Title: Bio-inspired computer fovea model based on hexagonal-type cellular neural network
Authors: Huang, Chao-Hui
Lin, Chin-Teng
資訊工程學系
電控工程研究所
腦科學研究中心
Department of Computer Science
Institute of Electrical and Control Engineering
Brain Research Center
Keywords: bipolar cell;cellular neural networks (CNNs);color constancy;fovea;ganglion;hexagonal;horizontal cell;photoreceptor;retina;sharpness
Issue Date: 1-Jan-2007
Abstract: For decades, numerous scientists have examined the following questions: "How do humans see the world?" and "How do humans experience vision?" To answer these questions, this study proposes a computer fovea model based on hexagonal-type cellular neural network (hCNN). Certain biological mechanisms of a retina can be simulated using an in-state-of-art architecture named CNN. Those biological mechanisms include the behaviors of the photoreceptors, horizontal cells, ganglions, and bipolar cells, and their co-operations in the retina. Through investigating the model and the abilities of the CNN, various properties of the human vision system can be simulated. The human visual system possesses numerous interesting properties, which provide natural methods of enhancing visual information. Various visual information enhancing algorithms can be developed using these properties and the proposed model. The proposed algorithms include color constancy, image sharpness, and some others. This study also discusses how the proposed model works for video enhancement and demonstrates it experimentally.
URI: http://dx.doi.org/10.1109/TCSI.2006.887975
http://hdl.handle.net/11536/5445
ISSN: 1057-7122
DOI: 10.1109/TCSI.2006.887975
Journal: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
Volume: 54
Issue: 1
Begin Page: 35
End Page: 47
Appears in Collections:Conferences Paper