Solar Cells Surface Defects Detection Based on Deep Learning
WANG Xian-Bao1,2, LI Jie1, YAO Ming-Hai1, HE Wen-Xiu1, QIAN Yun-Tao2
1College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023 2College of Computer Science and Technology, Zhejiang University, Hangzhou 310027
Abstract Defects of solar cells are detected mainly by manual operation, and they are difficult to be detected automatically by traditional charge-coupled device(CCD) imaging system. As a training multi-layer neural network, deep learning draws great attention due to its strong ability to extract features from input sample data. A method for solar cells surface defects detection based on deep learning is proposed. Firstly, deep belief networks(DBN) are established and trained according to the sample features to obtain the initial weights of the networks. Then, the traditional BP algorithm is conducted to fine-tune the network parameters to get the mapping relationship between the training samples and the defect-free template. Finally, the defects of testing samples are detected by the contrast between the reconstruction image and the defect image. Experimental results show that DBN perfectly establishes the mapping relationship, and it can quickly detect defects with a high accuracy.
[1] Bengio Y. Learning Deep Architectures for AI. Foundations and Trends in Machine Learning, 2009, 2(1): 1-127 [2] Hinton G E, Salakhutdinov R R. Reducing the Dimensionality of Data with Neural Networks. Science, 2006, 313(5786): 504-507 [3] Sun Z J, Xue L, Xu Y M, et al. Overview of Deep Learning. Application Research of Computers, 2012, 29(8): 2806-2810 (in Chinese) (孙志军,薛 磊,许阳明,等.深度学习研究综述.计算机应用研究, 2012, 29(8): 2806-2810) [4] Bengio Y, Delalleau O. On the Expressive Power of Deep Architectures // Proc of the 22nd International Conference on Algorithmic Learning Theory. Espoo, Finland, 2011: 18-36 [5] Yoshua B, LeCun Y. Scaling Learning Algorithms towards AI. Cambridge, USA: MIT Press, 2007 [6] Dahl G E, Yu D, Deng L, et al. Context-Dependent Pre-trained Deep Neural Networks for Large-Vocabulary Speech Recognition. IEEE Trans on Audio, Speech and Language Processing, 2012, 20(1): 30-42 [7] Hinton G, Deng L, Yu D, et al. Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups. IEEE Signal Processing Magazine, 2012, 29(6): 82-97 [8] Sungjoon C, Kim E, Oh S. Human Behavior Prediction for Smart Homes Using Deep Learning // Proc of the 22nd IEEE International Symposium on Robot and Human Interactive Communication. Gyeongju, Republic of Korea, 2013: 173-179 [9] Lin M Z. Research on Face Recognition Based on Deep Learning. Master Dissertation. Dalian, China: Dalian University of Technology, 2013 (in Chinese) (林妙真.基于深度学习的人脸识别研究.硕士学位论文.大连:大连理工大学, 2013) [10] Wang N Y, Yeung D. Learning a Deep Compact Image Representation for Visual Tracking // Proc of the 27th Annual Conference on Neural Information Processing Systems. Lake Tahoe, USA, 2013: 809-817 [11] Chen Y, Zheng D Q, Zhao T J. Chinese Relation Extraction Based on Deep Belief Nets. Journal of Software, 2012, 23(10): 2572-2585 (in Chinese) (陈 宇,郑德权,赵铁军.基于Deep Belief Nets的中文名实体关系抽取.软件学报, 2012, 23(10): 2572-2585) [12] Tsai D M, Wu S C, Li W C. Defect Detection of Solar Cells in Electroluminescence Images Using Fourier Image Reconstruction. Solar Energy Materials and Solar Cells, 2012, 99: 250-262 [13] Bastari A, Bruni A, Cristalli C. Classification of Silicon Solar Cells Using Electroluminescence Texture Analysis // Proc of the IEEE International Symposium on Industrial Electronics. Bari, Italy, 2010: 1722-1727 [14] Fuyuki T, Kitiyanan A. Photographic Diagnosis of Crystalline Silicon Solar Cells Utilizing Electroluminescence. Applied Physics A: Materials Science and Processing, 2009, 96(1): 189-196 [15] Hinton G E, Osindero S, Teh Y W. A Fast Learning Algorithm for Deep Belief Nets. Neural Computation, 2006, 18(7): 1527-1554 [16] Smolensky P. Information Processing in Dynamical Systems: Foundations of Harmony Theory[EB/OL]. [2013-12-10]. http://www-psych.stanford.edu/~jlm/papers/PDP/Volume%201/Chap6_PDP86.pdf [17] Ackley D H, Hinton G E, Sejnowski T J. A Learning Algorithm for Boltzmann Machines. Cognitive Science, 1985, 9(1): 147-169 [18] Zhang C X, Ji N N, Wang G W. Introduction of Restricted Boltzmann Machines[EB/OL]. [2013-01-11]. http://www.paper.edu.cn/releasepaper/content/201301-528 (in Chinese) (张春霞,姬楠楠,王冠伟.受限玻尔兹曼机简介[EB/OL]. [2013-01-11]. http://www.paper.edu.cn/releasepaper/content/201301-528) [19] Hinton G E. Training Products of Experts by Minimizing Contrastive Divergence. Neural Computation, 2002, 14(8): 1771-1800 [20] Hu Y. Markov Chain Monte Carlo Based Improvements to the Learning Algorithm of Restricted Boltzmann Machines. Master Dissertation. Shanghai, China: Shanghai Jiao Tong University, 2012(in Chinese) (胡 洋.基于马尔可夫链蒙特卡罗方法的RBM学习算法改进.硕士学位论文.上海:上海交通大学, 2012) [21] Sutskever I, Tieleman T. On the Convergence Properties of Contrastive Divergence[EB/OL].[2013-12-20].http://machinelearning.wustl.edu/mlpapers/paper_files/AISTATS2010_SutskeverT10.pdf [22] Hinton G E, Dayan P, Frey B J, et al. The "Wake-Sleep" Algorithm for Unsupervised Neural Networks. Science, 1995, 268(5214): 1158-1161 [23] Yao M H, Li J, Wang X B. Solar Cells Surface Defects Detection Using RPCA Method. Chinese Journal of Computers, 2013, 36(9): 1943-1952 (in Chinese) (姚明海,李 洁,王宪保.基于RPCA的太阳能电池片表面缺陷检测.计算机学报, 2013, 36(9): 1943-1952)
2014, Vol. 27 
