Visual Learning: An Overview
Abstract
A review is presented of modern approaches to the learning and recognition of complex patterns, including discriminant functions, neural networks, decision trees, and hidden Markov models. Next, several relational learning systems are introduced and discussed, in detail one specific technique, conditional rule generation. This technique is shown to be very flexible and useful for the learning of static patterns, such as objects, as well as dynamic patterns, such as movement patterns. The technique is illustrated with a number of very difficult visual learning problems.
References
Bischof, W. F. , Caelli, T. (1994). Learning structural descriptions of patterns: A new technique for conditional clustering and rule generation. Pattern Recognition, 27, 689– 697Bischof, W. F. , Caelli, T. (1997a). Visual learning of Patterns and objects. IEEE Transactions on Man, Machine, and Cybernetics, 27, 907– 917Bischof, W. F. , Caelli, T. (1997b). Scene understanding by rule evaluation. IEEE Transactions on Pattern Analysis and Machine Intelligence, 19, 1284– 1288Bischof, W. F. , Caelli, T. (2000). Learning complex action patterns with CRGst. In S. Singh, N. Murshed, & W. Kropatsch (Eds.), Advances in Pattern Recognition - IACPR 2001(pp. 280-289). Berlin: SpringerBischof, W. F. , Caelli, T. (2001). Learning spatio-temporal relational structures. Journal of Applied Intelligence, 15, 707– 722Briscoe, G. , Caelli, T. (1996). A Compendium of Machine Learning. Norwood, NJ: AblexBunke, H. , Caelli, T. Eds. (2001). Hidden Markov Models: Applications in computer vision. Singapore: World ScientificCaelli, T. , Bischof, W. F. Eds. (1997). Machine learning and image interpretation. New York: PlenumCaelli, T. , Dreier, A. (1994). Variations on the evidence-based object recognition theme. Pattern Recognition, 27, 185– 204Devijver, P. A. , Kittler, J. (1980). Pattern recognition: A statistical approach. Englewood Cliffs, NJ: Prentice-HallDuda, R. , Hart, P. , Stork, D. (2001). Pattern Classification. New York: WileyFlynn, P. , Jain, A. (1993). Handbook of pattern recognition and image processing. New York: AcademicHertz, J. , Krogh, A. , Palmer, R. (1991). Introduction to the theory of neural computation. Redwood City, CA: Addison-WesleyJain, A. , Dubes, R. (1988). Algorithms for clustering data. Englewood Cliffs, NJ: Prentice-HallMcCane, B. , Caelli, T. (1997). Fuzzy conditional rule generation for the learning and recognition of 3D objects from 2D images. In T. Celli & W. F. Bischof (Eds.), Machine learning and image interpretation. Advances in computer vision and machine intelligence(pp. 17-65). New York: PlenumMitchell, T. (1997). Machine Learning. New York: McGraw-HillPao, Y. (1989). Adaptive pattern recognition and neural networks. Reading, MA: Addison-WesleyQuinlan, R. (1992). C4.5: Programs for machine learning. San Mateo, CA: Morgan KaufmannRabiner, L. , Juang, B.-H. (1993). Fundamentals of speech recognition. chapter 6 Englewood Cliffs, NJ: Prentice-HallRosenfeld, A. , Kak, A. (1982). Digital picture processing. 2nd ed New York: AcademicShapiro, L. , Haralick, R. (1981). Structural descriptions and inexact matching. IEEE Transactions on Pattern Analysis and Machine Intelligence, 3, 501– 519