Title :
Color analysis by learning subspaces and optical processing
Author :
Parkkinen, Jussi ; Oja, Erkki ; Jääskeläinen, Timo
Author_Institution :
Dept. of Comput. Sci. & Phys., Kuopio Univ., Finland
Abstract :
Most machine vision systems are based on a three-parameter representation for colors. It is argued that in contrast to three-parameter methods, the whole color spectrum should be used for recognition, resulting in improved accuracy. A method of colour representation based on the spectrum is the subspace method, which is capable of accurate color recognition after a learning phase. The subspace method stems from well-known neural-network models for associative memory. A practical parallel realization for the subspace model is an optical one. Different possibilities for optical implementations are discussed, and concrete color classification results are given.<>
Keywords :
content-addressable storage; neural nets; picture processing; spectral analysis; associative memory; color analysis; color representation; computer vision; learning phase; neural-network models; optical processing; parallel realization; subspace learning; subspace method; Associative memories; Image processing; Neural networks; Spectral analysis;
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/ICNN.1988.23955