Presentation 2006/6/8
Reduced-Complexity Variational Retinex for Video Image Enhancement
Kazuyuki TAKAHASHI, Yoshihiro NOZATO, Hiroyuki OKUHATA, Takao ONOYE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to realize adaptive image enhancement, various models based on Retinex theory have been proposed. These models in general did not take into consideration the computational cost. In this report, we propose a technique which reduces the computational cornplexty of retinex without affecting the visual quality of images. As a new method, image layers with low resolution are mainly processed by using the characteristic of spatially smooth. As a result, computational complexity is reduced by 94% for each HD frame.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Adaptive Enhancement / Digital Image Processing / Retinex / Variational method
Paper # SIS2006-3
Date of Issue

Conference Information
Committee SIS
Conference Date 2006/6/8(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Smart Info-Media Systems (SIS)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Reduced-Complexity Variational Retinex for Video Image Enhancement
Sub Title (in English)
Keyword(1) Adaptive Enhancement
Keyword(2) Digital Image Processing
Keyword(3) Retinex
Keyword(4) Variational method
1st Author's Name Kazuyuki TAKAHASHI
1st Author's Affiliation Graduate School of Information Science and Technology Osaka University()
2nd Author's Name Yoshihiro NOZATO
2nd Author's Affiliation Graduate School of Information Science and Technology Osaka University
3rd Author's Name Hiroyuki OKUHATA
3rd Author's Affiliation Synthesis Corporation
4th Author's Name Takao ONOYE
4th Author's Affiliation Graduate School of Information Science and Technology Osaka University
Date 2006/6/8
Paper # SIS2006-3
Volume (vol) vol.106
Number (no) 95
Page pp.pp.-
#Pages 6
Date of Issue