Title :
Orientation Selectivity of TAM Network with Extensive Receptive Field
Author :
Hayashi, Isao ; Williamson, James R.
Author_Institution :
Dept. of Informatics, Kansai Univ., Osaka
Abstract :
TAM (topographic attentive mapping) network is a biologically-motivated neural network with Gabor function type receptive fields. However, the structure of receptive fields is a mono-layer, and there is a lack of performance for rotating images. In this paper, we formulate a new TAM network with multilayer structure of extensive receptive fields. We also show the usefulness of TAM network using some examples of character recognition
Keywords :
Gabor filters; character recognition; neural nets; Gabor function; TAM network; biologically-motivated neural network; character recognition; image rotation; multilayer structure; receptive field; topographic attentive mapping network; Character recognition; Filtering; Gabor filters; Humans; Informatics; Multi-layer neural network; Neural networks; Object detection; Retina; Visual system;
Conference_Titel :
Computational Intelligence for Modelling, Control and Automation, 2005 and International Conference on Intelligent Agents, Web Technologies and Internet Commerce, International Conference on
Conference_Location :
Vienna
Print_ISBN :
0-7695-2504-0
DOI :
10.1109/CIMCA.2005.1631423
