KR20230094935A - Semiconductor material inspection device and semiconductor material inspection method using the same - Google Patents

Abstract

The present invention provides a material inspection device and a semiconductor material inspection method. Disclosed is a technology for performing quality inspection through vision inspection on semiconductor materials cut in a sorter facility. The semiconductor material inspection method includes: a material image acquisition step; a pattern analysis step; a material center identification stage; and a quality inspection step.

Description

Semiconductor material inspection device and semiconductor material inspection method using the same}

The present invention relates to a semiconductor material inspection device and a semiconductor material inspection method, and more particularly, to a technique for performing quality inspection through vision inspection on semiconductor materials cut in a sorter facility.

Vision inspection of the cut material according to the prior art may be performed through the following process.

Edge components are analyzed in a predetermined direction in the edge ROI area defined in the teaching process. Then, vertices for each of the four corners are detected by detecting the vertices of the material through the intersection of the two straight lines detected at the edges of the material. Calculate the center of the material based on vertex information.

Through this process, the approximate location of the material can be estimated.

The final position of the material may be calculated by analyzing the edge component again based on the detected center of the material, detecting each vertex, and then calculating the center of the material. At this time, it is performed by reducing the edge ROI.

Since this conventional technology sets an edge ROI for a material seated in a general position during the teaching process and performs an edge inspection, when the material position is changed due to material handling and assembly deformation of the instrument , there is a problem that edge detection fails.

Figure 1 shows an example of detecting a semiconductor material through vision inspection, Figure 1 (a) shows the result of performing teaching (Teaching) for a normal material, Figure 1 (b) shows the material seating As the position moves and the edge of the material deviates from the edge ROI of the teaching process, a position (B) different from the center position (A) of the actual semiconductor material is mistakenly identified as the center position of the semiconductor material, resulting in an inspection error. An example is shown.

The present invention has been made to solve the problems of the prior art as described above, and provides a way to determine the center position of the semiconductor material even when the position of the semiconductor material is distorted or part of the semiconductor material is out of the image and is not visible. want to do

In particular, it is intended to solve the problem that an error occurs when detecting the material position due to the material seating position of the table and the straightness of the camera and the table being distorted.

The object of the present invention is not limited to the above, and other objects and advantages of the present invention not mentioned can be understood by the following description.

An embodiment of a semiconductor material inspection method according to the present invention includes a material image acquisition step of acquiring a material image of an upper surface of a semiconductor material; A pattern analysis step of analyzing a pattern for the obtained material image; A material center determination step of determining the center of a semiconductor material in the material image through pattern analysis; and a quality inspection step of measuring the position and size of the semiconductor material based on the identified center of the semiconductor material and evaluating the quality of the semiconductor material based on the measurement.

As an example, the pattern analysis step may include a differential image generation step of generating a differential image by performing edge preprocessing filtering on the obtained material image; and a feature region extraction step of extracting a plurality of feature regions corresponding to a feature point or feature region by analyzing a pattern of the differential image.

Preferably, in the feature part extraction step, a feature point corresponding to a corner position of a material may be extracted from the differential image.

Preferably, in the feature region extraction step, a feature region corresponding to a corner region of the material may be extracted from the differential image.

As an example, in the feature region extraction step, a region corresponding to a preset reference figure in the differential image may be extracted as a feature region.

Furthermore, in the determining the center of the material, the center of the semiconductor material may be determined in the material image by combining a plurality of feature regions.

As an example, the pattern analysis step analyzes the pattern of the obtained material image to extract a feature part, and the material center identification step includes a feature part of a reference image prepared in advance corresponding to the semiconductor material and the obtained material image. It is possible to determine the center of the semiconductor material in the material image by comparing the feature part of the .

In addition, one embodiment of the semiconductor material inspection apparatus according to the present invention, the image acquisition unit for acquiring a material image for the semiconductor material; a pattern analysis unit analyzing a pattern for the obtained material image; a material center determination unit determining the center of the semiconductor material in the material image based on the pattern analysis result; and a quality inspection unit performing a quality inspection on the semiconductor material based on the identified center of the semiconductor material.

As an example, the pattern analysis unit generates a differential image by performing edge preprocessing filtering on the obtained material image, extracts a plurality of feature regions through pattern analysis on the differential image, and the material center determination unit, a plurality It is possible to determine the center of the semiconductor material in the material image by combining the feature parts of .

As an example, the pattern analysis unit analyzes the pattern of the obtained material image to extract a feature region, and the material center determination unit corresponds to the semiconductor material and prepares a feature region of a reference image in advance and a characteristic of the obtained material image. It is possible to determine the center of the semiconductor material in the material image by comparing the region.

Furthermore, the quality inspection unit may perform a quality inspection on the semiconductor material by measuring the location and size of the semiconductor material based on the identified center of the semiconductor material.

According to the present invention, the position and size of the semiconductor material can be accurately grasped even when the position of the material is changed or warped in the inspection image obtained for the material cut in the sorter facility.

In particular, since the entire area of the inspection image is inspected using the image characteristics of the teaching material, there is no restriction on the seating position of the semiconductor material, and even if a part of the semiconductor material is out of the acquired image and is not visible, pattern matching is performed. It is possible to determine the center position of the semiconductor material through partial matching of .

The effects of the present invention are not limited to those mentioned above, and other effects not mentioned will be clearly understood by those skilled in the art from the following description.

1 shows an example of detecting a semiconductor material through vision inspection according to the prior art.
2 shows a configuration diagram of an embodiment of a semiconductor material inspection apparatus according to the present invention.
Figure 3 shows a flow chart of one embodiment of a semiconductor material inspection method according to the present invention.
Figure 4 shows a flow chart of one embodiment of the pattern analysis and the process of determining the center of the semiconductor material in the semiconductor material inspection method according to the present invention.
FIG. 5 shows an example of determining the center of a semiconductor material through the embodiment of FIG. 4 .
FIG. 6 shows another example of determining the center of a semiconductor material through the embodiment of FIG. 4 .
7 is a flowchart of another embodiment of a process of analyzing a pattern and determining the center of a semiconductor material in a method for inspecting a semiconductor material according to the present invention.
FIG. 8 illustrates an example of determining the center of a semiconductor material through the embodiment of FIG. 7 .

Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings, but the present invention is not limited or limited by the embodiments.

In order to explain the present invention and the operational advantages of the present invention and the objects achieved by the practice of the present invention, the following describes a preferred embodiment of the present invention and references it.

First, the terms used in this application are used only to describe specific embodiments, and are not intended to limit the present invention, and singular expressions may include plural expressions unless the context clearly dictates otherwise. In addition, in this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other It should be understood that the presence or addition of features, numbers, steps, operations, components, parts, or combinations thereof is not precluded.

In describing the present invention, if it is determined that a detailed description of a related known configuration or function may obscure the gist of the present invention, the detailed description will be omitted.

The present invention proposes a technology for inspecting the quality of semiconductor materials after detecting and cutting the position of the material seated on the table of the sorter facility, In order to solve the error of material location detection due to the prealignment method based on the image or feature, a prealign method is applied.

2 shows a configuration diagram of an embodiment of a semiconductor material inspection apparatus according to the present invention.

The semiconductor material inspection apparatus 100 according to the present invention may include an image acquisition unit 110, a pattern analysis unit 130, a material center determination unit 150, a quality inspection unit 170, and the like.

The image acquisition unit 110 may obtain a material image by photographing the semiconductor material to be inspected. To this end, the image acquisition unit 110 may include a camera for photographing the semiconductor material seated on the table from above, a driving unit for adjusting the position of the camera and the table, and obtaining an upper surface image of the semiconductor material to be inspected. can do.

The pattern analysis unit 130 may analyze the pattern through image analysis processing on the material image acquired by the image acquisition unit 110 .

As an example, the pattern analyzer 130 may generate a differential image in which only an edge portion is revealed by performing edge prefiltering on the material image. Here, various image processing techniques may be applied when the pattern analyzer 130 generates a differential image through edge preprocessing filtering.

Also, the pattern analyzer 130 may extract a plurality of feature regions through pattern analysis of the generated differential image.

For example, the pattern analyzer 130 may extract a feature point of a corner point where edge ends meet in a differential image. Alternatively, the pattern analyzer 130 may extract a region having a certain shape from the differential image as a feature region.

Preferably, the pattern analyzer 130 may extract a feature point or feature region from an outermost edge portion.

The material center determination unit 150 may determine the center of the semiconductor material in the material image based on the pattern analysis result of the material image performed by the pattern analysis unit 130 .

Preferably, the material center determination unit 150 may determine the center of the semiconductor material based on the plurality of feature points or the plurality of feature regions extracted by the pattern analyzer 130 .

As an example, the material center determination unit 150 may combine a plurality of feature points or a plurality of feature regions and determine an overlapping point on a line connecting them as the center of the semiconductor material.

As another example, the material center determination unit 150 may determine the center of the semiconductor material in the material image by holding a reference image in advance corresponding to the semiconductor material and matching the material image and the reference image for comparison. For example, the center point of the material and a plurality of feature points or a plurality of feature regions are set in the reference image, and the feature point or feature region of the material image is matched and contrasted with the feature point or feature region of the reference image. Semiconductor material in the material image can determine the central point of

The quality inspection unit 170 may perform a quality inspection of the semiconductor material based on the center of the semiconductor material in the material image determined by the material center determination unit 150 . The quality inspection unit 170 may measure the position and size of the semiconductor material based on the identified center point, and evaluate the quality of the semiconductor material by comparing the measured position and size with a reference range.

Furthermore, the present invention proposes a method for inspecting the quality of semiconductor materials using the semiconductor material inspection apparatus according to the present invention described above. Hereinafter, the semiconductor material inspection method according to the present invention will be described through examples. do.

Since the semiconductor material inspection method according to the present invention is implemented through the semiconductor material inspection apparatus according to the present invention described above, it will be described with reference to the embodiment of the semiconductor material inspection apparatus according to the present invention.

Figure 3 shows a flow chart of one embodiment of a semiconductor material inspection method according to the present invention.

When the semiconductor material to be inspected is transferred to the quality inspection table, the image acquisition unit 110 may acquire a material image by photographing the upper surface of the semiconductor material (S100).

When a material image is acquired through the image acquisition unit 110, the pattern analysis unit 130 performs image processing and pattern analysis on the acquired material image (S200) to extract a plurality of feature regions from the material image. .

When a plurality of feature regions are extracted through pattern analysis of the material image, the material center determination unit 150 may determine the center of the semiconductor material in the material image based on the pattern analysis result (S300).

In addition, the quality inspection unit 170 measures the position and size of the semiconductor material based on the center of the identified semiconductor material (S300) and compares the measured position and size with a reference range to perform quality evaluation on the semiconductor material. The quality of the semiconductor material may be inspected (S500).

Through this process, it is possible to perform quality inspection on semiconductor materials, which will be examined in more detail through more specific embodiments.

4 is a flow chart of an embodiment of a process of pattern analysis and determining the center of a semiconductor material in a method for inspecting a semiconductor material according to the present invention, and FIG. An example is shown, and FIG. 6 shows another example of determining the center of a semiconductor material through the embodiment of FIG. 4 .

When a material image of the semiconductor material to be inspected is obtained, pattern analysis is performed on the material image. For more accurate pattern analysis, the pattern analyzer 130 performs edge preprocessing filtering (S211) on the acquired material image to obtain a differential image can be generated (S213).

As an example, if a differential image is generated so that only the edge portion is revealed by edge preprocessing through image processing for the material image, the differential image for the semiconductor material as shown in FIG. 5 (a) and FIG. 6 (a) (210, 230) can be generated.

The pattern analyzer 130 may perform pattern analysis on the generated differential image (S215) and extract a plurality of feature regions corresponding to the feature point or feature region (S217).

As an example, through pattern analysis of the differential image 210 of FIG. 221b, 221c, and 221d) can be extracted as feature regions.

In order to identify the feature area, a reference shape may be set in advance to correspond to the edge characteristics of the material. For example, shapes such as ┌, ┐, └, ┘ may be set as the reference shape corresponding to each edge of the material. .

Areas corresponding to the set reference figures may be extracted as feature areas 221a, 221b, 221c, and 221d.

As another example, through pattern analysis of the differential image 230 of FIG. 6 (a), as shown in FIG. , 241c, 241d) can be extracted as feature regions.

For example, the position of the edge of the material can be extracted as a plurality of feature points 241a, 241b, 241c, and 241d by identifying a point where straight edges meet or a point where a straight edge bends near the outermost edge of the image as the edge position of the material. .

When a plurality of feature regions are extracted from the material image, the material center determination unit 150 combines the plurality of extracted feature regions (S311) and determines the center of the semiconductor material in the material image based on the combined feature regions (S313) can do.

As an example, a plurality of feature regions 221a, 221b, 221c, and 221d are extracted as shown in (b) of FIG. 5 and a plurality of feature regions 221a, 221b, and 221c are extracted as shown in (c) of FIG. , 221d), the center 223 of the semiconductor material can be identified based on the relationship between the feature regions 221a, 221b, 221c, and 221d.

As another example, as shown in (b) of FIG. 6, a plurality of feature points 241a, 241b, 241c, and 241d are extracted, and as shown in (c) of FIG. After combining 241c and 241d), the center 243 of the semiconductor material may be identified based on the relationship between the plurality of feature points 241a, 241b, 241c, and 241d.

In determining the center, an overlapping point on a line connecting the feature regions 221a, 221b, 221c, and 221d or the feature points 241a, 241b, 241c, and 241d may be estimated as the center 223 or 243 of the semiconductor material.

And, as shown in (d) of FIG. 5 and (d) of FIG. 235) can be considered.

In this way, according to an embodiment of the present invention, the center of a semiconductor material can be grasped only with a material image obtained in a situation where a separate reference point or reference image is not provided.

7 is a flowchart of another embodiment of a process of pattern analysis and determining the center of a semiconductor material in a method for inspecting a semiconductor material according to the present invention, and FIG. show an example

In the embodiment of FIG. 7 , when a material image of a semiconductor material to be inspected is obtained as in the embodiment of FIG. 4 described above, the pattern analysis unit 130 performs pattern analysis on the material image (S221) and analyzes the pattern. Based on the result, a feature part may be extracted (S223).

As an example, a plurality of feature points or feature regions may be extracted from the material image 250 as shown in (a) of FIG. 8 through pattern analysis.

In addition, the material center determination unit 150 matches (S321) the characteristic part of the reference image prepared in advance corresponding to the semiconductor material and the characteristic part of the obtained material image, and compares it to determine the center of the semiconductor material in the material image (S323) can do.

As an example, feature regions 261a, 261b, 261c, and 261d are set in the reference image 260 in (b) of FIG. 8, and a center point 265 of the material is set.

Characteristic regions 251a, 251b, 251c, and 251d of the material image 250 and feature regions 261a, 261b, 261c, and 261d of the reference image 260 are matched and contrasted to determine the semiconductor material in the material image 250. The center point 265 of the reference image 260 may be regarded as the center point 255 of the semiconductor material in the material image 250 as shown in (c) of FIG. 8 .

In this way, according to an embodiment of the present invention, it is possible to more accurately determine the center point of the semiconductor material in the material image by matching the material image to the reference image.

According to the present invention described above, even when a material position is changed or a warp occurs in an inspection image obtained for a material cut in a sorter facility, the position and size of the semiconductor material can be accurately grasped.

In particular, since the entire area of the inspection image is inspected using the image characteristics of the teaching material, there is no restriction on the seating position of the semiconductor material, and even if a part of the semiconductor material is out of the acquired image and is not visible, pattern matching is performed. It is possible to determine the center position of the semiconductor material through partial matching of .

The above description is merely an example of the technical idea of the present invention, and various modifications and variations can be made to those skilled in the art without departing from the essential characteristics of the present invention. Therefore, the embodiments described in the present invention are not intended to limit the technical spirit of the present invention, but to explain, and the technical spirit of the present invention is not limited by these embodiments. The protection scope of the present invention should be construed by the following claims, and all technical ideas within the equivalent range should be construed as being included in the scope of the present invention.

100: semiconductor material inspection device,
110: image acquisition unit,
130: pattern analysis unit,
150: material-centered judgment unit,
170: quality inspection department.

Claims (11)

A material image acquisition step of obtaining a material image of the upper surface of the semiconductor material;
A pattern analysis step of analyzing a pattern for the obtained material image;
A material center determination step of determining the center of a semiconductor material in the material image through pattern analysis; and
A semiconductor material inspection method comprising a quality inspection step of measuring the position and size of the semiconductor material based on the identified center of the semiconductor material and evaluating the quality of the semiconductor material based on this. According to claim 1,
The pattern analysis step,
A differential image generation step of generating a differential image by performing edge preprocessing filtering on the obtained material image; and
and a feature part extraction step of extracting a plurality of feature parts corresponding to a feature point or feature region by analyzing a pattern of the differential image. According to claim 2,
In the feature part extraction step,
A semiconductor material inspection method, characterized in that for extracting a feature point corresponding to a corner position of the material from the differential image. According to claim 2,
In the feature part extraction step,
A semiconductor material inspection method, characterized in that for extracting a feature region corresponding to a corner region of the material from the differential image. According to claim 4,
In the feature part extraction step,
A semiconductor material inspection method characterized in that for extracting a region corresponding to a previously set reference figure from the differential image as a feature region. According to claim 2,
In the step of determining the center of the material,
A semiconductor material inspection method, characterized in that by combining a plurality of feature parts to determine the center of the semiconductor material in the material image. According to claim 1,
The pattern analysis step,
Analyzing the pattern of the obtained material image to extract feature parts,
In the step of determining the center of the material,
A semiconductor material inspection method characterized by identifying the center of a semiconductor material in the material image by comparing a feature part of a reference image prepared in advance corresponding to the semiconductor material and a feature part of the obtained material image. An image acquisition unit for acquiring a material image of the semiconductor material;
a pattern analysis unit analyzing a pattern for the obtained material image;
a material center determination unit determining the center of the semiconductor material in the material image based on the pattern analysis result; and
A semiconductor material inspection apparatus comprising a quality inspection unit for performing a quality inspection on the semiconductor material based on the identified center of the semiconductor material. According to claim 8,
The pattern analysis unit,
Edge preprocessing is performed on the obtained material image to generate a differential image, and a plurality of feature regions are extracted through pattern analysis on the differential image,
The material center determination unit,
A semiconductor material inspection device characterized in that for recognizing the center of a semiconductor material in a material image by combining a plurality of feature parts. According to claim 8,
The pattern analysis unit,
Analyzing the pattern of the obtained material image to extract feature parts,
The material center determination unit,
A semiconductor material inspection device, characterized in that for determining the center of the semiconductor material in the material image by comparing the characteristic part of the reference image prepared in advance corresponding to the semiconductor material and the characteristic part of the obtained material image. According to claim 8,
The quality inspection unit,
A semiconductor material inspection device characterized in that for performing quality inspection on the semiconductor material by measuring the location and size of the semiconductor material based on the identified center of the semiconductor material.

Images