CN117911400B - Wafer defect determining method and device, computer equipment and storage medium - Google Patents
Wafer defect determining method and device, computer equipment and storage medium Download PDFInfo
- Publication number
- CN117911400B CN117911400B CN202410289678.XA CN202410289678A CN117911400B CN 117911400 B CN117911400 B CN 117911400B CN 202410289678 A CN202410289678 A CN 202410289678A CN 117911400 B CN117911400 B CN 117911400B
- Authority
- CN
- China
- Prior art keywords
- region
- feature extraction
- intensity
- type
- wafer
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 230000007547 defect Effects 0.000 title claims abstract description 57
- 238000003860 storage Methods 0.000 title claims abstract description 15
- 238000000605 extraction Methods 0.000 claims abstract description 151
- 239000007771 core particle Substances 0.000 claims abstract description 83
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 42
- 238000009826 distribution Methods 0.000 claims abstract description 42
- 239000007787 solid Substances 0.000 claims description 30
- 238000004364 calculation method Methods 0.000 claims description 27
- 238000004590 computer program Methods 0.000 claims description 14
- 238000012216 screening Methods 0.000 claims description 11
- 238000004458 analytical method Methods 0.000 claims description 2
- 235000012431 wafers Nutrition 0.000 abstract description 183
- 238000005259 measurement Methods 0.000 abstract description 11
- 238000001514 detection method Methods 0.000 description 14
- 230000008569 process Effects 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 238000003384 imaging method Methods 0.000 description 9
- 238000013135 deep learning Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 6
- 238000004519 manufacturing process Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 239000004065 semiconductor Substances 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009792 diffusion process Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000004020 luminiscence type Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30148—Semiconductor; IC; Wafer
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Software Systems (AREA)
- Quality & Reliability (AREA)
- Testing Or Measuring Of Semiconductors Or The Like (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a method, a device, computer equipment and a storage medium for determining wafer defects, which are used for solving the problems that when a large number of different types of wafer defects are detected through computer vision, the time is too long, and accurate measurement results are difficult to obtain for different types of wafers. The determining method comprises the following steps: defining a characteristic region of the core particle in the wafer image; analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region; selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type; combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combined algorithm; and calculating the wafer image by utilizing a combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer.
Description
Technical Field
The present invention relates to the field of semiconductor manufacturing, and in particular, to a method and apparatus for determining wafer defects, a computer device, and a storage medium.
Background
In the semiconductor manufacturing process, defects of the wafer-level light emitting diode need to be detected to ensure the yield and performance of the wafer. Among them, the wafer level light emitting diode includes, but is not limited to, mini LED (sub millimeter light emitting diode), micro LED (Micro light emitting diode), and the like. The method for detecting the wafer of the light emitting diodes comprises the step of visually detecting the surface defects of the wafer, and the method mainly extracts the characteristics of the wafer image through the visual detection. The yield and performance of the wafer are determined by analyzing the extracted features. However, since the wafer of this type has a smaller size, and the core particles in the wafer not only emit light, but also have different forms and types, the wafer image generated by the wafer will also have larger differences in the characteristic information such as exposure, gain and imaging size of the wafer image due to different measurement modes. Therefore, the wafer image is more various and complex than the ordinary image, and the image features are finer.
In the existing computer vision technology, complex operation is usually performed on a wafer image according to a large number of different operators so as to extract the characteristics of the wafer image. However, since a large number of operators are piled up in this way, it is difficult to perform targeted parameter adjustment for different wafer images during the operation, and the speed of wafer image detection is reduced due to the large number of operations. Therefore, when a large number of different types of wafer defects are detected through computer vision, the time is too long, and accurate measurement results are difficult to obtain for the different types of wafers.
Disclosure of Invention
The embodiment of the invention provides a method, a device, computer equipment and a storage medium for determining wafer defects, which are used for solving the problems that when a large number of different types of wafer defects are detected through computer vision, the time is too long, and accurate measurement results are difficult to obtain for different types of wafers.
In a first aspect of the present invention, a method for determining a wafer defect is provided, including:
defining a characteristic region of the core particle in the wafer image;
analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
Selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
Combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm;
and calculating the wafer image by utilizing the combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer.
In one possible design, the feature region includes a rectangular feature region and a circular feature region, the feature region defining a core particle in the wafer image, comprising:
determining the outline of the core particle in the wafer image, and obtaining the core particle shape of the core particle;
If the shape of the core particle is rectangular, determining the length and width information of the rectangle to obtain a rectangular characteristic region conforming to the length and width information;
and if the shape of the core particle is circular, determining the diameter information of the circular shape, and obtaining a circular characteristic region conforming to the diameter information.
In one possible design, the gray scale distribution trend includes a gray scale distribution direction and a gray scale trend intensity, and the analyzing the gray scale distribution trend of the feature region to obtain a region type and a luminous intensity type of the feature region includes:
If the gray distribution direction of the characteristic region is concentrated from the edge to the center, the region type of the characteristic region is solid;
if the gray distribution direction of the characteristic region is dispersed from the center to the edge, the region type of the characteristic region is hollow;
and analyzing the gray scale trend intensity of the characteristic region to obtain the luminous intensity type of the characteristic region.
In one possible design, the analyzing the gray scale trend intensity of the feature area to obtain the type of the luminous intensity of the feature area includes:
If the gray scale trend intensity of the characteristic region is higher than the expected intensity, the luminous intensity type of the characteristic region is high intensity;
and if the gray scale trend intensity of the characteristic region is lower than or equal to the expected intensity, the luminous intensity type of the characteristic region is low intensity.
In one possible design, the region type includes hollow and solid, and the selecting the region feature extraction operator corresponding to the region type includes:
if the region type is hollow, acquiring an external region outside the hollow region in the characteristic region;
taking the external area as a calculation area;
if the region type is solid, acquiring a solid region in the characteristic region, and taking the solid region as the calculation region;
And screening out the feature extraction operator with the calculation region as the region feature extraction operator.
In one possible design, the selecting an intensity feature extraction operator corresponding to the luminous intensity type includes:
if the characteristic region is solid and the luminous intensity type is high intensity, the operator direction parameter is assigned to be a positive number;
If the characteristic region is solid and the luminous intensity type is low intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is high intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is low intensity, the operator direction parameter is assigned to be a positive number;
And screening out a feature extraction operator with the same direction parameter as the operator direction parameter in the feature extraction operator, and taking the feature extraction operator as the intensity feature extraction operator.
In one possible design, the selecting the contour feature extraction operator corresponding to the feature region includes:
Obtaining the core particle shape of the core particles in the characteristic region;
and screening out a feature extraction operator suitable for the core particle shape from the feature extraction operators, and taking the feature extraction operator as a contour feature extraction operator.
In a second aspect, there is provided an apparatus for determining a wafer defect, including:
the demarcating module is used for demarcating a characteristic area of the core particle in the wafer image;
The analysis module is used for analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
The selection module is used for selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
The combining module is used for combining the contour feature extraction operator, the region feature extraction operator and the intensity feature extraction operator to obtain a combined algorithm;
And the operation module is used for operating the wafer image by utilizing the combination algorithm and extracting the characteristics of the wafer image so as to determine the defects of the wafer.
In a third aspect, a computer device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the steps of the method for determining wafer defects described above when the computer program is executed.
In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program which, when executed by a processor, implements the steps of the above-described method for determining wafer defects.
The method, the device, the computer equipment and the storage medium for determining the wafer defects are used for obtaining the region type and the luminous intensity type of the characteristic region by defining the characteristic region of the core particle in the wafer image and analyzing the gray distribution trend of the characteristic region. In this step, a feature region is defined for each core particle in the wafer image, and such region features will more closely conform to the morphology of the different core particles. In this way, the method is different from the prior art in that the method directly detects the wafer image, and because the accurate feature region definition is performed for different core grains, in the subsequent step, the core grain features can be extracted more accurately according to the region feature extraction operator selected from the feature region. Then, selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type. The step is that the wafer image is different from the common image, and the luminous core particles are distributed in the wafer, so that the core particles show obvious gray scale trend characteristics, namely the gray scale of the image in the characteristic region tends to have obvious regularity and trend, so that the characteristic extraction operators more conforming to the current characteristic trend can be selected according to different characteristic trends, and the characteristics of each characteristic region can be extracted more accurately according to the characteristic extraction operators. And then combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm. Because these operators are selected one by one through the characteristic of the current wafer image, compared with the prior art, a large number of operators are piled up to carry out a large number of operations on the wafer image, in the step, partial operators are accurately selected to combine the selected operators, and finally, the combination algorithm is utilized to carry out operation on the wafer image, so that the characteristic of the wafer image is extracted, the defect of the wafer is accurately determined, and meanwhile, the efficiency of the detection process is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the description of the embodiments of the present invention will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic view of an application environment of a method for determining wafer defects according to an embodiment of the present invention;
FIG. 2 is a flow chart illustrating a method for determining wafer defects according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 4 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 5 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 6 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 7 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 8 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 9 is a schematic diagram of a method for determining wafer defects according to an embodiment of the invention;
FIG. 10 is a schematic diagram of an apparatus for determining wafer defects according to an embodiment of the present invention;
FIG. 11 is a schematic diagram of a computer device in accordance with an embodiment of the invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
In the field of industrial semiconductor manufacturing, the wafer itself is small in size, but in the wafer-level light emitting diode, there are core grains of different shapes, sizes and types, and the core grains in the wafer are light emitting core grains, and the imaged image of the core grains will have certain regularity and trend in a small range. In addition, due to the different measurement modes of the wafers, even for the same core particle and wafer, the finally generated wafer image has a certain difference. Therefore, when the wafer of the light emitting diode is visually inspected, that is, the surface defect of the wafer of the light emitting diode is determined, the wafer image has more complex detail features to be captured compared with the common industrial imaging image. Further, it is also necessary to consider the influence of luminescence of the core particle in the wafer image on the wafer image.
In the existing computer vision technology, the detection of the luminous core particles in the wafer image requires the extraction of the characteristics in the wafer image candidate area, namely the effective information in the wafer image, so as to provide a basis for the subsequent defect detection. In the industrial and manufacturing fields, there are two methods for extracting features commonly used in wafer vision inspection: first, identifying a specific feature of a wafer image; and secondly, predicting all possible features of the wafer image, and mutually matching operators corresponding to all the features to realize identification and detection of the wafer image. The first method uses the extraction method of different characteristics to detect the wafer image, but each detection method is only sensitive to one of the characteristics of the wafer image, so that the vision image with complex changes generated by different wafers cannot be accurately detected, and the wafer image generated under different measurement environments cannot be accurately identified; in the second method, a large number of operators are needed to be piled up and then operated so as to realize the identification of the wafer image, so that the whole characteristic extraction process is complex, the calculated amount is large, the requirement of high-speed detection is difficult to meet, and the detection of the wafer image obtained by measuring the wafer with complex shape change under a complex measurement environment is difficult to meet due to complex operator operation and difficult parameter adjustment.
Based on the above-mentioned problems, in order to achieve the extraction of the wafer features more accurately according to the specific features of the wafer, the embodiment of the present invention provides a method for determining the wafer defects, which can be applied in the application environment as shown in fig. 1, wherein the measurement device communicates with the server through the network. The measuring equipment acquires a wafer image of the wafer, sends the wafer image to the server, and detects the wafer image by the server to further determine the defects of the wafer. The measuring device may be, but is not limited to, various industrial cameras, industrial sensors, laser gauges, scanning gauges, etc. The server may be implemented by an industrial computer, an independent server, or a server cluster formed by a plurality of servers.
In one embodiment, as shown in fig. 2, a method for determining a wafer defect is provided, and the method is applied to the server in fig. 1, and includes the following steps:
s10: and defining a characteristic region of the core particle in the wafer image.
Each wafer image will contain a plurality of core particles, such as the wafer image shown in fig. 3, which contains a plurality of core particles as shown in fig. 4. The wafer image can be obtained by measuring the wafer through a measuring device, and the characteristic region refers to a specific region containing core particle characteristics in the wafer image. Each specific region contains one core particle, and each wafer image will contain one or more characteristic regions, and the number of the characteristic regions may be identical to or smaller than the number of core particles, which is not limited herein. The specific region may be a region of a different shape, such as a rectangular shape in the wafer image of fig. 7, and a circular shape in the wafer image of fig. 8.
It should be noted that, in the step S10, the feature areas of the core particles in the wafer image need to be determined because the shapes of the wafers with different shapes and the core particles with different shapes are complex and changeable, and the wafer image is defined by the feature areas of the core particles, so that each feature area will be accurately attached to the core particles finally, so that the recognition range of the feature areas in the subsequent step is small and accurate, and the features of the wafer image can be extracted more accurately and efficiently.
S20: and analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region.
The gray level distribution trend refers to a distribution rule and a change trend in a characteristic area of the wafer image, and includes, but is not limited to, uniformity, gradient, and the like. The gray scale distribution trend of the feature region in the wafer image includes, but is not limited to, concentration in the center portion, diffusion to the edge portion, and the like. When the gray level distribution trend is that the central part is concentrated, the area type of the characteristic area is solid, and the luminous intensity type is high intensity; when the gradation distribution trend is to spread toward the edge portion, the region type of the feature region is hollow, and the light emission intensity type is low intensity. Since the embodiment can be used for detecting the light-emitting core particles on the wafer, the step S20 is to analyze the gray distribution trend of the feature region, thereby obtaining the intensity and type of the light-emitting core particles, so that the wafer image can be extracted more accurately according to the information of the intensity and type of the light-emitting core particles in the subsequent steps.
It should be noted that, when the measurement device measures the wafer, the finally generated wafer image may have problems of exposure, gain, imaging size, etc. due to the limitation of the measurement device and the measurement environment, and in addition, the light-emitting core particle may be light-emitting or non-light-emitting. Therefore, step S20 not only determines the gray value of the imaged wafer image, but also accurately determines the light emitting condition of each core particle, so as to infer the imaging brightness of the wafer image and the light emitting intensity and type of the core particle.
S30: and selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type.
The Operator (Op for short) is a calculation unit, and these calculation units constitute a deep learning algorithm. The contour feature extraction operator refers to a calculation unit capable of calculating the contour feature of the feature region, the contour feature extraction includes but is not limited to contour edge extraction, shape feature extraction and the like, and the region feature extraction operator refers to a calculation unit capable of calculating the region type including but not limited to hollow and solid. The intensity feature extraction operator refers to a calculation unit capable of calculating the type of intensity of emitted light, including but not limited to high intensity light emission, low intensity light emission, and the like.
It is noted that different operators calculate the same feature region, different features will be extracted, for example, operators based on edge extraction are sensitive to noise of the feature region, operators based on gray value extraction are sensitive to brightness variation of the feature region, operators based on shape feature extraction are sensitive to shape variation of the feature region. Therefore, different operators are required to be selected for different detection targets of the same feature region, so that the features of the wafer image can be extracted more accurately in the subsequent steps.
S40: and combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm.
The combination algorithm is composed of different operators, and the combination algorithm forms a deep learning algorithm for identifying the wafer image.
It is worth noting that compared with the prior art that a single operator is directly adopted as a deep learning algorithm to detect the image, the combined algorithm obtained in the step can extract the characteristics of the wafer image more comprehensively and accurately. Compared with the other mode of stacking all possible operators into a deep learning algorithm to detect the image in the prior art, the method reduces the calculated amount, improves the calculation efficiency, and further improves the detection efficiency because the corresponding operators are extracted according to the possible characteristics of the wafer image before the combination algorithm, so that complicated parameter adjustment is not needed in the calculation process, and the possible difficulties in parameter adjustment are reduced.
S50: and calculating the wafer image by utilizing the combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer.
9 Since the combination algorithm is a deep learning algorithm for recognizing the wafer image, the features of the wafer image can be extracted more accurately by using the combination algorithm, and the extracted features are shown in fig. 7 or 9. Then, the defects of the wafer are determined through the identified features.
For example, the region feature extraction operator is denoted as direction, and the intensity feature extraction operator is denoted as G (i, j). An expected intensity threshold, feature minimum confidence, is set.
(One) feature extraction is performed on the wafer feature shown in fig. 3, the feature area is shown in fig. 4, the contour feature extraction operator is marked as (X, Y), and the formula is as follows because the feature area is rectangular:
;
The calculation of fig. 3 is performed using the above formula, resulting in fig. 6 (the white point in the upper left corner is the extracted feature point). Next, the combination algorithm is used to calculate the wafer characteristics shown in fig. 7.
(II) feature extraction is performed on the wafer feature shown in FIG. 8, and the contour extraction operator is denoted as (diameter), and the formula is as follows because the feature region is circular:
;
The calculation of fig. 8 using the above formula, the process is the same as above, and finally the wafer characteristics shown in fig. 9 will be obtained.
It should be noted that, in steps S10-S20, a feature region is defined for each core particle in the wafer image, and such a region feature will more conform to the morphology of the different core particle. In this way, the method is different from the prior art in that the method directly detects the wafer image, and because the accurate feature region definition is performed for different core grains, in the subsequent step, the core grain features can be extracted more accurately according to the region feature extraction operator selected from the feature region. In step S30, since the wafer image is different from the normal image, and the wafer is fully covered with the luminescent core particles, the core particles will show a characteristic with obvious gray scale trend, that is, the gray scale of the image in the characteristic region tends to have obvious regularity and trend, so that the characteristic extraction operator more conforming to the current characteristic trend can be selected according to different characteristic trends, so that the characteristic of each characteristic region can be extracted more accurately according to the characteristic extraction operators. Because these operators are selected one by the features of the current wafer image, compared with the prior art in which a large number of operators are piled up to perform a large number of operations on the wafer image, in step S40, the selected operators are combined by accurately selecting part of the operators. In the step S50, the combination algorithm is used as a deep learning algorithm for detecting the wafer image, so that the defects of the wafer are accurately determined, and meanwhile, the efficiency of the detection process is improved.
In one embodiment, in step S10, a feature area of the core particle in the wafer image is defined, where the feature area includes a rectangular feature area and a circular feature area, and specifically includes the following steps:
S11: and determining the outline of the core particle in the wafer image, and obtaining the core particle shape of the core particle.
S12: if the shape of the core particle is rectangular, determining the length and width information of the rectangle, and obtaining a rectangular characteristic area conforming to the length and width information.
S13: and if the shape of the core particle is circular, determining the diameter information of the circular shape, and obtaining a circular characteristic region conforming to the diameter information.
The embodiment identifies the outline of the core particle in the wafer image and classifies the identification result. The recognition results are classified into two types: the result of the recognition is circular, that is, as shown in fig. 8, the core particles in the wafer image are circular; another recognition result is rectangular, i.e., as shown in fig. 7, the core particles in the wafer image are rectangular.
When the identification result is a circle, the diameter information of the circle is determined, so that a circle feature area conforming to the diameter information is obtained. The diameter information may directly identify the diameter of the circle, so as to measure the diameter of the circle, or may measure the circumference of the circle, so as to calculate the diameter of the circle, which is not limited herein. Because the circular characteristic area is determined through the diameter information, the circular characteristic area can be finally determined to be more attached to the core particle, and therefore the characteristics of the wafer image extracted in the subsequent step are ensured to be more accurate.
When the identification result is rectangular, the rectangular characteristic area conforming to the length and width information is obtained by determining the length and width information of the rectangle. The length and width information refers to the length and width of the rectangle, and the length and width of the rectangle can be measured by identifying the length and width of the rectangle. Because the rectangular feature area is determined by the long and wide information, the rectangular feature area can be finally determined to be more attached to the core particles, so that the features of the wafer image extracted in the subsequent step are more accurate.
The step S11 to S13 are substantially performed to bond the size of the feature region to the core particle feature, and the bonding method may be a complete bonding of the edge of the core particle or bonding of the surface of the core particle, which is not limited herein. The final feature region is more accurate, and the accuracy and efficiency of feature extraction in the subsequent steps are further improved.
In an embodiment, in step S20, the gray scale distribution trend of the feature area is analyzed to obtain the area type and the luminous intensity type of the feature area, where the gray scale distribution trend includes a gray scale distribution direction and a gray scale trend intensity, and specifically includes the following steps:
s21: if the gray distribution direction of the characteristic region is concentrated from the edge to the center, the region type of the characteristic region is solid.
S22: if the gray distribution direction of the characteristic region is dispersed from the center to the edge, the region type of the characteristic region is hollow.
S23: and analyzing the gray scale trend intensity of the characteristic region to obtain the luminous intensity type of the characteristic region.
The core particles in the wafer image can be luminous core particles, and the characteristic areas of the luminous core particles show specific distribution rules due to the luminous characteristics of the luminous core particles, wherein the distribution rules comprise but are not limited to gray distribution directions, gray trend intensities and the like. Since the gray distribution of the feature area has a certain directionality, the embodiment determines whether the area type of the feature area is solid or hollow, that is, substantially determines the light emitting mode of the core particle by identifying the gray distribution direction in the feature area. Then, the gray scale trend intensity of the characteristic region, namely the luminous intensity of the luminous core particle is analyzed, so that the luminous intensity type of the characteristic region is obtained.
It should be noted that, in this embodiment, the region type of the feature region is further determined substantially according to the gray distribution trend after the core particle imaging. The region types are classified into hollow and solid types because the features of the core particles after imaging are concentrated in the center or dispersed at the edges, and thus the present embodiment makes a classification judgment. So that the subsequent steps can be divided according to solid and hollow, the calculation process is more accurate and reasonable, and the accuracy of wafer image identification is further improved.
In an embodiment, in step S23, the gray scale trend intensity of the feature area is analyzed to obtain the type of the luminous intensity of the feature area, which specifically includes the following steps:
s231: and if the gray scale trend intensity of the characteristic region is higher than the expected intensity, the luminous intensity type of the characteristic region is high intensity.
S232: and if the gray scale trend intensity of the characteristic region is lower than or equal to the expected intensity, the luminous intensity type of the characteristic region is low intensity.
In this embodiment, the gray scale trend intensity of the feature region is determined, so that the type of the luminous intensity of the feature region is classified into two types, i.e., high intensity and low intensity.
For example, as in the feature region shown in fig. 4, if the mean feature of the individual region gray is calculated, the expected intensity threshold=feature×0.1.
It should be noted that, in this embodiment, the types of light emission intensity are divided into two types, namely high intensity and low intensity, because the calculation modes corresponding to the high light emission intensity and the low light emission intensity are different, the division is more beneficial to more accurately extracting the features in the wafer image in the subsequent steps, thereby further improving the accuracy of wafer image identification.
In an embodiment, in step S30, a region feature extraction operator corresponding to the region type is selected, where the region type includes hollow and solid, and specifically includes the following steps:
s311: and if the region type is hollow, acquiring an outer region outside the hollow region in the characteristic region.
S312: the outer region is taken as a calculation region.
S313: and if the region type is solid, acquiring a solid region in the characteristic region, and taking the solid region as the calculation region.
S314: and screening out the feature extraction operator with the calculation region as the region feature extraction operator.
The feature extraction operator refers to a calculation unit of different feature extraction methods, and includes, but is not limited to, an operator based on edge extraction features, an operator based on gray value extraction features, and an operator based on shape extraction features. And the regional feature extraction operator refers to an operator for extracting features based on gray values.
For example, if the calculation region is solid, the original calculation region a is used by default, if the calculation region is hollow, the hollow region B is acquired first, and then the relative position and size information of a and B are obtained, wherein the calculation region of B is opposite to a.
It should be noted that, since the features of the core particle after imaging are collected in the center or scattered at the edges, the calculated regions are different when the program extracts the features, so the embodiment essentially determines different calculated regions according to the region types, that is, hollow and solid, and further obtains the corresponding operators according to the different calculated regions. The combined algorithm obtained according to the region extraction operator in the subsequent step is more accurate and reasonable, so that the accuracy and the efficiency of extracting the wafer image features are improved.
In an embodiment, in step S30, an intensity feature extraction operator corresponding to the luminous intensity type is selected, which specifically includes the following steps:
S321: and if the characteristic region is solid and the luminous intensity type is high intensity, assigning the operator direction parameter as a positive number.
S322: and if the characteristic region is solid and the luminous intensity type is low intensity, assigning the operator direction parameter as a negative number.
S323: and if the characteristic region is hollow and the luminous intensity type is high intensity, assigning the operator direction parameter as a negative number.
S324: and if the characteristic region is hollow and the luminous intensity type is low intensity, assigning the operator direction parameter as a positive number.
S325: and screening out a feature extraction operator with the same direction parameter as the operator direction parameter in the feature extraction operator, and taking the feature extraction operator as the intensity feature extraction operator.
The operator direction parameter value refers to a direction parameter in the algorithm, and the direction parameter may be 1 or-1, which is not limited herein. And the intensity feature extraction operator refers to an operator based on imaging intensity feature extraction.
For example, a gray scale distribution trend chart shown in fig. 5 is obtained according to the length and width information of the feature region of fig. 4. The gray distribution trend graph is analyzed to obtain that the gray distribution of the characteristic region is higher, so that direction=1, (if the gray distribution of the characteristic region is lower, direction= -1);
It should be noted that the present embodiment substantially handles the situation that the gray scale intensity of the whole wafer image is too high or too low, so as to exclude the environmental influence of the wafer image during imaging, which includes but is not limited to exposure, gain, and other different environmental conditions. Corresponding intensity feature extraction operators are obtained aiming at different intensities, so that a subsequent combination algorithm obtained according to the intensity feature extraction operators is more accurate and reasonable, and the accuracy and efficiency of extracting wafer image features are further improved.
In an embodiment, in step S30, a contour feature extraction operator corresponding to the feature region is selected, which specifically includes the following steps:
S331: and obtaining the core particle shape of the core particles in the characteristic region.
S332: and screening out a feature extraction operator suitable for the core particle shape from the feature extraction operators, and taking the feature extraction operator as a contour feature extraction operator.
In this embodiment, the contour feature extraction operator refers to a computing unit based on edge extraction features or a computing unit based on shape extraction features.
For example, determining the size and shape of the feature to be detected, determining specific combinators based on the size and shape, denoted (X, Y), respectively
It should be noted that, the extraction operators conforming to the shapes are screened out according to the core particle shapes of the core particles in the characteristic region, so that the image noise and the shape change in the image are ensured not to influence the subsequent calculation, the subsequent combination algorithm obtained according to the contour feature extraction operators is more accurate and reasonable, and the accuracy and the efficiency of extracting the wafer image features are further improved.
In the prior art, different feature extraction operators have different advantages and disadvantages, so the determination method provided by the embodiment essentially integrates and screens the feature extraction operators, that is, the condition of the wafer image is judged through a program, and the corresponding operators are screened according to the judged condition, so that the operators are combined into a final combination algorithm, and the combination mode can be disordered or can be orderly, and the method is not limited.
In the traditional scheme, a large number of cooperation operations are carried out on all feature extraction operators so as to obtain feature extraction results and defect detection results. In addition, the algorithm obtained in this way is sensitive to environmental conditions, scene changes and parameter changes, so that the process needs to consume a large amount of debugging parameters and strong calculation force, and therefore the extraction and detection efficiency is low. The invention can obtain a simplified and accurate combination algorithm by accurately judging and screening operators, and the combination algorithm has the advantages of high efficiency, small calculated amount and improved accuracy, so that the efficiency and accuracy of extracting the image features of the wafer are effectively improved, and the defects of the wafer are accurately and efficiently determined. In addition, the accurate operators are screened out, so that a large amount of parameter adjustment is not needed in the process, and the research and development cost is saved.
It should be understood that the sequence number of each step in the foregoing embodiment does not mean that the execution sequence of each process should be determined by the function and the internal logic, and should not limit the implementation process of the embodiment of the present invention.
In an embodiment, a wafer defect determining apparatus is provided, where the wafer defect determining apparatus corresponds to the wafer defect determining method in the above embodiment one by one. As shown in fig. 10, the wafer defect determining apparatus includes a demarcating module 10, an analyzing module 20, a selecting module 30, a combining module 40 and an operation module 50. The functional modules are described in detail as follows:
a demarcating module 10 for demarcating a characteristic area of the core particle in the wafer image;
The analyzing module 20 is configured to analyze the gray distribution trend of the feature area to obtain an area type and a luminous intensity type of the feature area;
the selecting module 30 is configured to select a contour feature extraction operator corresponding to the feature region, select a region feature extraction operator corresponding to the region type, and select an intensity feature extraction operator corresponding to the luminous intensity type;
A combining module 40, configured to combine the contour feature extraction operator, the region feature extraction operator, and the intensity feature extraction operator to obtain a combination algorithm;
And the operation module 50 is configured to perform an operation on the wafer image by using the combination algorithm, and extract features of the wafer image to determine defects of the wafer.
For specific limitations of the device for determining wafer defects, reference may be made to the above description of the method for determining wafer defects, which is not repeated here. The above-mentioned respective modules in the wafer defect determining apparatus may be implemented in whole or in part by software, hardware, and a combination thereof. The above modules may be embedded in hardware or may be independent of a processor in the computer device, or may be stored in software in a memory in the computer device, so that the processor may call and execute operations corresponding to the above modules.
In one embodiment, a computer device is provided, which may be a server, and the internal structure of which may be as shown in fig. 11. The computer device includes a processor, a memory, a network interface, and a database connected by a system bus. Wherein the processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer equipment is used for all data generated in the implementation process of the wafer defect determination method. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method of determining wafer defects.
In one embodiment, a computer device is provided comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the steps of when executing the computer program:
defining a characteristic region of the core particle in the wafer image;
analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
Selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
Combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm;
and calculating the wafer image by utilizing the combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer.
In one embodiment, a computer readable storage medium is provided having a computer program stored thereon, which when executed by a processor, performs the steps of:
defining a characteristic region of the core particle in the wafer image;
analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
Selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
Combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm;
and calculating the wafer image by utilizing the combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
It will be apparent to those skilled in the art that, for convenience and brevity of description, only the above-described division of the functional units and modules is illustrated, and in practical application, the above-described functional distribution may be performed by different functional units and modules according to needs, i.e. the internal structure of the apparatus is divided into different functional units or modules to perform all or part of the above-described functions.
The above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention.
Claims (9)
1. A method for determining a wafer defect, comprising:
defining a characteristic region of the core particle in the wafer image;
analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
Selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type, and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
Combining the contour feature extraction operator, the regional feature extraction operator and the intensity feature extraction operator to obtain a combination algorithm;
calculating the wafer image by utilizing the combination algorithm, and extracting the characteristics of the wafer image to determine the defects of the wafer;
wherein the selecting the intensity feature extraction operator corresponding to the luminous intensity type includes:
if the characteristic region is solid and the luminous intensity type is high intensity, the operator direction parameter is assigned to be a positive number;
If the characteristic region is solid and the luminous intensity type is low intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is high intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is low intensity, the operator direction parameter is assigned to be a positive number;
And screening out a feature extraction operator with the same direction parameter as the operator direction parameter in the feature extraction operator, and taking the feature extraction operator as the intensity feature extraction operator.
2. The method of determining as claimed in claim 1, wherein the feature region includes a rectangular feature region and a circular feature region, and the defining the feature region of the core particle in the wafer image includes:
determining the outline of the core particle in the wafer image, and obtaining the core particle shape of the core particle;
If the shape of the core particle is rectangular, determining the length and width information of the rectangle to obtain a rectangular characteristic region conforming to the length and width information;
and if the shape of the core particle is circular, determining the diameter information of the circular shape, and obtaining a circular characteristic region conforming to the diameter information.
3. The method of determining as claimed in claim 1, wherein the gray scale distribution trend includes a gray scale distribution direction and a gray scale trend intensity, and the analyzing the gray scale distribution trend of the feature region to obtain the region type and the luminous intensity type of the feature region includes:
If the gray distribution direction of the characteristic region is concentrated from the edge to the center, the region type of the characteristic region is solid;
if the gray distribution direction of the characteristic region is dispersed from the center to the edge, the region type of the characteristic region is hollow;
and analyzing the gray scale trend intensity of the characteristic region to obtain the luminous intensity type of the characteristic region.
4. The method of determining as claimed in claim 3, wherein said analyzing the gray scale trend intensity of the feature area to obtain the type of the luminous intensity of the feature area includes:
If the gray scale trend intensity of the characteristic region is higher than the expected intensity, the luminous intensity type of the characteristic region is high intensity;
and if the gray scale trend intensity of the characteristic region is lower than or equal to the expected intensity, the luminous intensity type of the characteristic region is low intensity.
5. The method for determining as claimed in claim 1, wherein the region types include hollow and solid, and the selecting the region feature extraction operator corresponding to the region type includes:
if the region type is hollow, acquiring an external region outside the hollow region in the characteristic region;
taking the external area as a calculation area;
if the region type is solid, acquiring a solid region in the characteristic region, and taking the solid region as the calculation region;
and screening out a feature extraction operator corresponding to the calculation region to serve as the region feature extraction operator.
6. The method for determining as recited in claim 1, wherein said selecting a contour feature extraction operator corresponding to said feature region comprises:
Obtaining the core particle shape of the core particles in the characteristic region;
and screening out a feature extraction operator suitable for the core particle shape from the feature extraction operators, and taking the feature extraction operator as a contour feature extraction operator.
7. A wafer defect determining apparatus, comprising:
the demarcating module is used for demarcating a characteristic area of the core particle in the wafer image;
The analysis module is used for analyzing the gray distribution trend of the characteristic region to obtain the region type and the luminous intensity type of the characteristic region;
The selection module is used for selecting a contour feature extraction operator corresponding to the feature region, selecting a region feature extraction operator corresponding to the region type and selecting an intensity feature extraction operator corresponding to the luminous intensity type;
The combining module is used for combining the contour feature extraction operator, the region feature extraction operator and the intensity feature extraction operator to obtain a combined algorithm;
The operation module is used for operating the wafer image by utilizing the combination algorithm, extracting the characteristics of the wafer image and determining the defects of the wafer;
wherein the selecting the intensity feature extraction operator corresponding to the luminous intensity type includes:
if the characteristic region is solid and the luminous intensity type is high intensity, the operator direction parameter is assigned to be a positive number;
If the characteristic region is solid and the luminous intensity type is low intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is high intensity, the operator direction parameter is assigned to be negative;
if the characteristic region is hollow and the luminous intensity type is low intensity, the operator direction parameter is assigned to be a positive number;
And screening out a feature extraction operator with the same direction parameter as the operator direction parameter in the feature extraction operator, and taking the feature extraction operator as the intensity feature extraction operator.
8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method for determining wafer defects according to any of claims 1 to 6 when the computer program is executed.
9. A computer readable storage medium storing a computer program, characterized in that the computer program when executed by a processor implements the steps of the method of determining a wafer defect according to any one of claims 1 to 6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410289678.XA CN117911400B (en) | 2024-03-14 | 2024-03-14 | Wafer defect determining method and device, computer equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202410289678.XA CN117911400B (en) | 2024-03-14 | 2024-03-14 | Wafer defect determining method and device, computer equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN117911400A CN117911400A (en) | 2024-04-19 |
CN117911400B true CN117911400B (en) | 2024-06-14 |
Family
ID=90692361
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202410289678.XA Active CN117911400B (en) | 2024-03-14 | 2024-03-14 | Wafer defect determining method and device, computer equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN117911400B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118247285A (en) * | 2024-05-30 | 2024-06-25 | 无锡星微科技有限公司杭州分公司 | Wafer defect identification method and system based on image processing |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113096119A (en) * | 2021-04-30 | 2021-07-09 | 上海众壹云计算科技有限公司 | Method and device for classifying wafer defects, electronic equipment and storage medium |
CN114067136A (en) * | 2021-10-13 | 2022-02-18 | 北京旷视科技有限公司 | Image matching method and device, electronic equipment, storage medium and related product |
Family Cites Families (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6456899B1 (en) * | 1999-12-07 | 2002-09-24 | Ut-Battelle, Llc | Context-based automated defect classification system using multiple morphological masks |
WO2009155502A2 (en) * | 2008-06-19 | 2009-12-23 | Kla-Tencor Corporation | Computer-implemented methods, computer-readable media, and systems for determining one or more characteristics of a wafer |
CN101515286B (en) * | 2009-04-03 | 2012-04-11 | 东南大学 | Image matching method based on image feature multi-level filtration |
CN110767564A (en) * | 2019-10-28 | 2020-02-07 | 苏师大半导体材料与设备研究院(邳州)有限公司 | Wafer detection method |
CN117611590B (en) * | 2024-01-24 | 2024-04-09 | 深存科技(无锡)有限公司 | Defect contour composite detection method, device, equipment and storage medium |
-
2024
- 2024-03-14 CN CN202410289678.XA patent/CN117911400B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113096119A (en) * | 2021-04-30 | 2021-07-09 | 上海众壹云计算科技有限公司 | Method and device for classifying wafer defects, electronic equipment and storage medium |
CN114067136A (en) * | 2021-10-13 | 2022-02-18 | 北京旷视科技有限公司 | Image matching method and device, electronic equipment, storage medium and related product |
Also Published As
Publication number | Publication date |
---|---|
CN117911400A (en) | 2024-04-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN117911400B (en) | Wafer defect determining method and device, computer equipment and storage medium | |
US10127651B2 (en) | Defect sensitivity of semiconductor wafer inspectors using design data with wafer image data | |
KR102137184B1 (en) | Integration of automatic and manual defect classification | |
US10192107B2 (en) | Object detection method and object detection apparatus | |
KR102110755B1 (en) | Optimization of unknown defect rejection for automatic defect classification | |
WO2021000524A1 (en) | Hole protection cap detection method and apparatus, computer device and storage medium | |
EP1736758A2 (en) | Board inspecting apparatus, its parameter setting method and parameter setting apparatus | |
TWI808266B (en) | System, method, and computer-readable medium for setting up inspection of a specimen with design and noise based care areas | |
US8731278B2 (en) | System and method for sectioning a microscopy image for parallel processing | |
JP5168215B2 (en) | Appearance inspection device | |
JP2012501011A (en) | Image analysis method and system | |
EP2212909B1 (en) | Patterned wafer defect inspection system and method | |
KR20120014886A (en) | Inspection recipe generation and inspection based on an inspection recipe | |
KR20180090756A (en) | System and method for scoring color candidate poses against a color image in a vision system | |
CN113820333B (en) | Battery pole piece abnormality detection method, device, upper computer and detection system | |
CN114764770A (en) | Wafer detection method, device, equipment and storage medium | |
JP2004109018A (en) | Circuit pattern inspecting method and inspecting device | |
JP4038210B2 (en) | Particle extraction for automatic flow microscopy | |
KR20220104776A (en) | Clustering of Subcare Areas Based on Noise Characteristics | |
US10957035B2 (en) | Defect classification by fitting optical signals to a point-spread function | |
US20140079311A1 (en) | System, method and computer program product for classification | |
US10241000B2 (en) | Method for checking the position of characteristic points in light distributions | |
US11928808B2 (en) | Wafer detection method, device, apparatus, and storage medium | |
CN112582292B (en) | Automatic detection method for abnormality of parts of chip production machine, storage medium and terminal | |
CN117686190B (en) | Method, device, equipment and storage medium for detecting light-emitting chips in wafer |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |