Title :
A connectionist classifier architecture applied to image segmentation
Author :
Blanz, W.E. ; Gish, Sheri L.
Author_Institution :
IBM Almaden Res. Center, San Jose, CA, USA
Abstract :
A connectionist classifier architecture that is used in an image segmentation scheme based upon a decision analysis paradigm is described. An appropriate architecture for a connectionist classifier is discussed, and its relationship to other image segmentation architectures following the same paradigm is shown. The performance of a complete system, including pixel descriptor extraction and connectionist classifier, is demonstrated using scenes from industrial inspection and combustion chamber research tasks
Keywords :
computerised pattern recognition; computerised picture processing; parallel architectures; combustion chamber; connectionist classifier architecture; decision analysis paradigm; image segmentation; industrial inspection; pixel descriptor extraction; Convolution; Image analysis; Image segmentation; Information analysis; Layout; Multi-layer neural network; Pixel; Real time systems; Table lookup; Training data;
Conference_Titel :
Pattern Recognition, 1990. Proceedings., 10th International Conference on
Conference_Location :
Atlantic City, NJ
Print_ISBN :
0-8186-2062-5
DOI :
10.1109/ICPR.1990.119369
