Computer Science ›› 2017, Vol. 44 ›› Issue (Z11): 238-243.doi: 10.11896/j.issn.1002-137X.2017.11A.050

Previous Articles     Next Articles

Research of Workpiece Defect Detection Method Based on CNN

QIAO Li, ZHAO Er-dun, LIU Jun-jie and CHENG Bin   

  • Online:2018-12-01 Published:2018-12-01

Abstract: The application of convolutional neural network (CNN) was proposed in workpiece defect detection,which can detect workpiece defects on its surface,to improve the product quality.The CNN can’t recognize the small defects of a product although it can classify different objects very well.This paper presented a method which uses CNN for defect detection based on the results of a recognition process.Firstly the defective samples are expanded to overcome the difficulty for lacking of training samples.Then by observing the output data obtained from a recognition CNN,a concept called “the defect distinguish ratio” is defined to measure the degree of defection.It is considered as a non-defect pattern only when the defect distinguish ratio reaches a certain level.Finally,the experiment demonstrates the validity and feasibility of the method,in which the defect detection ratio can reach 93.3%.

Key words: Workpiece defect detection,CNN,Training samples,Defect distinguish ratio

[1] 王宪保,何文秀,王辛刚,等.基于堆叠降噪自动编码器的胶囊缺陷检测方法[J].计算机科学,2016,43(2):64-67.
[2] 罗菁,董婷婷,宋丹,等.表面缺陷检测综述[J].计算机科学与探索,2014,8(9):1041-1048.
[3] LAWRENCE S,GILES C L,TSOI A C,et al.Face recognition:a convolutional neural-network approach.[J].IEEE Transactions on Neural Networks,1997,8(1):98-113.
[4] LCUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based lear-ning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[5] 黎健成,袁春,宋友.基于卷积神经网络的多标签图像自动标注[J].计算机科学,2016,3(7):41-45.
[6] ABDEL-HAMID O,DENG L,YU D.Exploring Convolutional Neural Network Structures and Optimization Techniques for Speech Recognition[C]∥Interspeech.2013:1173-1175.
[7] MA L,LU Z,SHANG L,et al.Convolutional Neural Networks for Sentence Classification[J].Eprint Arxiv,arXiv:1408.5882.
[8] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324.
[9] 陈勇.基于机器视觉的表面缺陷检测系统的算法研究及软件设计[D].南京:南京航空航天大学,2006.
[10] SIMARD P Y,STEINKRAUS D,PLATT J C.Best Practicesfor Convolutional Neural Networks Applied to Visual Document Analysis[C]∥International Conference on Document Analysis and Recognition.IEEE Computer Society,2003:958.
[11] 高如新,杨晓雪,齐成.基于钢板表面缺陷检测的图像增强研究[J].河南理工大学学报(自然科学版),2015,34(6):850-854.
[12] LIU C,LIU J,YU F,et al.Handwritten character recognitionwith sequential convolutional neural network[C]∥International Conference on Machine Learning and Cybernetics.IEEE,2013:291-296.
[13] 赵志宏,杨绍普,马增强.基于卷积神经网络LeNet-5的车牌字符识别研究[J].系统仿真学报,2010,2(3):638-641
[14] ZHONG Z,JIN L,FENG Z.Multi-font printed Chinese character recognition using multi-pooling convolutional neural network[C]∥2015 13th International Conference on Document Analysis and Recognition (ICDAR).IEEE Computer Society,2015:96-100.
[15] LIU C,LIU J,YU F,et al.Handwritten character recognition with sequential convolutional neural network[C]∥International Conference on Machine Learning and Cybernetics.IEEE,2013:291-296.
[16] BLUCHER T,NEY H,KERMORVANT C.Tandem HMMwith convolutional neural network for handwritten word recognition[C]∥2013 IEEE International Conference on Acoustics,Speech and Signal Processing(ICASSP).IEEE,2013:2390-2394.

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!