This Article 
 Bibliographic References 
 Add to: 
Automatic Solder Joint Inspection
January 1988 (vol. 10 no. 1)
pp. 31-43

The task of automating the visual inspection of pin-in-hole solder joints is addressed. Two approaches are explored: statistical pattern recognition and expert systems. An objective dimensionality-reduction method is used to enhance the performance of traditional statistical pattern recognition approaches by decorrelating feature data, generating feature weights, and reducing run-time computations. The expert system uses features in a manner more analogous to the visual clues that a human inspector would rely on for classification. Rules using these cues are developed, and a voting scheme is implemented to accumulate classification evidence incrementally. Both methods compared favorably with human inspector performance.

[1] R. T. Chin and C. A. Harlow, "Automated visual inspection: A survey,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-4, pp. 557-573, Nov. 1982.
[2] V. Bunze, "Automated optical inspection: Quality and profit pick-up for PWBs,"Conductor, pp. 2-3, June 1985.
[3] P. J. Besl, E. J. Delp, and R. C. Jain, "Automatic visual solder joint inspection,"IEEE J. Robotics Automation, vol. RA-1, pp. 42-56, Mar. 1985.
[4] IPC Workshop Handbook, "Electronic assembly soldering technology," Inst. Interconnecting and Packaging Electronic Circuits, Evanston, IL, June 1978.
[5] R. W. Woodgate,Handbook of Machine Soldering. New York: Wiley, 1983.
[6] H. H. Manko,Solders and Soldering. New York: McGraw-Hill, 1964.
[7] M. Juha, "Automated inspection of SMD solder connections," IRT Corp. Publ., San Diego, CA, 1985.
[8] F. Murphy, "Automatic optical inspection questions and answers,"IPC Tech. Rev., pp. 13-23, June 1984.
[9] V. C. Bolhouse, "Machine vision applications for high volume electronics manufacturing," inVISION '85 Conf. Proc., Detroit, MI, June 1985, pp. 5-75-5-98.
[10] J. G. Davy, "A comprehensive list of wave solder defects and their probable causes," presented at the 1985 Soldering Technology Seminar, Naval Weapons Center, China Lake, CA.
[11] C. D. Bernard, "Wave soldered solder joint quality troubleshooting guide," IBM Tech. Rep. TR00.2761, pp. 1-18, June 1976.
[12] W. M. Sterling, "Automatic non-reference inspection of printed wiring boards," inProc. IEEE Conf. Pattern Recognition and Image Processing, Aug. 1979, pp. 93-100.
[13] J. F. Jarvis, "A method of automating visual inspection of printed wiring boards,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-2, pp. 77-82, Jan. 1980.
[14] N. Akiyama, Y. Nakagawa,et al., "Recent progress in pattern recognition technology for automated production lines,"Bull. Japan Soc. Proc. Eng., vol. 18, no. 2, pp. 165-170, June 1984.
[15] W. A. Perkins, "Model-based inspection system for component boards,"Pattern Recognition, vol. 17, no. 1, pp. 135-140, 1984.
[16] G. A. W. West, "A system for the automatic visual inspection of bare-printed circuit boards,"IEEE Trans. Syst., Man, Cybern., vol. SMC-14, pp. 767-773, Sept. 1984.
[17] J. L. C. Sanz and A. K. Jain, "Machine-vision techniques for inspection of printed wiring boards and thick-film circuits,"J. Opt. Soc. Amer. A, vol. 3, no. 9, pp. 1465-1482, 1986.
[18] Y. Nakagawa, "Automatic visual inspection of solder joints on printed circuit boards,"Proc. SPIE, vol. 336, pp. 121-127, May 1982.
[19] Y. Nakagawa and T. Ninomiya, "Structured light method for inspection of solder joints and assembly robot vision system," presented at the First Int. Symp. Robotics Res., Bretton Woods, NH, Aug. 28- Sept. 2, 1983.
[20] Y. Nakagawa, Y. Hara, and M. Hashimoto, "Automatic visual inspection using digital image processing,"Hitachi Rev., vol. 34, no. 1, pp. 55-60, 1985.
[21] W. E. McIntosh, "Automating the inspection of printed circuit boards,"Robotics Today, pp. 75-78, June 1983.
[22] R. Vanzetti, A. C. Traub, and J. S. Ele, "Hidden solder joint defects detected by laser infrared system," inProc. IPC 24th Annu. Meeting, Apr. 1981, pp. 1-15.
[23] M. Juha, "The economics of automated x-ray inspection for solder quality," IRT Corp. Publ., San Diego, CA, Feb. 1986.
[24] P. J. Besl, K. D. Skifstad, and R. C. Jain, "Objective dimensionality reduction using out-of-class covariance," Center Res. Integrated Manufacturing (CRIM), Univ. Michigan, Ann Arbor, Tech. Rep. RSD-TR-17-85, Nov. 1985.
[25] A. H. Feivson, "Classification by thresholding,"IEEE Trans. Pattern Anal. Machine Intell., vol. PAMI-5, pp. 48-54, Jan. 1983.
[26] A. Rosenfeldet al., "'Expert' vision systems: Some issues,"Comput. Vision, Graphics, Image Processing, vol. 34, pp. 99-117, 1984.
[27] L. T. Watson, K. Arvind, and R. W. Ehrich, "Extraction of lines and regions from grey tone drawing images,"Pattern Recognition, vol. 17, pp. 493-507, 1984.
[28] A. Ginsberg, "A metalinguistic approach to the construction of knowledge base refinement systems," inProc. AAAI-86, vol. 1, pp. 436-441.
[29] D. C. Wilkins and B. G. Buchanan, "On debugging rule sets when reasoning under uncertainty," inProc. AAAI-86, vol. 1, pp. 448- 454.
[30] R. Dye, "Multivariate categorical analysis--Bendix style," Bendix Corp., Southfield, MI, Tech. Rep. BSR 4149, June 1974.
[31] J. H. Friedman, "A recursive partitioning decision rule for non-parametric classification,"IEEE Trans. Comput., pp. 404-408, Apr. 1977.
[32] K. Fukunaga,Introduction to Statistical Pattern Recognition. New York: Academic, 1972.

Index Terms:
computer vision; automatic joint inspection; PCBs; decorrelation; pin-in-hole solder joints; statistical pattern recognition; expert systems; objective dimensionality-reduction method; feature data; feature weights; voting scheme; classification evidence; computer vision; computerised pattern recognition; electronic engineering computing; expert systems; inspection; printed circuit testing
S.L. Bartlett, P.J. Besl, C.L. Cole, R. Jain, D. Mukherjee, K.D. Skifstad, "Automatic Solder Joint Inspection," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 10, no. 1, pp. 31-43, Jan. 1988, doi:10.1109/34.3865
Usage of this product signifies your acceptance of the Terms of Use.