- 专利标题: Method for defect classification, method for training defect classifier, and apparatus thereof
-
申请号: US16859332申请日: 2020-04-27
-
公开(公告)号: US11334982B2公开(公告)日: 2022-05-17
- 发明人: Xiangjun Peng , Yunqi Wang , Chenxi Zhao , Yachong Xue , Gang Li , Yaoyu Lv , Shuo Zhang , Minglei Chu , Lili Chen , Hao Zhang
- 申请人: Beijing BOE Optoelectronics Technology Co., Ltd. , BOE Technology Group Co., Ltd.
- 申请人地址: CN Beijing; CN Beijing
- 专利权人: Beijing BOE Optoelectronics Technology Co., Ltd.,BOE Technology Group Co., Ltd.
- 当前专利权人: Beijing BOE Optoelectronics Technology Co., Ltd.,BOE Technology Group Co., Ltd.
- 当前专利权人地址: CN Beijing; CN Beijing
- 代理机构: Banner & Witcoff, Ltd.
- 优先权: CN201910670824.2 20190724
- 主分类号: G06T7/00
- IPC分类号: G06T7/00
摘要:
The disclosure provides a method for defect classification, including: extracting a low-level feature of a defect region from a defect image; encoding the low-level feature by using a defect dictionary to obtain a middle-level semantic feature corresponding to the low-level feature; classifying a defect in the defect region of the defect image into one of a plurality of defect categories based on the middle-level semantic feature, wherein the defect dictionary includes a defect intra-category dictionary and a defect inter-category dictionary.
公开/授权文献
信息查询