Surface Defect Detection of Solar Cells Based on Feature Pyramid Network and GA-Faster-RCNN

Automatic defect detection of solar cells' near-infrared electroluminescence (EL) images is a challenging task due to non-uniform complex texture background interference and the defects' small size. Therefore, this paper proposes a new surface defect detection scheme of solar cells based on Faster-RCNN. In order to improve the accuracy and speed of defect detection, we modify the defect extraction part and RPN part of the original Faster-RCNN. Firstly, we combine CNN with Feature Pyramid Network (FPN) to achieve multi-scale defect feature extraction. By combining multiple layers of feature information, the semantic information is more robust and the detection accuracy of small targets is improved. Secondly, we apply Guided Anchoring RPN (GA-RPN) to achieve adaptive adjustment of the anchor. It will predict the position and shape of the anchor according to the feature of the defect, and then use the feature adaption to adjust the feature map to generate proposals with high quality and low density. Experiment results show that the improved model has a mAP of 94.62, an increase of 11.26% compared with the original Faster-RCNN model, and the detection speed is increased from 0.91s/img to 0.19s/img, which can meet the basic requirements of industrial production. The architecture combining FPN, GA-RPN and Faster-RCNN improves the accuracy and speed of defect detection, and effectively realizes the defect detection of polysilicon near-infrared image under complex background, which lays a foundation for the defect detection automation of solar cells.