CN114723647A - Defect classification method and device, equipment and storage medium - Google Patents
Defect classification method and device, equipment and storage medium Download PDFInfo
- Publication number
- CN114723647A CN114723647A CN202011510556.7A CN202011510556A CN114723647A CN 114723647 A CN114723647 A CN 114723647A CN 202011510556 A CN202011510556 A CN 202011510556A CN 114723647 A CN114723647 A CN 114723647A
- Authority
- CN
- China
- Prior art keywords
- defect
- pixels
- image
- difference image
- specific features
- 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.)
- Pending
Links
- 230000007547 defect Effects 0.000 title claims abstract description 258
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000000605 extraction Methods 0.000 claims description 10
- 241000940612 Medina Species 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 4
- 230000002950 deficient Effects 0.000 claims description 2
- 238000004519 manufacturing process Methods 0.000 abstract description 14
- 238000004458 analytical method Methods 0.000 abstract description 5
- 239000004065 semiconductor Substances 0.000 description 16
- 238000001514 detection method Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000013145 classification model Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
Images
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
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- Evolutionary Biology (AREA)
- Multimedia (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Computational Biology (AREA)
- Medical Informatics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Biomedical Technology (AREA)
- Quality & Reliability (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Mathematical Physics (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
Abstract
The application relates to a defect classification method and device, equipment and a storage medium, wherein the method comprises the following steps: reading a defect image to be subjected to defect classification at present, a reference image and a defect position; obtaining a difference image according to the defect image and the reference image, and extracting specific characteristics from the difference image; the specific characteristics correspond to the defect types to be subjected to defect classification at present; and inputting the extracted specific features into a trained classifier, and classifying the defects of the defect image by the classifier according to the specific features. When the defects are classified, the specific features corresponding to the defect types are extracted from the difference images, and corresponding defect classification is carried out based on the extracted specific features, so that the defect types are accurately distinguished, the defect cause analysis can be accurately carried out, the yield is improved, and the production is improved.
Description
Technical Field
The present application relates to the field of semiconductor device inspection technologies, and in particular, to a defect classification method and apparatus, a device, and a storage medium.
Background
In the semiconductor manufacturing process, the process is adjusted by performing defect tracing analysis through defect detection and classification, so that the purpose of yield is achieved. In the related art, the Defect detection on the wafer is generally divided into two steps of Defect detection and ADC (Automatic Defect Classification). In the defect detection process, the detection image is compared with the reference image to detect and position the defect, so that a defect image, a reference image and a defect position are obtained. In the ADC process, after the features are manually extracted, the defect is classified by classifiers such as svm (support Vector machine), knn (k Nearest neighbor), and the like. However, based on the conventional feature extraction, classification by using an SVM classifier often occurs in a case where bvc (bright Voltage contrast) and dvc (dark Voltage contrast) are mutually wrongly classified, thereby affecting the accuracy of the final classification result.
Disclosure of Invention
In view of this, the present application provides a defect classification method, which can effectively improve the accuracy of the classification result.
According to an aspect of the present application, there is provided a defect classification method including:
reading a defect image to be subjected to defect classification at present, a reference image and a defect position;
obtaining a difference image according to the defect image and the reference image, and extracting specific features from the difference image; the specific features correspond to the defect types to be subjected to defect classification at present;
inputting the extracted specific features into a trained classifier, and classifying the defects of the defect image by the classifier according to the specific features.
In a possible implementation manner, when obtaining a difference image according to the defect image and the reference image, the difference image is obtained by performing difference operation on the defect image and the reference image.
In one possible implementation manner, when extracting a specific feature from the difference image, the method includes:
carrying out noise evaluation on the difference image to obtain the range of a noise gray value;
and extracting the specific features from the difference image based on the range of the noise gray value and the defect area in the difference image.
In a possible implementation manner, extracting the specific feature from the difference image based on the range of the noise gray-scale value and the defect region in the difference image includes:
counting the pixel information of the defect area in the difference image based on the range of the noise gray value, and determining corresponding specific characteristics according to the pixel information of the defect area obtained by counting;
wherein the pixel information includes at least one of a pixel number of a bright pixel, a pixel number of a dark pixel, and a total pixel number of the defective region;
the specific features include: at least one of a proportion of the bright pixels to the total pixels in the defect region, a proportion of the dark pixels to the total pixels in the defect region, and a proportion between the bright pixels and the dark pixels in the defect region.
In a possible implementation manner, determining the corresponding specific feature based on the pixel information of the defect region obtained through statistics includes:
according to the formula:
calculated to obtainThe specific features described above;
wherein feature _ val1 is the proportion of the bright pixels in the defect area to the total pixels, and num _ bright is the number of the bright pixels; sum _ pixel is the total number of pixels of the defect area.
In a possible implementation manner, determining the corresponding specific feature based on the pixel information of the defect region obtained through statistics includes:
according to the formula:
calculating to obtain the specific characteristics;
wherein feature _ val2 is the proportion of the dark pixels in the defect area to the total pixels, and num _ dark is the number of the dark pixels; sum _ pixel is the total number of pixels of the defect area.
In a possible implementation manner, determining the corresponding specific feature based on the pixel information of the defect region obtained through statistics includes:
according to the formula:
calculating to obtain the specific characteristics;
wherein feature _ val3 is a ratio between the bright pixels and the dark pixels in the defect region, and num _ dark is a number of pixels lower than a second value; num _ bright is the number of pixels above the first value; sum _ pixel is the total number of pixels of the defect area.
In one possible implementation, the number of pixels of the bright pixels and the number of pixels of the dark pixels are determined based on a median value of the difference image and a noise gray value.
In one possible implementation, the number of bright pixels is according to the formula: determining medina + noise _ band/2;
the number of pixels of the dark pixels is according to the formula: determining medina-noise _ band/2;
where medina is a median of the difference image, and noise _ band is a range of the noise gray value.
According to another aspect of the present application, there is also provided a defect classification apparatus including: the system comprises a data reading module, a feature extraction module and a defect classification module;
the data reading module is configured to read a defect image to be subjected to defect classification at present, a reference image and a defect position;
the feature extraction module is configured to obtain a difference image according to the defect image and the reference image, and extract a specific feature from the difference image; the specific features correspond to the defect types to be subjected to defect classification at present;
the defect classification module is configured to input the extracted specific features into a trained classifier, and the classifier classifies the defects of the defect image according to the specific features.
According to another aspect of the present application, there is also provided a defect classification apparatus including:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to execute the executable instructions to implement any of the methods described above.
According to another aspect of the present application, there is also provided a non-transitory computer readable storage medium having stored thereon computer program instructions which, when executed by a processor, implement the method of any of the preceding.
After a defect image, a reference image and a defect position to be subjected to defect classification at present are read, a corresponding difference image is obtained according to the determined defect image and the reference image, specific features corresponding to the defect type to be classified at present are extracted from the difference image, and then the defect classification is carried out on the defect image based on the extracted specific features, so that the defect classification in the semiconductor manufacturing process is realized. When the defects are classified, the specific features corresponding to the defect types are extracted from the difference images, and corresponding defect classification is carried out based on the extracted specific features, so that the defect types are accurately distinguished, the defect cause analysis can be accurately carried out, the yield is improved, and the production is improved.
Other features and aspects of the present application will become apparent from the following detailed description of exemplary embodiments, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate exemplary embodiments, features, and aspects of the application and, together with the description, serve to explain the principles of the application.
FIG. 1 shows a flow chart of a defect classification method of an embodiment of the present application;
FIG. 2 is a block diagram illustrating the steps of a defect classification method according to an embodiment of the present application;
FIG. 3 illustrates a difference image of a DVC obtained in a defect classification method according to an embodiment of the present application;
fig. 4 shows a difference image of BVCs obtained in the defect classification method of an embodiment of the present application;
fig. 5 is a block diagram illustrating a structure of a defect classification apparatus according to an embodiment of the present application;
fig. 6 shows a block diagram of a defect classification apparatus according to an embodiment of the present application.
Detailed Description
Various exemplary embodiments, features and aspects of the present application will be described in detail below with reference to the accompanying drawings. In the drawings, like reference numbers can indicate functionally identical or similar elements. While the various aspects of the embodiments are presented in drawings, the drawings are not necessarily drawn to scale unless specifically indicated.
The word "exemplary" is used exclusively herein to mean "serving as an example, embodiment, or illustration. Any embodiment described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
Furthermore, in the following detailed description, numerous specific details are set forth in order to provide a better understanding of the present application. It will be understood by those skilled in the art that the present application may be practiced without some of these specific details. In some instances, methods, means, elements and circuits that are well known to those skilled in the art have not been described in detail so as not to obscure the present application.
Fig. 1 shows a flow chart of a defect classification method according to an embodiment of the present application. As shown in fig. 1, the method includes: step S100, a defect image, a reference image, and a defect position are read. Here, it is to be noted that the defect image, the reference image, and the defect position may be acquired by performing defect inspection on the manufactured semiconductor during the semiconductor manufacturing process. As can be understood by those skilled in the art, the defect detection method adopted in the defect detection of the semiconductor refers to comparing the detection image with the reference image to detect and locate the defect in the defect detection process, so as to determine the defect image, the reference image and the defect position of the image currently being detected. The inspection image may be an image of the semiconductor device acquired using any one of the imaging apparatuses, and the image may be a high resolution image or a low resolution image based on the SEM output. The reference image is a defect-free image corresponding to the semiconductor device. Here, it should be further noted that the detection image and the reference image may be acquired by using the same imaging device.
After the defect image, the reference image and the defect position to be currently subjected to defect classification are read, step S200 may be executed, a difference image is obtained according to the defect image and the reference image, and a specific feature is extracted from the difference image. Here, it should be noted that, in the method of the embodiment of the present application, the specific feature corresponds to a defect type to be currently subjected to defect classification. That is, in the present application, the types of defects currently classified are different, and the specific features extracted are different. By extracting different specific features aiming at different types of defect classification, the matching degree of feature data according to the defect classification is higher.
Finally, in step S300, the extracted specific features are input into a trained classifier, and the classifier classifies the defects of the defect image according to the specific features.
Therefore, according to the defect classification method provided by the embodiment of the application, after the defect image, the reference image and the defect position to be subjected to defect classification at present are read, the corresponding difference image is obtained according to the determined defect image and the reference image, the specific feature corresponding to the defect type to be classified at present is extracted from the difference image, and then the defect classification is performed on the defect image based on the extracted specific feature, so that the defect classification in the semiconductor manufacturing process is realized. When the defects are classified, the specific features corresponding to the defect types are extracted from the difference images, and corresponding defect classification is carried out based on the extracted specific features, so that the defect types are accurately distinguished, the defect cause analysis can be accurately carried out, the yield is improved, and the production is improved.
Here, it should be further noted that the types of defects to be classified are different, and the specific features to be extracted are different. For example, when the defect type to be currently classified is BVC or DVC, the specific feature extracted at this time may be at least one of a proportion of bright pixels at the defect area to total pixels of the defect area, a proportion of dark pixels at the defect area to total pixels of the defect area, and a proportion between the bright pixels and the dark pixels at the defect area in the defect image. Corresponding to other defect types, other characteristics can be selected as specific characteristics in a targeted manner. And will not be illustrated one by one here.
That is, referring to fig. 2, after the defect classification data is collectively read out from the defect classification data (including data information such as a defect image, a defect position, and a reference image) in step S100, a difference is made between the defect image and the reference image based on the read-out defect data in step S210 to obtain a corresponding difference image, and a corresponding specific feature is extracted from the difference image. In this case, the defect data in the defect classification data set generally includes a plurality of different defect types when performing defect classification, and thus the extracted specific features also have a plurality of types, and correspond to only one defect type. Therefore, at this time, it is necessary to select corresponding specific features from the extracted features according to different defect types through step S220, and then execute step S300 to input the selected specific features into the corresponding trained classifier, so that the classifier performs corresponding defect classification.
It should be noted that, in step S230, when selecting corresponding specific features for different defect types, the defect types and the specific feature mapping data may be sorted based on statistics in advance, or may be implemented in other manners, which is not specifically limited herein. Meanwhile, it should be further noted that, when determining the corresponding specific features for different defect types, the determination may be performed according to actual experience, or may be performed in other manners, and the determination is not specifically limited herein.
In addition, in the defect classification method according to the embodiment of the application, after the specific features are extracted, the extracted specific features are input into a trained classifier, and when the classifier classifies the defects of the defect image according to the specific features, the adopted classifier can be a linear SVM classifier. Automatic defect classification can be achieved using a linear SVM classifier. However, when defect classification is performed by using a linear SVM classifier, the linear SVM classifier needs to be trained first.
Referring to fig. 2, the training of the linear SVM classifier can be mainly implemented in the following manner. Specifically, firstly, existing defect samples are marked, and features are extracted. Here, it can be understood by those skilled in the art that the manner of marking the existing defect sample can be implemented by the conventional technical means in the art, and is not limited specifically here. Then, counting each characteristic value of the defect sample, and selecting the characteristic corresponding to the defect type to be classified from the extracted characteristics according to the statistical information. And then inputting the features selected by the marked samples into a linear SVM classifier for training to obtain a classification model.
After the training of the linear SVM classifier is completed in the above manner, corresponding feature extraction can be performed on the current defect image to be classified, and after a specific feature is selected from the extracted features, the selected specific feature is input into a trained linear classifier model for classification.
In a possible implementation manner, when obtaining the difference image according to the defect image and the reference image, the difference image may be obtained by performing a difference operation on the defect image and the reference image. Referring to fig. 3 and 4, a difference image of the DVC defect image and a difference image of the BVC defect image are illustrated, respectively.
After the difference operation is carried out on the defect image and the reference image to obtain a difference image, the specific features can be extracted from the difference image. According to the above, the extracted specific features are different, and the corresponding feature extraction modes are also different.
In one possible implementation, when the defect types are BVC and DVC, the extraction of the specific feature from the difference image may be implemented according to a noise grayscale value of the difference image and a defect region in the difference image (i.e., a region of interest in the defect image of the semiconductor device that is captured and detected). That is, first, noise evaluation is performed on the difference image, and the range noise _ band of the noise gray value is obtained. Then, based on the range of the noise gray value and the defect area in the difference image, the specific feature is extracted from the difference image. Here, it should be noted that the noise evaluation of the difference image can be implemented by the conventional technical means in the field, and is not limited in detail here. Meanwhile, it should be noted that the range of the noise gray value obtained by performing noise estimation on the difference image is specifically a numerical value.
Further, when the specific feature is extracted from the difference image based on the range of the noise gray value and the defect region of the difference image, the pixel information of the defect region in the difference image may be counted based on the range of the noise gray value noise _ band, and then the corresponding specific feature may be determined according to the pixel information of the defect region obtained through the counting.
Here, it should be noted that, according to the foregoing, when the defect types are BVC and DVC, the specific feature may be at least one of a proportion of the bright pixels to the total pixels in the defect area, a proportion of the dark pixels to the total pixels in the defect area, and a proportion between the bright pixels and the dark pixels in the defect area.
Correspondingly, the pixel information may include at least one of a number of bright pixels, a number of dark pixels, and a total number of pixels of the defect region. The bright pixels refer to pixels with a certain height of pixel values in the image, and the dark pixels refer to pixels with pixel values lower than a certain value. Here, it should be noted that the statistical determination of the bright pixels and the dark pixels may use the same set pixel value as a reference, or may use different pixel values as a reference, and is not specifically limited herein.
For example, in the method of the embodiment of the present application, the number of bright pixels may be according to the formula: determining medina + noise _ band/2; the number of dark pixels may be according to the formula: the determination is made as medina-noise _ band/2. Where medina is the median of the difference image, and noise _ band is the range of noise gray values.
That is, the pixel number num _ bright of the bright pixel can be obtained by calculating the median of the defect area in the difference image and counting the number of pixels in the defect area which is higher than medina + noise _ band/2. And counting the number of pixels in the defect area which are lower than the medina-noise _ band/2 to obtain the number num _ dark of dark pixels. Meanwhile, the total pixel number sum _ pixel of the defect area can be obtained by adopting a conventional pixel calculation mode.
After the pixel information of the defect area in the difference image is obtained through statistics in any one of the above manners, the corresponding specific feature can be obtained based on the pixel information of the defect area obtained through statistics.
In particular, the specific features are: when at least one of the proportion of the bright pixels in the defect area to the total pixels, the proportion of the dark pixels in the defect area to the total pixels, and the proportion between the bright pixels and the dark pixels in the defect area is selected, the obtaining mode can be realized according to the following formula:
the feature _ val1, feature _ val2, and feature _ val3 are three different specific features determined, and respectively correspond to the proportion of the bright pixels in the defect area to the total pixels, the proportion of the dark pixels in the defect area to the total pixels, and the proportion of the bright pixels and the dark pixels in the defect area.
After the specific features for classifying the defect types are determined in the mode, the specific features are input into a trained classifier, and the classifier judges the defect types of the defect images which are currently classified according to the specific features.
Therefore, according to the defect classification method provided by the embodiment of the application, specific features specially aiming at two types of defects (namely BVC and DVC) commonly seen in the semiconductor manufacturing process are extracted, and corresponding defect classification is carried out based on the extracted specific features, so that the automatic classification of the defects in the semiconductor manufacturing process is realized, the defect classification result is effectively improved, the higher classification accuracy is ensured, the correct defect reason analysis can be carried out, the yield is improved, and the production is improved.
It should be noted that the above method can be applied to manufacturing tools, such as those used in semiconductor factories, packaging factories, printed circuit factories, solar factories, panel factories, reticle factories and light emitting diode factories. Also, these manufacturing tools may be implemented in devices having computing capabilities. Compared with the traditional method, the method can improve the manufacturing efficiency and the yield by multiple times, and reduce the learning period of the qualified rate and the manufacturing cost. Meanwhile, it should be noted that the method of the embodiment of the present application may be applied to defect detection and classification of various semiconductor devices, where the semiconductor device may be a processed and prepared wafer, or may also be a prepared integrated circuit, and the like, and the semiconductor device is not specifically limited herein.
Correspondingly, based on any one of the defect classification methods, the application also provides a defect classification device. Because the working principle of the defect classification device provided by the application is the same as or similar to the principle of the defect classification method provided by the application, repeated parts are not described again.
Referring to fig. 5, the defect classification apparatus 100 provided by the present application includes a data reading module 110, a feature extraction module 120, and a defect classification module 130. The data reading module 110 is configured to read a defect image to be currently subjected to defect classification, a reference image and a defect position. A feature extraction module 120 configured to obtain a difference image according to the defect image and the reference image, and extract a specific feature from the difference image; the specific features correspond to the defect types to be subjected to defect classification at present. And the defect classification module 130 is configured to input the extracted specific features into a trained classifier, and the classifier performs defect classification on the defect image according to the specific features.
Still further, according to another aspect of the present application, there is also provided a defect classification apparatus 200. Referring to fig. 6, the defect classification apparatus 200 according to the embodiment of the present application includes a processor 210 and a memory 220 for storing instructions executable by the processor 210. Wherein the processor 210 is configured to execute the executable instructions to implement any of the defect classification methods described above.
Here, it should be noted that the number of the processors 210 may be one or more. Meanwhile, in the defect classification apparatus 200 of the embodiment of the present application, an input device 230 and an output device 240 may be further included. The processor 210, the memory 220, the input device 230, and the output device 240 may be connected via a bus, or may be connected via other methods, which is not limited in detail herein.
The memory 220, which is a computer-readable storage medium, may be used to store software programs, computer-executable programs, and various modules, such as: the program or the module corresponding to the defect classification method in the embodiment of the application. The processor 210 executes various functional applications and data processing of the defect classification apparatus 200 by executing software programs or modules stored in the memory 220.
The input device 230 may be used to receive an input number or signal. Wherein the signal may be a key signal generated in connection with user settings and function control of the device/terminal/server. The output device 240 may include a display device such as a display screen.
According to another aspect of the present application, there is also provided a non-transitory computer readable storage medium having stored thereon computer program instructions which, when executed by the processor 210, implement the defect classification method of any of the preceding claims.
Having described embodiments of the present application, the foregoing description is intended to be exemplary, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terms used herein were chosen in order to best explain the principles of the embodiments, the practical application, or technical improvements to the techniques in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein.
Claims (12)
1. A method of classifying defects, comprising:
reading a defect image to be subjected to defect classification at present, a reference image and a defect position;
obtaining a difference image according to the defect image and the reference image, and extracting specific characteristics from the difference image; the specific features correspond to the defect types to be subjected to defect classification at present;
inputting the extracted specific features into a trained classifier, and classifying the defects of the defect image by the classifier according to the specific features.
2. The method according to claim 1, wherein the difference image is obtained by performing a difference operation on the defect image and the reference image when the difference image is obtained from the defect image and the reference image.
3. The method according to claim 1, wherein extracting a specific feature from the difference image includes:
carrying out noise evaluation on the difference image to obtain the range of a noise gray value;
and extracting the specific features from the difference image based on the range of the noise gray value and the defect area in the difference image.
4. The method of claim 3, wherein extracting the specific feature from the difference image based on the range of the noise gray values and the defect region in the difference image comprises:
counting the pixel information of the defect area in the difference image based on the range of the noise gray value, and determining corresponding specific characteristics according to the pixel information of the defect area obtained by counting;
wherein the pixel information includes at least one of a pixel number of a bright pixel, a pixel number of a dark pixel, and a total pixel number of the defective region;
the specific features include: at least one of a proportion of the bright pixels to the total pixels in the defect region, a proportion of the dark pixels to the total pixels in the defect region, and a proportion between the bright pixels and the dark pixels in the defect region.
5. The method of claim 4, wherein determining the corresponding specific feature based on the statistical pixel information of the defect region comprises:
according to the formula:
calculating to obtain the specific characteristics;
wherein feature _ val1 is the proportion of the bright pixels in the defect area to the total pixels, and num _ bright is the number of the bright pixels; sum _ pixel is the total number of pixels of the defect area.
6. The method of claim 4, wherein determining the corresponding specific feature based on the statistical pixel information of the defect region comprises:
according to the formula:
calculating to obtain the specific characteristics;
wherein feature _ val2 is the proportion of the dark pixels in the defect area to the total pixels, and num _ dark is the number of the dark pixels; sum _ pixel is the total number of pixels of the defect area.
7. The method of claim 4, wherein determining the corresponding specific feature based on the statistical pixel information of the defect region comprises:
according to the formula:
calculating to obtain the specific characteristics;
wherein feature _ val3 is a ratio between the bright pixels and the dark pixels in the defect region, and num _ dark is a number of pixels lower than a second value; num _ bright is the number of pixels above the first value; sum _ pixel is the total number of pixels of the defect area.
8. The method of claim 4, wherein the number of pixels of the bright pixels and the number of pixels of the dark pixels are determined based on a median value of the difference image and a noise gray value.
9. The method of claim 8, wherein the number of bright pixels is according to the formula: determining medina + noise _ band/2;
the number of pixels of the dark pixels is according to the formula: determining the medina-noise _ band/2;
where medina is a median of the difference image, and noise _ band is a range of the noise gray value.
10. A defect classification apparatus, comprising: the system comprises a data reading module, a feature extraction module and a defect classification module;
the data reading module is configured to read a defect image to be subjected to defect classification at present, a reference image and a defect position;
the feature extraction module is configured to obtain a difference image according to the defect image and the reference image, and extract a specific feature from the difference image; the specific features correspond to the defect types to be subjected to defect classification at present;
the defect classification module is configured to input the extracted specific features into a trained classifier, and the classifier performs defect classification on the defect image according to the specific features.
11. A defect classification apparatus, comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to carry out the method of any one of claims 1 to 9 when executing the executable instructions.
12. A non-transitory computer readable storage medium having stored thereon computer program instructions, wherein the computer program instructions, when executed by a processor, implement the method of any one of claims 1 to 9.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011510556.7A CN114723647A (en) | 2020-12-18 | 2020-12-18 | Defect classification method and device, equipment and storage medium |
| PCT/CN2021/078757 WO2022126865A1 (en) | 2020-12-18 | 2021-03-02 | Defect classification method, apparatus and device, and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011510556.7A CN114723647A (en) | 2020-12-18 | 2020-12-18 | Defect classification method and device, equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114723647A true CN114723647A (en) | 2022-07-08 |
Family
ID=82058900
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011510556.7A Pending CN114723647A (en) | 2020-12-18 | 2020-12-18 | Defect classification method and device, equipment and storage medium |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN114723647A (en) |
| WO (1) | WO2022126865A1 (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996405A (en) * | 2010-08-30 | 2011-03-30 | 中国科学院计算技术研究所 | Method and device for rapidly detecting and classifying defects of glass image |
| KR20170127269A (en) * | 2016-05-11 | 2017-11-21 | 한국과학기술원 | Method and apparatus for detecting and classifying surface defect of image |
| CN109583489A (en) * | 2018-11-22 | 2019-04-05 | 中国科学院自动化研究所 | Defect classifying identification method, device, computer equipment and storage medium |
| CN110738237A (en) * | 2019-09-16 | 2020-01-31 | 深圳新视智科技术有限公司 | Defect classification method and device, computer equipment and storage medium |
| CN111833306A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | Defect detection method and model training method for defect detection |
| CN112036514A (en) * | 2020-11-04 | 2020-12-04 | 腾讯科技（深圳）有限公司 | Image classification method, device, server and computer readable storage medium |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101661169B (en) * | 2008-08-27 | 2011-12-28 | 北京京东方光电科技有限公司 | Method and device for detecting bright spot and dark spot of liquid crystal display |
| CN103218961A (en) * | 2013-03-22 | 2013-07-24 | 苏州领视测控科技有限公司 | Method and system for liquid crystal display (LCD) defect online detection |
| CN103811369B (en) * | 2013-10-21 | 2016-09-07 | 上海华力微电子有限公司 | Copper connecting hole etching deficiency defect online detection method |
-
2020
- 2020-12-18 CN CN202011510556.7A patent/CN114723647A/en active Pending
-
2021
- 2021-03-02 WO PCT/CN2021/078757 patent/WO2022126865A1/en active Application Filing
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101996405A (en) * | 2010-08-30 | 2011-03-30 | 中国科学院计算技术研究所 | Method and device for rapidly detecting and classifying defects of glass image |
| KR20170127269A (en) * | 2016-05-11 | 2017-11-21 | 한국과학기술원 | Method and apparatus for detecting and classifying surface defect of image |
| CN109583489A (en) * | 2018-11-22 | 2019-04-05 | 中国科学院自动化研究所 | Defect classifying identification method, device, computer equipment and storage medium |
| CN110738237A (en) * | 2019-09-16 | 2020-01-31 | 深圳新视智科技术有限公司 | Defect classification method and device, computer equipment and storage medium |
| CN111833306A (en) * | 2020-06-12 | 2020-10-27 | 北京百度网讯科技有限公司 | Defect detection method and model training method for defect detection |
| CN112036514A (en) * | 2020-11-04 | 2020-12-04 | 腾讯科技（深圳）有限公司 | Image classification method, device, server and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2022126865A1 (en) | 2022-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111539908B (en) | Method and system for detecting defects of sample | |
| US7110591B2 (en) | System and method for recognizing markers on printed circuit boards | |
| CN111161246A (en) | Product defect detection method, device and system | |
| CN108108753B (en) | Identification method and device for check box selection state based on support vector machine | |
| CN110717881A (en) | Wafer defect identification method and device, storage medium and terminal equipment | |
| CN110135514B (en) | Workpiece classification method, device, equipment and medium | |
| JP2013224943A (en) | Integration of automatic and manual defect classification | |
| CN112053318A (en) | Two-dimensional PCB defect real-time automatic detection and classification device based on deep learning | |
| CN109285791B (en) | Design layout-based rapid online defect diagnosis, classification and sampling method and system | |
| CN113538392B (en) | Wafer detection method, wafer detection equipment and storage medium | |
| CN110533654A (en) | The method for detecting abnormality and device of components | |
| CN113820333B (en) | Battery pole piece abnormality detection method, device, upper computer and detection system | |
| CN113781391A (en) | Image defect detection method and related equipment | |
| CN115690670A (en) | Intelligent identification method and system for wafer defects | |
| CN112805719A (en) | Classifying defects in semiconductor samples | |
| CN115170501A (en) | Defect detection method, system, electronic device and storage medium | |
| KR20190098271A (en) | Diagnostic Methods for Defects and Classifiers Captured by Optical Tools | |
| CN115719326A (en) | PCB defect detection method and device | |
| CN112287905A (en) | Vehicle damage identification method, device, equipment and storage medium | |
| CN116363136B (en) | On-line screening method and system for automatic production of motor vehicle parts | |
| CN117007940A (en) | Self-adaptive method for detecting performance of circuit board | |
| CN116993654B (en) | Camera module defect detection method, device, equipment, storage medium and product | |
| CN115131355B (en) | Intelligent method for detecting waterproof cloth abnormity by using electronic equipment data | |
| CN114723647A (en) | Defect classification method and device, equipment and storage medium | |
| CN113298166A (en) | Defect classifier, defect classification method, device, equipment and storage medium |
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 | ||
| CB02 | Change of applicant information |
Address after: 100176 building 12, yard 156, Jinghai 4th Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant after: Dongfang Jingyuan Microelectronics Technology (Beijing) Co.,Ltd. Address before: 101102 building 12, yard 156, Jinghai 4th Road, Beijing Economic and Technological Development Zone, Daxing District, Beijing Applicant before: DONGFANG JINGYUAN ELECTRON Ltd. |
|
| CB02 | Change of applicant information |