Fast Search Algorithms for IC Printed Mark Quality Inspection

This paper presents an effective and general purpose search algorithm for alignment, and we applied it to IC printed mark quality inspection. The search procedure is based on normalized cross correlation, and we improve the method with hierarchical resolution pyramid, dynamic programming, subpixel accuracy, multiple target search, and automatic model selection. The proposed search method can be applied to general visual inspection. The IC printed mark includes a logo pattern and characters. Due to the alignment error of the inspection machine, the mark can be rotated or translated. Main printing error of an IC mark is shown in Figure 1 PI. We develop the teaching and inspection function, optimize the system, and test it on an IC inspection machine. Our algorithm achieves high accuracy, reliability, and repeatability with high speed for industrial requirement and works well on field test of various IC products. 'Department of Computer Science and Information Engineering, National Taiwan University, Taipei, Taiwan. E-mail: derekQrobot.csie.ntu.edu.tw t ~ e c h a n i c a l Industry Research Laboratories (MIRL), Industrial Technology Research Inst,itute (ITRI), Hsinchu, Taiwan. E-mail: 770802Qmirl. itri .org.tw t ~ e p a r t m e n t of Computer Scietlce and Information Engineering, National Taiwan University, Taipei, Taiwan. E-mail: fuhQcsie.ntu.edu.tv 'This research work was supported by National Science Council of Taiwan, ROC, under Grants NSC 85-2212-E-002077 and NSC 86-2212-E-002-025, by Mechanical Industry Research Laboratories, Industrial Technology Research Institute under Grant MIRL 863K67BN2, by EeRise Corporation, ACME Systems, Mosel Vitelic, and Foxconn Inc. i l ABC ,234 1 ABC-,234 li Figure 1: Main IC printed mark errors: (a) good, (b) smeared, (c) scraped, (d) double print, (e) broken, (f) missing ink, (g) bad contrast, (h) misprinted, (i) partial bad contrast, and (j) mis-orientation.