Method and device for defect detection
AssigneeContemporary Amperex Technology (Hong Kong) Limited
InventorsYongfa Liu, Guannan Jiang, Annan Shu
Life of this patent
Estimating the term…
Abstract
A method and a device for defect detection are provided. The method includes: obtaining a defect eigenvector of an image to be detected; calculating a similarity score of the image to be detected for each known defect type according to the defect eigenvector; and performing defect classification on the image to be detected according to the similarity score. The similarity score between the defect eigenvector of the image to be detected and each known defect type is calculated, and then it is possible to distinguish known defects from unknown defects and accurately classify the known defects according to the similarity scores, so as to effectively detect the defects.
Claims15
A method for defect detection, performed by a defect detection device that comprises a storage medium storing program codes and a processor configured to execute the program codes, the method comprising:
- obtaining a defect eigenvector of an image to be detected by using an encoding module of the program codes;
- calculating a similarity score of the image to be detected for each known defect type according to the defect eigenvector;
- and
- performing defect classification on the image to be detected according to the similarity score;
- wherein the encoding module comprises a plurality of encoding sublayers, the plurality of encoding sublayers being connected by a maximum pooling layer;
- and
- wherein obtaining the defect eigenvector of the image to be detected by using the encoding module comprises:
- inputting the image to be detected to the encoding module, so as to obtain feature maps of sublayers that correspond to the plurality of encoding sublayers;
- and
- converting a feature map of a final sublayer in the feature maps of the sublayers into the defect eigenvector.
A device for defect detection, comprising:
- a computer-readable storage medium configured to store program codes, and a processor configured to execute the program codes;
- wherein by executing the program codes, the processor is configured to:
- obtain a defect eigenvector of an image to be detected by using an encoding module of the program codes;
- calculate a similarity score of the image to be detected for each known defect type according to the defect eigenvector;
- and
- perform defect classification on the image to be detected according to the similarity score;
- wherein the encoding module comprises a plurality of encoding sublayers, the plurality of encoding sublayers being connected by a maximum pooling layer;
- and
- wherein in obtaining the defect eigenvector of the image to be detected, the processor is configured to:
- input the image to be detected to the encoding module, so as to obtain feature maps of sublayers that correspond to the plurality of encoding sublayers;
- and
- convert a feature map of a final sublayer in the feature maps of the sublayers into the defect eigenvector.
An apparatus for defect detection, comprising a processor and a memory, wherein the memory is configured to store a program codes, and the processor is configured to call the program codes from the memory and run the program codes to perform a method that comprises:
- obtaining a defect eigenvector of an image to be detected by using an encoding module of the program codes;
- calculating a similarity score of the image to be detected for each known defect type according to the defect eigenvector;
- and
- performing defect classification on the image to be detected according to the similarity score;
- wherein the encoding module comprises a plurality of encoding sublayers, the plurality of encoding sublayers being connected by a maximum pooling layer;
- and
- wherein obtaining the defect eigenvector of the image to be detected by using the encoding module comprises:
- inputting the image to be detected to the encoding module, so as to obtain feature maps of sublayers that correspond to the plurality of encoding sublayers;
- and
- converting a feature map of a final sublayer in the feature maps of the sublayers into the defect eigenvector.
Dependencies are inferred from the claim text.