Title :
A retina-filtering model and its application in image restoration
Author :
KangHo Paek ; Min Yao ; Xiaowei Xue
Author_Institution :
Coll. of Comput. Sci. & Technol., Zhejiang Univ., Hangzhou, China
Abstract :
It is one of the attractive and challenging topics in the field of computer vision to reveal the mechanism of the biological visual system and gain useful insights from it. According to the experimental results of physiology, this paper analyzes the role of the image transmission components in mammalian retina for improving imaging clarity. Then, based on the theory of Bayesian estimation, a kind of retina-filtering model is proposed, of which the parameters were determined by Green´s solution of fractional diffusion equation and the optical characteristics of eye. Finally, experiment results in image restoration show the effectiveness and feasibility of the proposed method.
Keywords :
belief networks; computer vision; filtering theory; image restoration; Bayesian estimation; biological visual system; computer vision; fractional diffusion equation; image restoration; image transmission components; mammalian retina; retina-filtering model; Equations; Image edge detection; Mathematical model; Optical filters; Photoreceptors; Retina; Scattering; fraction diffusion; image restoration; retina reverted structure; retina-filtering model; scattering from random media;
Conference_Titel :
Natural Computation (ICNC), 2013 Ninth International Conference on
Conference_Location :
Shenyang
DOI :
10.1109/ICNC.2013.6817994
