Wafer defect inspection by neural analysis of region features
- 248 Downloads
Wafer defect inspection is an important process that is performed before die packaging. Conventional wafer inspections are usually performed using human visual judgment. A large number of people visually inspect wafers and hand-mark the defective regions. This requires considerable personnel resources and misjudgment may be introduced due to human fatigue. In order to overcome these shortcomings, this study develops an automatic inspection system that can recognize defective LED dies. An artificial neural network is adopted in the inspection. Actual data obtained from a semiconductor manufacturing company in Taiwan were used in the experiments. The results show that the proposed approach successfully identified the defective dies on LED wafers. Personnel costs and misjudgment due to human fatigue can be reduced using the proposed approach.
KeywordsRBF neural network Wafer defect detection
Unable to display preview. Download preview PDF.
- Gonzalez, R. C., & Woods, R. E. (2002). Order-statistic filters. In Digital image processing (2nd ed., pp. 123–124). Prentice Hall.Google Scholar
- Ham, F. M., & Kostanic, I. (2001a). Radial basis function neural networks. In Principles of neurocomputing for science and engineering (Int. ed., pp. 140–152). McGraw-Hill Book Co.Google Scholar
- Ham, F. M., & Kostanic, I. (2001b). Self-organizing map and LVQ. In Principles of neurocomputing for science and engineering (Int. ed., pp. 180–182). McGraw-Hill Book Co.Google Scholar
- Mital D. P., Teoh E. K. (1991) Computer based wafer inspection system. Proceedings. IECON ‘91 3(28): 2497–2503Google Scholar
- Shapiro, L. G., & Stockman, G. C. (2001). Connecting component labeling. In Computer vision (pp. 56–63). Upper Saddle River, New Jersey: Prentice Hall.Google Scholar
- Weisberg H. F. et al (1993) Central tendency and variability. In: Lewis-Beck M. S. (eds) Basic statistics 1. Sage Publication, California, pp 1–88Google Scholar