Translational rotational scaling invariant (TRSI) pattern recognition is an important problem in the automatic target recognition (ATR) field. Recent research has shown that the higher order neural networks (HONN) have numerous advantages over other neural network approaches in respect of the object recognition with invariant of the object's position size, and in-plane rotation. The major limitation of HONNs is that the number of connected weights is too large to store on most machines. For N/spl times/N image, the memory needed to store the connections is proportional to N/sup 6/. This huge memory requirement limits the HONN's application to large scale images. In this paper, we have developed an integrated method which combines the bi-directional log-polar mapping and HONN pattern recognizer. It reduces the HONN memory requirement from O(N/sup 6/) to O(N/sup 2/). The proposed method has been successfully verified. Finally, the results are compared with those of coarse-coding method, traditional log-polar method.
Automatic target recognition using higher order neural network
1996-01-01
311484 byte
Conference paper
Electronic Resource
English
Automatic Target Recognition Using Higher Order Neural Network
British Library Conference Proceedings | 1996
|Neural network based automatic target processing and recognition
Tema Archive | 1999
|Neural Network Based Automatic Target Processing and Recognition
British Library Conference Proceedings | 1999
|Neural networks for automatic target recognition
Tema Archive | 1990
|Automatic Target Recognition for Hyperspectral Imagery using High-Order Statistics
Online Contents | 2006
|