Summary
2007 International Symposium on Nonlinear Theory and its Applications
2007
Session Number:17PM2-B
Session:
Number:17PM2-B-1
DT-CNN Based Resolution Enhancement of Images using Cycle Spinning
Takefumi Konishi, Tsuyoshi Otake, Hisashi Aomori, Nobuaki Takahashi, Mamoru Tanaka,
pp.67-70
Publication Date:2007/9/16
Online ISSN:2188-5079
DOI:10.34385/proc.41.17PM2-B-1
PDF download (224.6KB)
Summary:
In this paper, novel image resolution enhancement technique using discrete-time celluar neural network (DT-CNN) with cycle spinning is proposed. Generally, interpolated images include a lot of noises when the enhacement factor is large. The denoising process is necessary to supress such noises. In our proposed method, images are interpolated by exploiting the nonlinear interpolative dynamics of the DT-CNN with a feedback A-template using cycle spinning. The experimental evaluation shows that the proposed method produces better results than those of the conventional image resolution enhancement methods.