Abstract
This study proposed an automatic LED defect detection system to investigate the defects of LED chips. Such defects include fragment chips, scratch marks and remained gold on the pad area, scratch marks on the luminous zone, and missing luminous zone respectively. The system was based on positioning and image acquisition, appearance feature recognition, and defect classification. The normalized correlation coefficient method was used to locate the chip and acquire its image, the K-means clustering method was used to distinguish the appearance, pad area, and luminous zone of chips. In terms of pad area detection, histogram equalization was used to enhance the pad image contrast, and statistical threshold selection and morphological closing were applied to modify the impure points in the pad. Feature values of the pad area were then calculated. The optimal statistical threshold separated the luminous zone and background from the substrate. After processed with closing operation, features of the luminous zone were extracted. Finally, features of each part were clarified by an efficient two-step back-propagation neural network, where a designed appearance classifier and an internal structure classifier were used for recognition. From experiments, total recognition rate of this study achieved 97.83 %, proving that the detection method proposed by this study can efficiently detect LED chip defects.
Similar content being viewed by others
References
Balfour, C., Smith, J. S., & Amin-Nejad, S. (2004). Feature correlation for weld image-processing applications. International Journal of Production Research, 42(5), 975–995.
Chang, C. Y., Chang, C. H., Li, C. H. & Jeng, M. D., (2007). Learning vector quantization neural networks for LED wafer defect inspection. IEEE Digital Object Identifier, 230–230.
Chiu, H. J., & Cheng, S. J. (2007). LED backlight driving system for large-scale LCD panels. IEEE Transactions on Industrial Electronics, 54(5), 2751–2760.
Chiu, H. J., Lo, Y. K., Chen, J. T., Cheng, S. J., Lin, C. Y., & Mou, S. C. (2010). A high-efficiency dimmable LED driver for low-power lighting applications. IEEE Transactions on Industrial Electronics, 57(2), 735–743.
Chung, K. L., & Chen, W. Y. (2003). Fast adaptive PNN-based thresholding algorithms. Pattern Recognition, 36(12), 2793–2804.
Fu, X. Y., Liu, X. J. & Wu, Y., (2009). Research and analysis of the design development and perspective technology for LED lighting products. In IEEE 10th international conference on computer-aided industrial design & Conceptual Design, pp. 1330–1334.
Huang, R. T., Holm, P., & Wright, P. D. (1998). Design and fabrication of AlGaInP LED array with integrated GaAs decode circuit. IEEE Transactions on Electron Devices, 45(18), 2283–2290.
Huang, C. J., Wu, C. F., & Wang, C. C. (2002). Image processing techniques for Wafer defect cluster identification. IEEE Design & Test of Computers, 19(2), 44–48.
Jain, A. K., & Dubes, R. C. (1988). Algorithms for clustering data. New Jersey: Prentice Hall.
Kai, B., & Uwe, D. H. (2001). Template matching using fast normalized cross correlation. Proceedings of SPIE—The International Society for Optical Engineering, 4387, 95–102.
Keränen, K., Heikkinen, M., Hiltunen, M., Lahti, M., Mäkinen, J.T., Sunnari, A., Rekilä, J. & Rönkä K., (2010). Backlight illumination structure based on inorganic LED devices and laminated multilayer polymer substrate. In IEEE 3rd Electronic System—Integration Technology Conference (ESTC), pp. 1–4.
Ko, S. J., & Lee, Y. H. (1991). Center weighted median filters and their applications to image enhancement. IEEE Transactions On Circuits and Systems for Video Technology, 39(9), 984–993.
Liao, Y. Y. (2008). Apply machine vision technology to defect inspection of high brightness light emitting diode. National Taiwan University of Science and Technology.
Lin, H. D., & Jiang, J. D. (2007). Applying discrete cosine transform and grey relational analysis to surface defect detection of LEDs. Journal of the Chinese Institute of Industrial Engineers, 24(6), 458–467.
Liu, T., Wang, Y., Yang, F. B., & Yu, J. (2009). Designing of LED illuminating system and testing notice. IEEE International Conference on Information Engineering, 2, 277–280.
Lo, Y. K., Wu, K. H., Pai, K. J., & Chiu, H. J. (2009). Design and implementation of RGB LED drivers for LCD backlight modules. IEEE Transactions on Industrial Electronics, 56(12), 4862–4871.
Miyawaki, Y., Wang, D. X., Tanaka, O., Oyama, N. & Okuno, A., (2007). Unique transparent resin and vacuum printing encapsulation systems (VPES) packaging method for new white LED. In IEEE 6th international conference on polymers and adhesives in microelectronics and photonics, pp. 81–86.
Okuno, A., Miyawaki, Y., Oyama, N. & Wang, D. X., (2006). Unique white LED packaging systems. IEEE international conference on electronic materials and packaging, pp. 1–5.
Otsu, N. (1979). A threshold selection method from gray-level histograms. IEEE Transactions on System, Man and Cybernetics, 9(1), 62–66.
Tsai, D. M., & Lin, C. T. (2003). Fast normalized cross correlation for defect detection. Pattern Recognition Letters, 24, 2625–2631.
Ward, G. (2003). Fast robust image registration for compositing high dynamic range photographs from handheld exposure. Journal of Graphics Tools, 8(2), 17–30.
Windyge, P. S. (2001). Fast impulsive noise removal. IEEE Transactions on Image Processing, 10(1), 173–179.
Wu, B. L., Luo, X. B. & Liu, S., (2010). Effect mechanism of moisture diffusion on LED reliability. In IEEE 3rd electronic system-integration technology conference (ESTC), 1–5.
Ying, S. P., Tang, C. W. & Huang, B. J., (2006). Characterizing LEDs for mixture of colored LED light sources. In IEEE International Conference on Electronic Materials and Packaging, pp. 1–5.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Kuo, CF.J., Hsu, CT.M., Liu, ZX. et al. Automatic inspection system of LED chip using two-stages back-propagation neural network. J Intell Manuf 25, 1235–1243 (2014). https://doi.org/10.1007/s10845-012-0725-7
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10845-012-0725-7