Neural network for region detection
The paper proposes a neural network organized in three structures , each of which is constituted by a set of levels . The lower structure is made up of two layer groups the first one filters the high frequency noise , while the second one is sensitive to scarcely lighted images . Finally the third structure detects contour and position of regions . The network uses neurons of C , S and V type in analogy to Fukushima Neo-Cognitron . A simulation program has been implemented, which shows good throughput in spite of network complexity.
KeywordsNeo-Cognitron Pre-Processing Filtering Vectorial Quantization
Unable to display preview. Download preview PDF.
- S.Zornetrzer,J.Davis,C.Lau: An Introduction to Neural and Electronic Networks. Academic Press Inc. (1991)Google Scholar
- E.Kandel,J.Schwartz,T.Jessel: Principles of Neural Science. Prentice Hall (1991)Google Scholar
- J.McClelland,D.Rumelhart and the PDP Research Group: Parallel Distributed Processing. Explorations in the microstructure of cognition Vol.2 Psycological and Biological Models. MIT Press (1986)Google Scholar
- Y. Pao: Adaptative Pattern Recognition and Neural etworks Reading (Mass.). Addison Wesley Publishing Co. (1989)Google Scholar
- D.Hubel: Eye, Brain and Vision. Scientific American Library (1988)Google Scholar
- K.Fukushima: Neo-Cognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Transaction on Systems, Man and Cybernetics Vol. 13 N.5 (1983)Google Scholar
- W.K.Pratt: Digital Image Processing, Wiley, New York (1991)Google Scholar