[1]王栋栋,陈 龙,吴晨睿.基于改进 SEAM 的金属表面缺陷检测算法[J].计算机技术与发展,2022,32(S2):126-131.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 022]
　WANG Dong-dong,CHEN Long,WU Chen-rui.Metal Surface Defect Detection Algorithm Based on Improved SEAM[J].,2022,32(S2):126-131.[doi:10. 3969 / j. issn. 1673-629X. 2022. S2. 022]
点击复制

基于改进 SEAM 的金属表面缺陷检测算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
32
期数:
2022年S2期
页码:
126-131
栏目:
应用前沿与综合
出版日期:
2022-12-11

文章信息/Info

Title:
Metal Surface Defect Detection Algorithm Based on Improved SEAM
文章编号:
1673-629X(2022)S2-0126-06
作者:
王栋栋; 陈 龙; 吴晨睿
上海理工大学 机械工程学院,上海 200093
Author(s):
WANG Dong-dong; CHEN Long; WU Chen-rui
School of Mechanical Engineering,University of Shanghai for Science and Technology, Shanghai 200093,China
关键词:
金属表面缺陷; 深度学习; 弱监督分割; 高响应区域抑制; 因果干预
Keywords:
metal surface defects; deep learning; weakly supervised segmentation; high response region suppression; causal intervention
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2022. S2. 022
摘要:
金属表面缺陷检测对于把控产品的质量安全至关重要。 针对现有缺陷检测算法存在数据标注困难和准确率低的问题,提出一种基于弱监督学习的检测算法。 以 SEAM 算法为框架,使用图像级别标签来预测缺陷位置和种类。 在网络特征提取部分添加融合通道注意力的高响应区域抑制模块,挖掘缺陷特征深层信息。 在模型训练阶段,通过因果干预策略消除类间模糊造成的语义混淆,从而提升金属表面缺陷检测准确度。 通过实验在金属表面缺陷的小样本数据集上验证了该方法的有效性与优越性。
Abstract:
Metal surface defect detection is very important to control the quality and safety of products. Aiming at the problems of dataannotation difficulty and low accuracy of existing defect detection algorithms,a detection algorithm based on weakly supervised learningwas proposed. Using the SEAM algorithm as the framework,image-level labels are used to predict the location and type of defects. Thehigh-response region suppression module of fusion channel attention was added in the network feature extraction part to mine the deep information of defect features. In the model training stage,the semantic confusion caused by inter-class ambiguity is eliminated throughcausal intervention strategy,so as to improve the accuracy of metal surface defect detection. The effectiveness and superiority of theproposed method are verified by experiments on a small sample data set of metal surface defects.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(S2):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(S2):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(S2):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(S2):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(S2):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(S2):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(S2):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(S2):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(S2):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(S2):7.

更新日期/Last Update: 2022-10-10