Computer Science ›› 2016, Vol. 43 ›› Issue (2): 64-67.doi: 10.11896/j.issn.1002-137X.2016.02.014

Previous Articles     Next Articles

Capsule Defects Detection Based on Stacked Denoising Autoencoders

WANG Xian-bao, HE Wen-xiu, WANG Xin-gang, YAO Ming-hai and QIAN Yun-tao   

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

Abstract: At present defects of capsules are detected mainly by manual operation,which is time-consuming and needs high labor costs,besides,it is easily misled by subjective factors.This paper proposed a method of detection of capsules surface defects based on stacked denoising autoencoders (SDAE).Our method firstly establishes deep autoencoders networks and trains using a denoising criterion according to the defect samples to obtain the initial weights at first.Then,BP algorithm fine-tunes the network parameters to get the mapping relationship between the training sample and defect-free template.Finally, defect detection of the testing samples is finished by comparing the reconstruction image and defect image.Experimental results show that SDAE perfectly establishes the mapping relationship,which is robust and stable to noise,and can quickly detect defects with high accuracy.

Key words: Stacked denoising autoencoders,Defect detection,Deep learning

[1] Hinton G E,Salakhutdinov R R.Reducing the dimensionality of data with neural networks[J].Science,2006,3(28):504-507
[2] Hinton G E,Osindero S,Teh Y-W.A fast learning algorithm for deep belief nets[J].Nueral Computation,2006,8(7):1527-1554
[3] Bengio Y.Learning deep architectures for AI[J].Foundations and Trends in Machine Learning,2009,2(1):1-127
[4] Dong Yu,Li Deng.Deep learning and its applications to signal and information processing[J].IEEE Signal Processing M agazine,2011,28(1):145-154
[5] Karnowski T P,Arel I,et al.Deep spatiotemporal feature lear-ning with application to image classification[C]∥Proceedings of the Ninth International Conference on Machine Learning and Applications.Washington,USA,2010:883-888
[6] Schulz H,Behnke S.Deep learning:layer-wise learning of fea-ture hierarchies[J].Künstl Intell,2012,26:357-363
[7] Vincent P,Larochelle H,Lajoie I,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion [J].Journal of Machine Learning Research,2010,11(12):3371-3408
[8] Kang Y,Lee K T,Eun J,et al.Stacked Denoising Autoencoders for Face Pose Normalization [C]∥20th International Confe-rence on Neural Information Processing.Berlin:Springer Press,2013:241-248
[9] Zhang Ying,Liu Rui,Zhang Sai-zheng,et al.Occlusion-Robust Face Recognition Using Iterative Stacked Denoising Autoenco-der[C]∥20th International Conference on Neural Information Processing.Berlin:Springer Press,2013:352-359
[10] Sang Ruo-xin,Jin Pei-quan,Wan Shou-hong.Discriminative Feature Learning for Action Recognition Using a Stacked Denoising Autoencoder[M]∥Intelligent Data Analysis and Its Applications, Volume1.2014:521-531
[11] Agostinelli F,Anderson M R,et al.Adaptive multi-column deep neural networks with application to robust image denoising[C]∥Proceedings of the Advances in Neural Information Processing Systems 26 (NIPS’12).Cambridge:MIT Press,2013:1-9
[12] Wei Lin,Hu Rong-qiang.The Automatic Inspection System ofCapsule Product Based on BP Neural Network[J].Application Research of Computers,2002,9(4):52-53(in Chinese)韦琳,胡荣强.基于BP网络的胶囊药片自动检测系统[J].计算机应用研究,2002,9(4):52-53
[13] Zuo Qi,Shi Zhong-ke.General design for capsule integrality detection system based on machine vision[J].Journal of Xi’an Jiaotong University,2002,36(12):1262-1265(in Chinese) 左奇,史忠科.基于机器视觉的胶囊完整性检测系统研究[J].西安交通大学学报,2002,36(12):1262-1265
[14] Feng Shan-shan,Chen Shu-yue.Research on identification me-thod for capsule-grain of real and false medicine based on image analyzing[J].Transducer and Micro system Technologies,2008,27(8):54-56(in Chinese) 冯姗姗,陈树越.基于图像分析的真假药胶囊颗料识别方法研究[J].传感器与微系统,2008,27(8):54-56
[15] Lai Da-hu,Huang Yan-wei.Inspection for defected capsulesbased on extreme learning machine[J].Journal of Fuzhou University (Natural Science Edition),2012,0(4):489-494(in Chinese) 赖大虎,黄宴委.基于极端学习机的胶囊缺陷检测[J].福州大学学报(自然科学版),2012,0(4):489-494

No related articles found!
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!