计算机科学 ›› 2017, Vol. 44 ›› Issue (Z11): 238-243.doi: 10.11896/j.issn.1002-137X.2017.11A.050
乔丽,赵尔敦,刘俊杰,程彬
QIAO Li, ZHAO Er-dun, LIU Jun-jie and CHENG Bin
摘要： 将卷积神经网络(CNN)应用于工件缺陷检测,来检测工件在生产过程中表面出现的缺陷,以提高工件的生产质量。利用CNN可以对工件的图案进行识别,但识别无法检测出细微缺陷的问题。在CNN进行工件图案识别的基础上,研究一种利用CNN实现缺陷检测的方法。该方法通过扩充缺陷样本,利用CNN识别的中间输出参数,定义了缺陷分辨率的概念来衡量缺陷的程度,当缺陷分辨率达到一定水平时则认为是无缺陷图案,否则认为其存在缺陷。实验验证了提出的CNN工件缺陷检测方法的有效性,数据表明缺陷检出率可达到 93.3%。
| [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] LCUN 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! |
|
||
首页