Title :
Morphological shared-weight neural network for pattern classification and automatic target detection
Author :
Won, Yonggwan ; Gader, Paul D.
Author_Institution :
Dept. of Electr. & Comput. Eng., Missouri Univ., Columbia, MO, USA
Abstract :
A shared-weight neural network which performs a novel gray-scale morphological hit-miss transform operation for feature extraction is introduced. The network is applied to general pattern classification and automatic target detection (ATD) problems. The network is compared to the linear shared-weight network and a minimum average correlation energy (MACE) matched filter approach. A training method designed to suppress the background output for ATD problem is presented. Experimental results show that this morphological network is fast in training and is superior for gray-scale pattern classification and ATD
Keywords :
feature extraction; feedforward neural nets; multilayer perceptrons; object detection; pattern classification; automatic target detection; gray-scale morphological hit-miss transform operation; gray-scale pattern classification; linear shared-weight network; minimum average correlation energy matched filter approach; morphological shared-weight neural network; training method; Computer networks; Convolution; Data mining; Feature extraction; Gray-scale; Matched filters; Morphological operations; Neural networks; Object detection; Pattern classification;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.489008
