Wafer defect inspection by neural analysis of region features

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.

[1]  Huan Liu,et al.  Feature Selection for Classification , 1997, Intell. Data Anal..

[2]  H. Weisberg.  Central tendency and variability , 1991 .

[3]  Anil K. Jain,et al.  Face Detection in Color Images , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Jose A. Ventura,et al.  A neural network approach for defect identification and classification on leather fabric , 2000, J. Intell. Manuf..

[5]  Cheng-Lung Huang,et al.  Data Mining using Genetic Programming for Construction of a Semiconductor Manufacturing Yield Rate Prediction System , 2006, J. Intell. Manuf..

[6]  MuDer Jeng,et al.  An unsupervised neural network approach for automatic semiconductor wafer defect inspection , 2009, Expert Syst. Appl..

[7]  Taho Yang,et al.  A neural-network approach for semiconductor wafer post-sawing inspection , 2002 .

[8]  Ching-Yuen Chan,et al.  A particle swarm optimization approach for components placement inspection on printed circuit boards , 2009 .

[9]  M.-J.J. Wang,et al.  Evaluating the eye fatigue problem in wafer inspection , 2004, IEEE Transactions on Semiconductor Manufacturing.

[10]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[11]  Chuan-Yu Chang,et al.  A contextual-based Hopfield neural network for medical image edge detection , 2004, 2004 IEEE International Conference on Multimedia and Expo (ICME) (IEEE Cat. No.04TH8763).

[12]  Kenneth W. Tobin,et al.  Integrated applications of inspection data in the semiconductor manufacturing environment , 2001, SPIE LASE.

[13]  Manuel G. Penedo,et al.  Computer-aided diagnosis: a neural-network-based approach to lung nodule detection , 1998, IEEE Transactions on Medical Imaging.

[14]  Madan M. Gupta,et al.  Radial Basis Function Neural Networks , 2003 .

[15]  Mao-Jiun J. Wang,et al.  The development of an automatic post-sawing inspection system using computer vision techniques , 1999 .

[16]  Paul Wintz,et al.  Digital image processing (2nd ed.) , 1987 .

[17]  Euiyoung Cha,et al.  Face Detection in Color Image , 2003 .

[18]  Fernando Torres Medina,et al.  Automatic inspection for phase-shift reflection defects in aluminum web production , 2002, J. Intell. Manuf..

[19]  Eam Khwang Teoh,et al.  Computer based wafer inspection system , 1991, Proceedings IECON '91: 1991 International Conference on Industrial Electronics, Control and Instrumentation.