Open AccessSegmentation of Cracked Silicon Wafer Image Based on Deep Learning
Author(s) -
Xingxing Li,
Panpan Yin,
Chao Duan,
Ningxing Wang
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2083/3/032088
Subject(s) - wafer , artificial intelligence , segmentation , deep learning , silicon , automation , computer science , image segmentation , test set , set (abstract data type) , pattern recognition (psychology) , materials science , computer vision , engineering , optoelectronics , mechanical engineering , programming language
With the development of the new energy industry, a large number of silicon wafers need to be tested for production quality through the automation industry. The development of deep learning technology has brought huge technological improvements to the industrial quality inspection industry. Through the image segmentation technology based on deep learning, it can accurately divide the defects existing in the silicon wafer. In this paper, the UNet deep learning network is used to segment the hidden cracks in the silicon wafer. The network can extract the shallow semantic features in the silicon wafer well. It uses 5,000 samples collected on the industrial site as the training set,1,000 pieces the sample is used as the test set, and the segmentation accuracy IOU can reach 58.7%.