The Korea Institute of Information and Commucation Engineering 2004; 2(2): 132-137
Published online June 1, 2004
© Korea Institute of Information and Communication Engineering
Information Processing in Primate Retinal Ganglion
Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.
Keywords Artificial vision, Compression, Image recognition, artificial neural network, Retinal Ganglion
PDF
Standard view
Export citation
Share Article
The Korea Institute of Information and Commucation Engineering 2004; 2(2): 132-137
Published online June 1, 2004
Copyright © Korea Institute of Information and Communication Engineering.
Information Processing in Primate Retinal Ganglion
Je, Sung-Kwan;Cho, Jae-Hyun;Kim, Gwang-Baek;
Department of Computer Sciences, Pusan National University, Department of Computer Information, Catholic University of Pusan, Department of Computer Engineering, Silla University
Abstract
Most of the current computer vision theories are based on hypotheses that are difficult to apply to the real world, and they simply imitate a coarse form of the human visual system. As a result, they have not been showing satisfying results. In the human visual system, there is a mechanism that processes information due to memory degradation with time and limited storage space. Starting from research on the human visual system, this study analyzes a mechanism that processes input information when information is transferred from the retina to ganglion cells. In this study, a model for the characteristics of ganglion cells in the retina is proposed after considering the structure of the retina and the efficiency of storage space. The MNIST database of handwritten letters is used as data for this research, and ART2 and SOM as recognizers. The results of this study show that the proposed recognition model is not much different from the general recognition model in terms of recognition rate, but the efficiency of storage space can be improved by constructing a mechanism that processes input information.
Keywords: Artificial vision, Compression, Image recognition, artificial neural network, Retinal Ganglion
