%0 Journal Article
%A DU Yunhao
%A TONG Zhihang
%A WAN Junfeng
%A ZHAO Yanyun
%A ZHANG Binyu
%T Character Detection Method for PCB Image Based on Deep Learning
%D 2022
%R 10.13190/j.jbupt.2021-109
%J Journal of Beijing University of Posts and Telecommunications
%P 108-114
%V 45
%N 1
%X Retrieve the printed circuit board (PCB) image with characters is an effective method for PCB fragments tracing. To this end, a high-performance character detection method for PCB images is proposed, which adopts feature pyramid network based on residual network and has two detecting heads to predict character distribution heatmaps. The local pattern consistency loss function is introduced to optimize the network model. A heatmap generation algorithm of character region for network training is presented. A series of strategies are adopted, such as data augmentation and multi-scale detection, which increases the performance of character detection. The test results on PCB image set show that the character detection accuracy is 95.6% and the recall rate is 92.4%. Especially, F1 score can reach 93.6%, which exceeds the comparison methods, proving that the proposed comprehensive detection method outperforms the state of the art methods of character detection in natural scene images.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2021-109