Neural Networks and Robot Vision
- 118 Downloads
Traditionally robot vision and robot control applications are written in imperative languages, such as Fortran, Pascal, Modula or C. Since the development of Artificial Intelligence techniques, specialized robot languages emerged. The upper layers of robot languages are: programmed in declarative languages, such as Lisp and Prolog. Recently, neural computing has become a third exciting programming alternative which complements the other programming styles. Neural programming paradigms apply to both robot vision and robot control. In this chapter the basic neural network techniques applicable to robot vision are explored. Among these are pattern recognition, blurred image restoration and unsupervised classification. It is likely that a judicious blend of these techniques will be used in complex scene analysis. Neural networks are characterized by an interconnection structure and a learning rule. These offer a wealth of combinations for each particular application. Therefore the major neural network models are analyzed and compared.
KeywordsInput Pattern Hide Unit Input Unit Linear Network Target Pattern
Unable to display preview. Download preview PDF.
- Hartmann, G. (1988) Mapping Images to a Hierarchical Data Structure — a Way to Knowledge-Based Pattern Recognition, Neural Computers, Rolf Eckrniller and Christoph v.d. Malsburg (Editors), NATO ASI Series, pp. 91–100.Google Scholar
- Hinton, G.E. and Sejnowski, T.J. (1986) Learning and Relearning in Boltzmann Machines, Parallel Distributed Processing, Vol. 1: Foundations, D.E. Rumelhart, J.L. McClelland and the PDP research group, Chapter 7, pp. 182–317.Google Scholar
- Hinton, G.E. and Sejnowski, T.J. (1983) Optimal Perceptual Inference, Proc. IEEE Conf. on Computer Vision and Pattern Recognition, pp. 448–453.Google Scholar
- McClelland, J.L. (1986) Resource Requirements of Standard and Programmable Nets, Parallel Distributed Processing, Vol. 1: Foundations, D.E. Rumelhart, J.L. McClelland and the PDP research group, pp. 461–487.Google Scholar
- McClelland, J.L. and Rumelhart, D.E. (1988) Explorations in Parallel Distributed Processing, A Handbook of Models, Programs and Exercises, The MIT Press.Google Scholar
- Myake S., Kawato M., Sonohara N., Hongo S., Inui T. (1989) em Applications in Image Processing and Pattern Recognition, Flanders Technology Seminar on Neural Networks, April, 9 pp.Google Scholar
- Minsky, M. and Papert, S. (1969) Perceptrons, MIT Press.Google Scholar
- Rumelhart, D.E. and Zipser, D. (1986) Feature Discovery by Competitive Learning, Parallel Distributed Processing, Vol. 1: Foundations, D.E. Rumelhart, J.L. McClelland and the PDP research group, Chapter 5, pp. 151–193.Google Scholar
- Rumelhart D.E., Smolensky R., McClelland J.L., Hinton G.E. (1986) Schemata and Sequential Thought Processes in PDP models, Parallel Distributed Processing, Vol. 2: Psychological and Biological Models, D.E. Rumelhart, J.L. McClelland and the PDP research group, Chapter 14, pp. 7–57.Google Scholar
- Smolensky, P. (1986) Information Processing in Dynamical Systems, Parallel Distributed Processing, Vol. 1: Foundations, D.E. Rumelhart, J.L. McClelland and the PDP research group, Chapter 6, pp. 194–281.Google Scholar