Title :
Learning and extracting edges from images by a modified Hopfield neural network
Author :
Chartier, Sylvain ; Lepage, Richard
Author_Institution :
Departement de Psychologie, Univ. du Quebec a Montreal, Que., Canada
Abstract :
This paper introduces a modified unsupervised Hopfield network that can learn the underlying process in an edge detection task from grey level images. After the learning phase, the network performance is tested to ensure that it can detect only the significant edges and that it can generalise other images.
Keywords :
Hopfield neural nets; edge detection; feature extraction; performance evaluation; unsupervised learning; edge detection; feature extraction; grey level images; image generalisation; learning; modified unsupervised Hopfield network; network performance; neural network; Application software; Artificial neural networks; Eigenvalues and eigenfunctions; Feature extraction; Hopfield neural networks; Image edge detection; Image recognition; Phase detection; Psychology; Testing;
Conference_Titel :
Pattern Recognition, 2002. Proceedings. 16th International Conference on
Print_ISBN :
0-7695-1695-X
DOI :
10.1109/ICPR.2002.1047940
