Presentation 2001/9/7
Image Estimation by Nonlinear Projection : Extraction of Eyeglass Frame Region and Estimation of Facial Image from Eyeglass Facial Image
Yasuyuki SAITO, Yukiko KENMOCHI, Kazunori KOTANI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper presents a new method of image estimation by nonlinear projection. We deal with eyeglass facial images and estimate eyeglassless facial images by using basis vectors. In this case, the estimation accuracy depends on a gray value of pixels in eyeglass region. Therefore we extract an eyeglass region by using a parametric eyeglass model and replace the gray value of the pixels in the region. Then we estimate an eyeglassless facial images using the result image by former process which replaces the gray value. In this way we could improve the estimation accuracy.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Nonlinear projection / Principal Component Analysis / Eyeglass facial image / Eyeglass frame model / Facial image analysis and processing
Paper # PRMU2001-98
Date of Issue

Conference Information
Committee PRMU
Conference Date 2001/9/7(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 Estimation by Nonlinear Projection : Extraction of Eyeglass Frame Region and Estimation of Facial Image from Eyeglass Facial Image
Sub Title (in English)
Keyword(1) Nonlinear projection
Keyword(2) Principal Component Analysis
Keyword(3) Eyeglass facial image
Keyword(4) Eyeglass frame model
Keyword(5) Facial image analysis and processing
1st Author's Name Yasuyuki SAITO
1st Author's Affiliation Deptartment of Information Engineering, Kisarazu National College of Technology()
2nd Author's Name Yukiko KENMOCHI
2nd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
3rd Author's Name Kazunori KOTANI
3rd Author's Affiliation School of Information Science, Japan Advanced Institute of Science and Technology
Date 2001/9/7
Paper # PRMU2001-98
Volume (vol) vol.101
Number (no) 303
Page pp.pp.-
#Pages 8
Date of Issue