Presentation 2009-10-22
Image Quality Improvement System of Color Images by Using Eyegaze Tracking Interface
Ryo OHTERA, Takahiko HORIUCHI, Shoji TOMINAGA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This report presents a high-speed image quality improvement system for digital color images around a user's eyegaze point on a display. The proposed system is constructed by a monocular video camera for tracking eyegaze and a personal computer with GPU. The proposed algorithm consists of the eyegaze detection stage and the image processing stage. As the image improvement algorithm, this study focuses on the Retinex model. In general, the Retinex has the disadvantage for the expensive computational cost. In this report, the problem is solved by improving the algorithm and parallel processing using the GPU. The feasibility of the proposed system is verified by experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Image Improvement / Eyegaze Tracking / Retinex / GPU
Paper # PRMU2009-74
Date of Issue

Conference Information
Committee PRMU
Conference Date 2009/10/15(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Image Quality Improvement System of Color Images by Using Eyegaze Tracking Interface
Sub Title (in English)
Keyword(1) Image Improvement
Keyword(2) Eyegaze Tracking
Keyword(3) Retinex
Keyword(4) GPU
1st Author's Name Ryo OHTERA
1st Author's Affiliation Graduate School of Science and Technology, Chiba University()
2nd Author's Name Takahiko HORIUCHI
2nd Author's Affiliation Graduate School of Advanced Integration Science, Chiba University
3rd Author's Name Shoji TOMINAGA
3rd Author's Affiliation Graduate School of Advanced Integration Science, Chiba University
Date 2009-10-22
Paper # PRMU2009-74
Volume (vol) vol.109
Number (no) 249
Page pp.pp.-
#Pages 6
Date of Issue