Presentation 1996/10/17
A representation for 3D faces with better feature correspondence for image generation using PCA
Katsunori ISONO, Shigeru AKAMATSU,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In psychological experiments that retrieve feature factors to construct facial impressions, many facial image samples are needed. However it is difficult to collect these image samples by only using real images. More specifically, artificial image generation is additionally necessary. In this paper, we consider generating image samples using 3D data by PCA. One major problem is how to geometrically correspond the feature data among the samples. To do this, we resample 3D shapes and make it possible to represent data with a better feature correspondence. Using the data for PCA, we can generate many more sharp facial images by changing the coefficients for linear combinations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Facial Image / Principal Component Analysis / Image Synthesis / Feature Correspondence
Paper # HIP96-17
Date of Issue

Conference Information
Committee HIP
Conference Date 1996/10/17(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A representation for 3D faces with better feature correspondence for image generation using PCA
Sub Title (in English)
Keyword(1) Facial Image
Keyword(2) Principal Component Analysis
Keyword(3) Image Synthesis
Keyword(4) Feature Correspondence
1st Author's Name Katsunori ISONO
1st Author's Affiliation ATR Human Information Processing Research Laboratories()
2nd Author's Name Shigeru AKAMATSU
2nd Author's Affiliation ATR Human Information Processing Research Laboratories
Date 1996/10/17
Paper # HIP96-17
Volume (vol) vol.96
Number (no) 306
Page pp.pp.-
#Pages 6
Date of Issue