresponding to the same part of the object; Mask pattern setting means for determining a pixel at a portion where the value is equal to or greater than a predetermined first threshold value, and setting a mask pattern including the determined pixel;

Pattern matching execution means for executing pattern matching for calculating the degree of matching by matching the captured image of the reference pattern with the captured image of another inspection object after excluding the pixels constituting the mask pattern. When,

If the value of the variation of the degree of coincidence is equal to or greater than a predetermined second threshold value, the first threshold value is reset to a smaller value, and then the mask pattern setting means and the pattern matching are performed. Means for sequentially repeating the execution means until the value of the variation in the degree of coincidence becomes smaller than the second threshold value.

Inspection equipment with pattern matching equipped with