[KSCI] Korea Science Citation Index Service

Development and Characterization of Pattern Recognition Algorithm for Defects in Semiconductor Packages

Kim, Jae-Yeol (Department of mechatronics engineering, Chosun University)
Yoon, Sung-Un (Department of mechanical engineering, Chosun University)
Kim, Chang-Hyun (Department of precision mechanical engineering, Graduate school, Chosun University)

Publication Information

International Journal of Precision Engineering and Manufacturing / v.5, no.3, 2004 , pp. 11-18 More about this Journal

Abstract

In this paper, the classification of artificial defects in semiconductor packages is studied by using pattern recognition technology. For this purpose, the pattern recognition algorithm includes the user made MATLAB code. And preprocess is made of the image process and self-organizing map, which is the input of the back-propagation neural network and the dimensionality reduction method, The image process steps are data acquisition, equalization, binary and edge detection. Image process and self-organizing map are compared to the preprocess method. Also the pattern recognition technology is applied to classify two kinds of defects in semiconductor packages: cracks and delaminations.

Keywords

Ultrasonic image; Defects in semiconductor package; Image process; Neural network; Pattern recognition;

Citations & Related Records

Reference

1	Kim, Jae-Yeol, 'A Study on the Image Processing of Micro-defects Detection of Semiconductor Package by Ultrasonic Wave,' Ph. D thesis, Hanyang University, 1990
2	Kohonen, T., 'The self-organizing map,' Proceedings of the IEEE, Vol. 78, pp. 1464 - 1480, 1990 DOI ScienceOn
3	Kim, J. Y. and Hong, W. and Han, J. H., 'A Study on the Detection of Interfacial Defect to Boundary Surface in Semiconductor Packages by Ultrasonic Signal Processing,' Journal of KSNT, Vol. 19, No. 5, pp. 369 - 377, 1999
4	Choi, M. Y. and Park, I. G. and Han, E. K., 'Measurement of Defects with Scanning Acoustic Microscope and Acoustic Emission,' Journal of the KSPE, Vol. 8, No. 4, pp. 118 - 125, 1991
5	Tompson, R. B., 'Quantitative Ultrasonic Non-destructive Evaluation Methods,' Journal of Applied Mechanics, Vol. 50, pp. 1991 - 1201, 1983
6	Master, Timothy, 'Signal and Image Processing with Neural Networks,' John Wiley & Sons, 1994.
7	Hall, E. L., 'A Survey of Preprocessing and Feature Extraction Techniques for Radiographic Image,' IEEE Transaction on Computation, Vol. C-20, No. 9, pp. 1032 - 1044, 1971 DOI ScienceOn
8	Lawrence, C. Steve, and Lee, Giles and Tsoi, Ah Chung and Back, D. Andrew, 'Face Recognition: A Convolutional Neural Network Approach,' IEEE Transaction on Neural Network, Special Issue on Neural Network and Pattern Recognition, Vol. 8, No. 1, pp. 98 - 113, 1997
9	Jhang, K. Y. and Jang, H. S. and Park, P. Y., 'Separation of Superimposed Pulse-Echo Signal for Improvement of Resolution of Scanning Acoustic Microscope,' Journal of the KSPE, Vol. 17, No. 7, pp. 217 - 225, 2000
10	Otsu, Nobuyuki, 'A Threshold Selection Method from Gray-Level Histograms,' IEEE Transaction on Systems, Men, and Cybernetics, Vol. SMC-9, No. 1, pp. 41 - 47, 1986
11	Sim, J. H. and Kweon, H. J. and Paik, I. H., 'Identification of the Chip Form Using Neural Network,' Journal of the KSPE, Vol. 15, No. 12, pp. 517 - 112, 1998