Journal of Intelligent Manufacturing

, Volume 30, Issue 2, pp 727–741 | Cite as

Applying the support vector machine with optimal parameter design into an automatic inspection system for classifying micro-defects on surfaces of light-emitting diode chips

  • Chung-Feng Jeffrey KuoEmail author
  • Chun-Ping Tung
  • Wei-Han Weng


This study discusses the optimal design of an automatic inspection system for processing light-emitting diode (LED) chips. Based on support vector machine (SVM) with optimal theory, the classifications of micro-defects in light area and electrode area on the chip surface, and develop a robust classification module will be analyzed. In order to design the SVM-based defect classification system effectively, the multiple quality characteristics parameter design. The Taguchi method is used to improve the classifier design, and meanwhile, PCA is used for analysis of multiple quality characteristics on influence of characteristics on multi-class intelligent classifier, to regularly select effective features, and reduce classification data. Aim to reduce the classification data and dimensions, and with features containing higher score of principal component as decision tree support vector machine classification module training basis, the optimal multi-class support vector machine model was established for subdivision of micro-defects of electrode area and light area. The comparison of traditional binary structure support vector machine and neural network classifier was conducted. The overall recognition rate of the inspection system herein was more than 96%, and the classification speed for 500 micro-defects was only 3 s. It is clear that we have effectively established an inspection process, which is highly effective even under disturbance. The process can realize the subdivision of micro-defects, and with quick classification, high accuracy, and high stability. It is applicable to precise LED detection and can be used for accurate inspection of LED of mass production effectively to replace visual inspection, economizing on labor cost.


Taguchi methods Principal component analysis Decision tree support vector machine Multi-class support vector machine model 



The research was supported by the Ministry of Science & Technology of the Republic of China under the Grant No. MOST 104-2221-E-011-156.


  1. Azadeh, O., & Nasser, S. (2011). An efficient hybrid algorithm for multi-class support vector machines. In: International conference on computer science and information technology June 10–12 (pp. 24–28). Chengdu, China.Google Scholar
  2. Chang, C. C., & Lin, C. J. (2012). LIBSVM: A library for support vector machines. ACM Transactions on Intelligent Systems and Technology, 2, 27:1–27:27. (2011).Google Scholar
  3. Chang, C. Y., Chang, C. H., Li, C. H., & Jeng, M. D. (2008). Learning vector quantization neural networks for LED wafer defect inspection. International Journal of Innovative Computing, Information and Control, 4(10), 2565–2579.Google Scholar
  4. Chang, F., Guo, C. Y., Lin, X. R., & Lu, C. J. (2010). Tree decomposition for large-scale SVM problems. Journal of Machine Learning Research, 11, 2855–2892.Google Scholar
  5. Fang, Y. C., Tzeng, Y. F., & Wu, K. Y. (2014). A study of integrated optical design and optimization for LED backlight module with prism patterns. Journal of Display Technology, 10(10), 812–818.Google Scholar
  6. Jair, C., Farid, G. L., Asdrúbal, L. C., Lisbeth, R. M., & Sergio, J. R. (2015). Data selection based on decision tree for SVM classification on large data sets. Applied Soft Computing, 37, 787–798.CrossRefGoogle Scholar
  7. Karimi, M. H., & Asemani, D. (2014). Surface defect detection in tiling industries using digital image processing methods: Analysis and evaluation. ISA Transactions, 53, 834–844.CrossRefGoogle Scholar
  8. Kuhn, H. W., & Tucker, A. W. (1951). Nonlinear programming. In Proceedings of 2nd Berkeley symposium (pp. 481–492). Berkeley: University of California Press.Google Scholar
  9. Kuo, C. F., Hsu, C. T., Liu, Z. X., & Wu, H. C. (2014). Automatic inspection system of LED chip using two-stages back-propagation neural network. Journal of Intelligent Manufacturing, 25, 1235–1243.Google Scholar
  10. Lin, H. D. (2009). Automated defect inspection of light-emitting diode chips using neural network and statistical approaches. Expert Systems With Applications, 36(1), 219–226.CrossRefGoogle Scholar
  11. Modi, S., Lin, Y., Cheng, L., Yang, G., Liu, L., & Zhang, W. (2011). A socially inspired framework for human state inference using expert opinion integration. IEEE ASME Transactions on Mechatronics, 16(5), 874–878.CrossRefGoogle Scholar
  12. Mulay, S. A., Devale, P. R., & Garje, G. V. (2010). Decision tree based support vector machine for intrusion detection. In IEEE international conference on networking and information technology (pp. 59–63).Google Scholar
  13. Nandi, G., Datta, S., Bandyopadhyay, A., & Pal, P. K. (2009). Application of PCA-based hybrid Taguchi method for correlated multicriteria optimization of submerged arc weld: A case study. International Journal of Advanced Manufacturing Technology, 45(3–4), 276–286.Google Scholar
  14. Pan, Z. L., & Chen, L. (2012). Defect inspection of LED chips using generalized regression neural network. Solid State Phenomena, 181–182, 212–215.Google Scholar
  15. Quinlan, J. R. (1993). C4.5: Programs for machine learning. San Mateo, CA: Morgan Kaufmann.Google Scholar
  16. Ross, P. J. (1996). Taguchi techniques for quality engineering. New York: McGraw-Hill.Google Scholar
  17. Song, X., Xiaojun, J., Songlin, S., & Hai, H. (2014). Binary decision tree based multiclass support vector machines. In International symposium on communications and information technologies. September 24–26 (pp. 85–89). Incheon, Songdo.Google Scholar
  18. Tan, S. C., Junzo, W., Zuwairie, I., & Marzuki, K. (2015). Evolutionary fuzzy ARTMAP neural networks for classification of semiconductor defects. IEEE Transactions on Neural Networks and Learning Systems, 26(5), 933–950.CrossRefGoogle Scholar
  19. Vapnik, V. N. (1998). Statistical learning theory. New York: Wiley.Google Scholar
  20. Vapnyarskii, I. B. (2001). Lagrange multipliers. Encyclopedia of mathematics. Hazewinkel: Springer.Google Scholar
  21. Xu, Z. H., Wang, S. C., Zhang, Z. W., Chin, T. S., & Sung, C. K. (2015). Optimization of magnetizing parameters for multipole magnetic scales using the Taguchi method. IEEE Transactions on Magnetics, 51(11), 1–4.Google Scholar
  22. Yingjie, Y., De, X., Xingang, W., & Mingran, B. (2015). Online state-based structured SVM combined with incremental PCA for robust visual tracking. IEEE Transactions on Cybernetics, 45(9), 1988–2000.CrossRefGoogle Scholar
  23. Zhong, F., He, S., Li, B., & Chen, M. S. (2015). Blob analyzation-based template matching algorithm for LED. Internal Journal of Advanced Technology,. doi: 10.1007/s00170-015-7638-5.CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media New York 2016

Authors and Affiliations

  • Chung-Feng Jeffrey Kuo
    • 1
    Email author
  • Chun-Ping Tung
    • 2
  • Wei-Han Weng
    • 1
  1. 1.Department of Materials Science and EngineeringNational Taiwan University of Science and TechnologyTaipeiTaiwan, ROC
  2. 2.Graduate Institute of Automation and ControlNational Taiwan University of Science and TechnologyTaipeiTaiwan, ROC

Personalised recommendations