This paper presents multispectral space image classification using the new neural model, called Concurrent Self-Organizing Maps (CSOM), representing a winner-takes-all collection of small modular self-organizing neural networks. The performance of this classifier is compared with the performance of Bayesian classifiers. The implemented neural/statistical classifiers are evaluated using a LANDSAT TM image with 7 bands composed by a set of 7-dimensional pixels, a subset of which contains labelled pixels corresponding to 7 thematic categories. The best experimental result leads to a recognition rate of 95.29%. The model has potential applications for harbour protection.
A New Neural Approach for Pattern Recognition in Space Imagery
2009-01-01
7 pages
Article/Chapter (Book)
Electronic Resource
English
Neural networks , pattern recognition , multispectral space imagery , concurrent self-organizing maps Computer Science , Computer Systems Organization and Communication Networks , Applications of Mathematics , Information Systems and Communication Service , Computer Imaging, Vision, Pattern Recognition and Graphics , Computer Appl. in Social and Behavioral Sciences
A New Neural Approach for Pattern Recognition in Space Imagery
British Library Conference Proceedings | 2009
|A pattern recognition technique for scene matching of dissimilar imagery
Tema Archive | 1979
|