A deep learning-based approach for the automated surface inspection of copper clad laminate images
- PDF / 4,447,324 Bytes
- 18 Pages / 595.224 x 790.955 pts Page_size
- 90 Downloads / 212 Views
A deep learning-based approach for the automated surface inspection of copper clad laminate images Xiaoqing Zheng1
· Jie Chen1 · Hongcheng Wang1 · Song Zheng1 · Yaguang Kong1
© Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract Surface quality inspection and control are extremely important for electronic manufacturing. The use of machine vision technology to automatically detect the defects of products has become an indispensable means for better quality control. A machine vision-based surface quality inspection system is usually composed of two processes: image acquisition and automatic defect detection. In this paper, we propose a deep learning-based approach for the defect detection of Copper Clad Laminate (CCL) images acquired from an industrial CCL production line. In the proposed approach, a new convolutional neural network (CNN) that realizes fast defect detection while maintaining high accuracy is designed. Our proposed approach makes four contributions. First, we introduce the depthwise separable convolution to reduce the calculation time. Second, we improve the squeeze-and-excitation block to improve network performance. Third, we introduce the squeezeand-expand mechanism to reduce the computation cost. Fourth, we employ a smoother activation function (Mish) to allow improved information flow. The proposed network is compared with the benchmark CNNs (including Inception, ResNet and MobileNet). The experimental results show that compared with the benchmark networks, our proposed network has achieved the best results regarding the accuracy and suboptimal results in terms of the speed compared with the benchmark networks. Therefore, our proposed method has been integrated into an industrial CCL production line as a guideline for online defective product rejection. Keywords Machine vision · Defect detection · Deep learning · Convolutional neural network · Efficient network
1 Introduction Traditionally, the surface quality inspection of electronic products employs manual detection methods performed by quality inspectors. However, these manual methods have the disadvantages of a low sampling rate, low accuracy, poor realtime performance, low efficiency and high labor intensity, whereas machine vision-based automated surface inspection methods can largely overcome the above drawbacks This work was supported in part by National Natural Science Foundation of China under grant number U1609212, Zhejiang Provincial Science and Technology Plan under grant number 2019C04021, and Zhejiang Province Public Technology Research Project under grant number LGG20F030002. Xiaoqing Zheng
[email protected] Jie Chen [email protected] 1
Hangzhou Dianzi University, Hangzhou, China
[1]. At present, the use of machine vision technology, i.e., by adding a vision system to the machine or automatic production line, has become an indispensable technical means of quality control for electronics manufacturing. Machine vision-based surface inspection systems are mainly composed of two processes: image
Data Loading...
