基于改进的Faster R-CNN的齿轮外观缺陷识别研究

doi:10.16182/j.issn1004731x.joss.19-0545

系统仿真学报 ›› 2019, Vol. 31 ›› Issue (11): 2198-2205.doi: 10.16182/j.issn1004731x.joss.19-0545

基于改进的Faster R-CNN的齿轮外观缺陷识别研究

吉卫喜^1,2, 杜猛¹, 彭威^1,2, 徐杰^1,2

1. 江南大学机械工程学院,江苏无锡 214122;
2. 江南大学江苏省食品制造装备重点实验室,江苏无锡 214122

收稿日期:2019-09-23 修回日期:2019-10-10 出版日期:2019-11-10 发布日期:2019-12-13
作者简介:吉卫喜(1961-),男,江苏泰州,博士,教授,博导,研究方向为产品数字化设计与智能制造、先进制造技术等;杜猛(1993-),男,江苏泰州,硕士生,研究方向为机器视觉、人工智能。
基金资助:
国家自然科学基金(11402264)

Research on Gear Appearance Defect Recognition Based on Improved Faster R-CNN

Ji Weixi^1,2, Du Meng¹, Peng Wei^1,2, Xu Jie^1,2

1. School of Mechanical Engineering, Jiangnan University, Wuxi 214122, China;
2. Jiangsu Provincial Key Laboratory of Food Manufacturing Equipment, Wuxi 214122, China

Received:2019-09-23 Revised:2019-10-10 Online:2019-11-10 Published:2019-12-13

摘要/Abstract

摘要： 为了实现齿轮外观缺陷自动化识别,提高齿轮产品的合格率。针对传统缺陷识别算法泛化差,人工提取特征耗时,提出了一种改进的较快的基于区域卷积神经网络(Faster R-CNN)的齿轮缺陷识别模型。设计出VGG-2CF网络,提高识别较小目标的能力;引入AM-Softmax损失函数,以减小类内特征的差异性,进一步增大类之间差异性;结合机器学习算法中的F度量值(F-measure),提出一种AMF-Softmax损失函数,解决数据不平衡的问题。实验结果表明,提出的改进模型具有较高的识别率,适用于齿轮外观的自动化检测。

关键词: 齿轮缺陷识别, Faster R-CNN, VGG-2CF, AMF-Softmax损失函数

Abstract: In order to achieve automatic identification of gear appearance defects and improve the qualification rate of gear products, aiming at the generalization of traditional defect recognition algorithms and the time-consuming of manual features extraction, this paper proposes an improved gear flaw detection algorithm for Faster R-CNN. VGG-2CF network is designed to improve the ability to identify smaller targets. Introducing AM-Softmax loss function is introduced to reduce the intra-class variation and optimize the inter-class difference. Combining with F-measure in machine learning algorithm, an AMF-Softmax loss function is proposed to solve the problem of data imbalance. The experimental results show the improved model proposed in the paper has a high recognition rate and is suitable for automatic detection of gear appearance.

Key words: gear defect recognition, Faster R-CNN, VGG-2CF, AMF-Softmax loss function

中图分类号:

TP391.4

吉卫喜, 杜猛, 彭威, 徐杰. 基于改进的Faster R-CNN的齿轮外观缺陷识别研究[J]. 系统仿真学报, 2019, 31(11): 2198-2205.

Ji Weixi, Du Meng, Peng Wei, Xu Jie. Research on Gear Appearance Defect Recognition Based on Improved Faster R-CNN[J]. Journal of System Simulation, 2019, 31(11): 2198-2205.

参考文献

[1] 杨淑莹, 任翠池, 张成, 等. 基于机器视觉的齿轮产品外观缺陷检测[J]. 天津大学学报, 2007, 40(9): 1111-1114.
Yang Sshuying, Ren Cuichi, Zhang Cheng, et al.Defect Inspection of Gear Product Appearance Based on Machine Vision[J]. Journal of Tianjin University, 2007, (9): 1111-1114.
[2] 贺秋伟, 王龙山, 于忠党, 等. 基于图像处理和支持向量机的微型齿轮缺陷检测[J]. 吉林大学学报(工学版), 2008, 38(3): 565-569.
He Qiuwei, Wang Longshan, Yu Zhongdang, et al.Defect Detection for Microgear Based on Image Processing and Support Vector Machine[J]. Journal of Jilin University (Engineering and Technology Edition), 2008, 38(3): 565-569.
[3] 吴秀永, 徐科, 徐金梧. 基于Gabor小波和核保局投影算法的表面缺陷自动识别方法[J]. 自动化学报, 2010, 36(3): 438-441.
Wu Xiuyong, Xu Ke, Xu Jinwu.Automatic Recognition Method of Surface Defects Based on Gabor Wavelet and Kernel Locality Preserving Projections[J]. Acta Automatica Sinica, 2010, 36(3): 438-441.
[4] Lecun Y, Bottou L, Bengio Y, et al.Gradient-based learning applied to document recognition[J]. Proceedings of the IEEE (S0018-9219), 1998, 86(11): 2278-2324.
[5] Krizhevsky A, Sutskever I, Hinton G.ImageNet Classification with Deep Convolutional Neural Networks[C]. 26th Annual Conference on Neural Information Processing Systems 2012. Lake Tahoe, Nevada, USA: NIPS. 2012: 1097-1105.
[6] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556, 2014.
[7] Szegedy C, Liu W, Jia Y, et al.Going Deeper with Convolutions[C]. 2015 IEEE Conference on Computer Vision and Pattern Recognition. Boston, Massachusetts, USA: IEEE, 2015: 1-9.
[8] He K, Zhang X, Ren S, et al.Deep Residual Learning for Image Recognition[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 770-778.
[9] Redmon J, Divvala S, Girshick R, et al.You only look once: Unified, real-time object detection[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 779-788.
[10] 薛月菊, 朱勋沐, 郑婵, 等. 基于改进FasterR-CNN识别深度视频图像哺乳母猪姿态[J]. 农业工程学报, 2018, 34(9): 189-196.
Xue Yueju, Zhu Xunmu, Zheng Chan, et al.Lactating sow postures recognition from depth image of videos based on improved Faster R-CNN[J]. Transactions of the Chinese Society of Agricultural Engineering, 2018, 34(9): 189-196.
[11] Girshick R, Donahue J, Darrell T, et al.Rich feature hierarchies for accurate object detection and semantic segmentation[C]. 2014 IEEE Conference on Computer Vision and Pattern Recognition. Columbus, OH, USA: IEEE. 2014: 580-587.
[12] Girshick Ross.Fast R-CNN[C]. Proceedings of the IEEE International Conference on Computer Vision. Santiago, Chile: IEEE Computer Society, 2015: 1440-1448.
[13] Ren S, He K, Girshick R, et al.Faster R-CNN: Towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence(S0162-8828), 2015, 39(6): 1137-1149.
[14] Wu Z, Su L, Huang Q.Cascaded Partial Decoder for Fast and Accurate Salient Object Detection[C]. 2019 IEEE Conference on Computer Vision and Pattern Recognition. Long Beach, CA, USA: IEEE, 2019: 3907-3916.
[15] Q Hou, M Cheng, X Hu, et al.Deeply supervised salient object detection with short connections[J]. IEEE TPAMI (S1057-7149), 2019, 41(4): 815-828.
[16] G Li and Y Yu. Deep contrast learning for salient object detection[C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas, NV, USA: IEEE, 2016: 478-487.
[17] Luo Z, Mishra A K, Achkar A, et al.Non-local deep features for salient object detection[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 6609-6617.
[18] Liu W, Rabinovich A, Berg A C. Parsenet: Looking wider to see better[J]. arXiv preprint arXiv:1506.04579, 2015.
[19] Wang F, Cheng J, Liu W, et al.Additive Margin Softmax for Face Verification[J]. IEEE Signal Processing Letters (S1070-9908), 2018: 1-1.
[20] Liu W, Wen Y, Yu Z, et al.SphereFace: Deep Hypersphere Embedding for Face Recognition[C]. 2017 IEEE Conference on Computer Vision and Pattern Recognition. Honolulu, HI, USA: IEEE, 2017: 212-220.
[21] Chawla N V, Bowyer K W, Hall L O, et al.SMOTE: Synthetic Minority Over-sampling Technique[J]. Journal of Artificial Intelligence Research (S1076-9757), 2002, 16(1): 321-357.
[22] He H, Bai Y, Garcia E A, et al.ADASYN: Adaptive Synthetic Sampling Approach for Imbalanced Learning[C]. 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence). Hong Kong, China: IEEE, 2008: 1322-1328.
[23] Liu T Y.EasyEnsemble and Feature Selection for Imbalance Data Sets[C]. International Joint Conferences on Bioinformatics, Systems Biology and Intelligent Computing. Shanghai, China: IEEE, 2009: 517-520.
[24] Liu X Y, Wu J, Zhou Z H.Exploratory Undersampli-ng for Class-Imbalance Learning[J]. IEEE Transactions on Cybernetics (S2168-2267), 2009, 39(2): 539-550.
[25] Deng J, Dong W, Socher R, et al.ImageNet: a Large-Scale Hierarchical Image Database[C]. 2009 IEEE Conference on Computer Vision and Pattern Recognition. Miami, Florida, USA: IEEE, 2009: 248-255.
[26] Zeiler M D, Fergus R.Visualizing and understanding convolutional networks[C]. European Conference on Computer Vision. Cham: Springer International Publishing, 2014: 818-833.

基于改进的Faster R-CNN的齿轮外观缺陷识别研究

Research on Gear Appearance Defect Recognition Based on Improved Faster R-CNN

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价