Title :
The design of multiresolution adaptive classifier
Author :
Lihua, Yu ; Diao Yimin ; Fusheng, Yang
Author_Institution :
Dept. of Electr. Eng., Tsinghua Univ., Beijing, China
Abstract :
The characteristics of visual information processing at the primary stage of the visual nerve system (from retina to striate cortex) are summarized briefly in this paper. The concept of wavelet transform (WT) implied in this procedure is emphasized. A multiresolution adaptive classifier (MAC)is presented to organize this concept into the network structure and the back propagation (BP) learning method is used to train the network. Computer simulation on the recognition of numerals shows the good performance of MAC.
Keywords :
adaptive signal processing; backpropagation; eye; image classification; neural nets; neurophysiology; physiological models; visual perception; wavelet transforms; back propagation learning method; multiresolution adaptive classifier design; retina; striate cortex; visual information processing; visual nerve system primary stage; wavelet transform; Bars; Biological system modeling; Computation theory; Computer simulation; Information processing; Radio frequency; Retina; Signal resolution; Spatial resolution; Wavelet transforms;
Conference_Titel :
Neural Networks, 1993. IJCNN '93-Nagoya. Proceedings of 1993 International Joint Conference on
Print_ISBN :
0-7803-1421-2
DOI :
10.1109/IJCNN.1993.714158
