Title :
A shape classifier based on Hopfield-Amari network
Author :
Fu, Alan M N ; Yan, Hong
Author_Institution :
Dept. of Electr. Eng., Sydney Univ., NSW, Australia
Abstract :
The representation and recognition of a planar shape based on contour information is an important issue in computer vision. We propose a method for extracting the main features of a contour using the curve bend function (CBF), which can be used to characterize the contour completely. A Hopfield-Amari network is built based on the CBF description to perform classification of planar shapes. The experimental results demonstrate that the proposed system is powerful and reliable for solving shape recognition problems
Keywords :
Hopfield neural nets; computer vision; feature extraction; image classification; object recognition; Hopfield-Amari network; computer vision; contour information; curve bend function; planar shape; shape classifier; shape recognition; Associative memory; Computer vision; Counting circuits; Data mining; Feature extraction; Hopfield neural networks; Pattern analysis; Pattern recognition; Power system reliability; Shape;
Conference_Titel :
Neural Networks, 1996., IEEE International Conference on
Conference_Location :
Washington, DC
Print_ISBN :
0-7803-3210-5
DOI :
10.1109/ICNN.1996.548961
