Abstract
In the manufacturing industry, there is a growing need for an adaptable automated visual inspection (AVI) system that can be used to perform different inspection tasks without excessive retuning or retraining efforts. This paper presents an automated visual inspection scheme to improve the adaptability of an AVI system. In doing so, we propose the design of an adaptable inspection model composed of two sub-models: one for localizing the region of useful features and the other for defect classification. The localization sub-model contains invariant features common to all inspection samples. Through an edge-based geometric template-matching process, the localization sub-model is used to locate a verification region containing the subject of inspection such as a clip or a screw in an assembly piece. Through principal component analysis (PCA), the verification sub-model is constructed based on the reconstruction error distribution of non-defective samples. Consequently, this sub-model can be used to identify defective samples. In addition, an efficient online training algorithm is proposed for the construction of the verification sub-model during system operation. This algorithm allows minimum manual inspection effort while ensuring model training sufficiency. Through case study, the proposed AVI scheme demonstrates its capability of self-tuning while inspecting different parts or under different operating conditions in an assembly process. The feature of adaptability will help increase the benefit and functionality of an AVI technique to the manufacturing industry.
Similar content being viewed by others
References
Newman S, Jian AK (1995) A survey of automated visual inspection. Comp Vision Image Understanding 61(2):231–262
Abramovich G, Weng J, Dutta D (2005) Adaptive part inspection through developmental vision, ASME. J Manuf Sci Eng 127:1–11
Garcia HC, Rene-Villalobos J, Runger GC (2006) An automated feature selection method for visual inspection systems. IEEE Trans Auto Eng 3(4):394–406
Chin RT, Harlow CA (1982) Automated visual inspection: survey. IEEE Trans Pat Anal Mach Intel, PAMI 4(6):557–573
Wallace AM (1988) Industrial applications of computer vision since 1982. IEE Proc E Comp Digital Technol 135(3):117–136
Malamas EN, Petrakis EGE, Zervakis M, Petit L, Legat J-D (2003) A survey on industrial vision systems, application and tools. Image Vision Comp 21(2):171–188
Sablatnig R (2000) Increasing flexibility for automatic visual inspection: the general analysis graph. Mach Vis Appl 12:158–169
Bayro-Corrochano E (1993) Review of automated visual inspection 1983–1993 part I: conventional approaches, SPIE 2055. Intelligent Robots and Comp Vision XII:128–158
Bayro-Corrochano E (1993) Review of automated visual inspection 1983–1993 part II: approaches to intelligent systems, SPIE 2055. Intel Robots Comp Vision XII:159–172
McAulay AD, Danset P, Wicker D (1990) Neural network system for manufacturing assembly line inspection. Proc IEEE Natl Aero Elect Conf 3:1160–1170
Beck H, McDonald D, Brzakovic D (1989) A self-training visual inspection system with a neural network classifier. Proc of Int Joint Conf on Neural Networks I:307–311
Cho T, Conners RW (1991) A neural network approach to machine vision systems for automated industrial inspection. Proc Int Joint Conf Neural Networks I:205–208
Su JC, Tarng YS (2006) Automated visual inspection for surface appearance defects of Varistors using an adaptive neuron-fuzzy inference system. Int J Adv Manuf Tech 35:789–802
Piccardi M, Cucchiara R, Bariani M, Mello P (1997) Exploiting symbolic learning in visual inspection. Lecture Notes in Comp Sci, Springer-Verlag 1280:223–236
Zheng H, Kong LH, Nahavandi S (2002) Automatic inspection of metallic surface defects using genetic algorithms. J Mater Process Tech 125–126:427–433
Kumar A (2003) Neural network based detection of local textile defects. Pattern Recog 36:1645–1659
Hata S, Matsukubo T, Shigeyama Y, Nakamura A (2004) Neural network visual system with human collaborated learning system. Proc IEEE Int Conf Indust Tech 1:214–128
Pham DT, Bayro-Corrochano EJ (1994) Neural classifiers for automated visual inspection. Proc Inst of Mech Eng 208:83–89
Weng J (2007) Incremental hierarchical discriminant regression. IEEE Trans Neural Networks 18(2):397–415
Jia H, Murphey YL, Shi J, Chang T (2004) An intelligent real-time vision system for surface defect detection. Proc 17th Int Conf Pat Recog (ICPR’04) 3:239–242
Pu Y, Liao K, Zhou J, Zhang N (2004) An adaptive inspection method for industrial welding seam based on PCA algorithm and the modification of BP ANN. Proc 2004 IEEE Int Conf Mach Learning Cybernet 6:3412–3416
Tanaka, M. and Okutomi, M., 2008, "Locally adaptive learning for translation-variant mrf image priors", IEEE Conf. Computer Vision and Pattern Recognition, Anchorage, USA, June 23–28, pp. 1–8
Matrox Imaging Inc., 2005, Matrox Imaging Library 8: User Guide, ch. 8
Turk M, Pentland A (1991) Eigenface for recognition. J Cognitive Neurosci 3(1):71–861
Vieira Neto, H. and Nehmzow, U., 2005, “Incremental PCA: an alternative approach for novelty detection,” Proc. Conf. Towards Autonomous Robotic Systems (TAROS), pp. 227–233.
Artac M, Jogan M, Leonardis A (2002) Incremental PCA for online visual learning and recognition. Proc 16th Intl Conf Pat Recog 3:30781–30885
Jackson JE, Mudholkar GS (1997) Control procedures for residuals associated with principle component analysis. Technometrics 21(3):341–349
Jensen DR, Solomon H (1972) A Gaussian approximation for the distribution of definite quadratic forms. J Am Stat Assoc 67:898–902
Sculley D., 2007, “Online active learning methods for fast label-efficient spam filtering,” in Proc. 4th Conf. Email and Anti-Spam
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Sun, J., Sun, Q. & Surgenor, B.W. An adaptable automated visual inspection scheme through online learning. Int J Adv Manuf Technol 59, 655–667 (2012). https://doi.org/10.1007/s00170-011-3524-y
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00170-011-3524-y