A Robust Method of LED Die Recognition Based on Dual BP Neural Networks

Abstract:

A robust method based on dual back-propagation neural networks (BPNN) is proposed to recognize light-emitting diode (LED) dies on wafer planes in vision-based LED sorting system. To improve the recognition accuracy of LED dies, particularly under the condition of LED die image degradation, a dual BPNN with 3 layers architecture is first constructed, in which the two BPNNs are trained respectively using the region features and edge features of die images based on batch gradient descent method, and then the outputs of the dual BPNN are fused according to Dempster-Shafer (D-S) theory to generate a final decision. Applying the trained dual BPNN as a classifier, the recognition experiment of a large-diameter LED wafer is completed, experimental results show that LED die recognition accuracy of the dual BPNN is higher than that of the single BPNN based on the region feature or edge feature and is robust to die image degradation, it can be used for LED die array location in vision-baesd LED sorting machines.

• Periodical: Applied Mechanics and Materials (Volume 442)
• Pages: 298-303
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.442.298
• Online since: October 2013
• Authors: He Xi Li*, Tie Niu Yang, Xiao Xi Zheng
• Keywords: Edge Feature, LED Die, Neural Network (NN), Recognition, Region Feature

References

[1] Lingyun Xue, Jiale Fang, Wei Huang and Meng Li. Research on LED die geometric parameter measurement based on shape recognition and sub-pixel detection, 2010 8th World Congress on Intelligent Control and Automation (WCICA), Jinan, China, pp.6204-6210.

DOI: 10.1109/wcica.2010.5554416

[2] Haining Zhang and Biwei Zhang. LED wafer segmented method of image recognition based on sub-pixel precision threshold, Electronic Design Engineering(In Chinese), 2011, vol. 19, no. 4, pp.113-116.

[3] Carsten Steger, Markus Ulrich and Charistian Wiedemann. Machine vision algorithms and applications, Tsinghua University Press, Beijing, 2008, pp.302-308.

[4] Cheng Hua Li, Soon Cheol Park. Combination of modified BPNN algorithms and an efficient feature selection method for text categorization. Information Processing and Management, 2009 vol. 45, no. 3, pp.329-340.

DOI: 10.1016/j.ipm.2008.09.004

[5] Sexton RS, Dorsey RE. Reliable classification using neural networks: a genetic algorithm and backpropagation comparison. Decision Support Systems, 2000, vol. 30, no. 1, pp.11-22.

DOI: 10.1016/s0167-9236(00)00086-5

[6] Basheer IA and Hajmeer.M. Artificial neural networks: fundamentals, computing, design, and application. Journal of Microbiological Methods, 2000, vol. 43, no. 1, pp.3-31.

DOI: 10.1016/s0167-7012(00)00201-3

[7] Jia J.C. and Chong C.C. Distributed normalisation input coding to speed up training process of BP-neural network classifier. Electronics Letters, 1995, vol. 31, no. 15, pp.1267-1269.

DOI: 10.1049/el:19950854

[8] P. Patrick and V. D. Smagt. Minimization method for training feedforward neural networks. Neural Networks, 1994, pp.1-11.

DOI: 10.1016/0893-6080(94)90052-3