Premium
81‐4: Array Defect Detection and Repair Based on Deep Learning
Author(s) -
Guo Kai,
Li Xiaolong,
Niu Yanan,
Qin Wei,
Peng Kuanjun,
Liu Weixing,
Xu Zhiqiang,
Teng Wanpeng,
Wang Tieshi,
Zhang Chunfang,
Qin Bin,
Wang Wei
Publication year - 2020
Publication title -
sid symposium digest of technical papers
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.351
H-Index - 44
eISSN - 2168-0159
pISSN - 0097-966X
DOI - 10.1002/sdtp.14099
Subject(s) - computer science , artificial intelligence , offset (computer science) , upsampling , feature (linguistics) , convolution (computer science) , pattern recognition (psychology) , layer (electronics) , convolutional neural network , deep learning , artificial neural network , computer vision , materials science , image (mathematics) , nanotechnology , linguistics , philosophy , programming language
Defect detection is a common task in industry production, array defect is an undesirable phenomenon in array substrate production process due to the environment, production conditions and so on. Array defect detection is very important for the quality performance of final product. Compared with other defects, array defects have a more complex background, make the detection logic is more advanced and difficult to judge. In this paper, we propose a convolution neural network (CNN) for array defect detection based on Faster‐RCNN architecture. On the basis of VGG16 network, we add cross‐connection layer in feature extracted layer to improve the accuracy of small‐size defect detection. On the other hand, we use ROIAlign layer instead of ROI pooling layer to offset the position migration caused by downsampling. The experimental results show that our strategies have a good performance in array defect detection. The precious of defect recognition is more than 95%, and the recall rate is more than 86%, while the defects are divided into 10 categories and the marking image is about 1400 for each type of defect. At the same time, a defect repair scheme based on generating adversarial network (GAN) were proposed: a) input an array defect image and GAN can be used to generate the image without defect or after defect repair, b) the defect repair template can be obtained by compare the generated result with original image, c) this defect repair template can provide reference for practical repair of array defect. In addition, the GAN can be used to optimize array repair scheme and even take the place of manual array defect repair in the future, which can promote the intelligent repair of array defect.