期刊
VISUAL COMPUTER
卷 38, 期 11, 页码 3731-3745出版社
SPRINGER
DOI: 10.1007/s00371-021-02210-6
关键词
Surface detection; Deep learning; Low-light enhancement; Complex scenes; Multi-scale feature extraction
资金
- R&D projects in key areas of Guangdong Province [2018B010109007]
- National Natural Science Foundation of Guangdong Joint Funds [U1801263, U1701262, U2001201]
- Natural Science Foundation of Guangdong Province [2020A1515010890]
- projects of science and technology plan of Guangdong Province [2017B090901019, 2016B010127005]
- Guangdong Provincial Key Laboratory of Cyber-Physical System [2020B1212060069]
This paper proposes a defect detection network based on low-light enhancement and multi-scale feature extraction, which introduces two blocks for low-light enhancement and combining channel dependencies for multi-scale feature extraction. This network can accurately locate defects of different scales in complex scenes, outperforming the state-of-the-art method for surface defect detection.
Surface defect detection of industrial products has become a promising area of research. Among the existing defect detection algorithms, most of the CNN-based methods can achieve the task of defect detection under ideal experimental conditions. However, the accuracy of defect detection is easily affected by the different lighting conditions of the environment and the inconsistency of the defect scale. Therefore, general deep learning methods have difficulties in solving the problem of defect detection in complex scenes. In this paper, a defect detection network based on low-light enhancement and multi-scale feature extraction (LE-MSFE-DDNet) is proposed. There are two blocks in the proposed network, including a low-light enhancement block and a SE-FP block. In the low-light enhancement block, the deep network is applied to enhance light adaptation of the deconstructed low-light feature map in our network. The influence of illumination inconsistency is weakened by the introduction of this block. In the SE-FP block, the dependencies between different channels are combined with the multi-scale feature extraction. The defects with different scales are accurately located through the combination of this block and our network. In addition, a Fine Cans Defect dataset based on the surface of fine cans is collected by this paper to verify the feasibility of the proposed network. The proposed model is compared with the state-of-the-art object detection network and the proposed method achieves 94.3% average accuracy on the Fine Cans Defect dataset. The experimental results show that the proposed method outperforms the state-of-the-art method for surface defect detection.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据