FAST SEARCH ALGORITHMS FOR INDUSTRIAL INSPECTION

作者: MING-CHING CHANG , CHIOU-SHANN FUH , HSIEN-YEI CHEN

DOI: 10.1142/S0218001401001039

关键词:

摘要: This paper presents an efficient general purpose search algorithm for alignment and applied procedure IC print mark quality inspection. The is based on normalized cross-correlation enhances it with a hierarchical resolution pyramid, dynamic programming, pixel over-sampling to achieve subpixel accuracy one or more targets. robust respect linear change of image intensity thus can be industrial visual Accuracy, speed, reliability, repeatability are all critical the use. After proper optimization, proposed was tested inspection platforms in Mechanical Industry Research Laboratories (MIRL), Industrial Technology Institute (ITRI), Taiwan. method meets these criteria has worked well field tests various products.

参考文章(6)
Changming Sun, A Fast Stereo Matching Method ,(1997)
D.P. Mital, Teoh Eam Khwang, An intelligent vision system for inspection of packaged ICs ieee region 10 conference. pp. 1003- 1006 ,(1989) , 10.1109/TENCON.1989.177100
M.J. McDonnell, Box-filtering techniques Computer Graphics and Image Processing. ,vol. 17, pp. 65- 70 ,(1981) , 10.1016/S0146-664X(81)80009-3
B. Pudipeddi, A.L. Abbott, P.M. Athanas, Real-time hierarchical visual tracking using a configurable computing machine international workshop on computer architecture for machine perception. pp. 153- 157 ,(1997) , 10.1109/CAMP.1997.631931
Daniel I. Barnea, Harvey F. Silverman, A Class of Algorithms for Fast Digital Image Registration IEEE Transactions on Computers. ,vol. C-21, pp. 179- 186 ,(1972) , 10.1109/TC.1972.5008923
Ming-Ching Chang, Chiou-Shann Fuh, Hsien-Yei Chen, Fast Search Algorithms for IC Printed Mark Quality Inspection1 Journal of Machine Vision and Applications. pp. 183- 188 ,(1998)