Presentation 2010-03-15
Personal Identification Using Facial Feature and Context for Partially Occluded Images
Junpei YAMAGUCHI, Kazutaka SHIMADA, Shuichi ENOKIDA, Toshiaki EJIMA, Tsutomu ENDO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we describe a method of personal identification using facial features and context information for partially occluded images. The method calculates a facial similarity by using the CLAFIC method from the face and face parts such as eyes. We apply clothes information to the context. The method calculates a clothes similarity by using four clothes features. Finally, it integrates the two similarities, and identifies the person of an input image. In the experiment, our method with the integrated similarity outperformed the method with the face similarity. The experimental result shows the effectiveness of our method with the context information.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Personal Identification / Context / Facial Feature / Clothes Feature
Paper # PRMU2009-237,HIP2009-122
Date of Issue

Conference Information
Committee HIP
Conference Date 2010/3/8(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 Human Information Processing (HIP)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Personal Identification Using Facial Feature and Context for Partially Occluded Images
Sub Title (in English)
Keyword(1) Personal Identification
Keyword(2) Context
Keyword(3) Facial Feature
Keyword(4) Clothes Feature
1st Author's Name Junpei YAMAGUCHI
1st Author's Affiliation Kyushu Institute of Technology, Graduate School of Computer Science and Systems Engineering()
2nd Author's Name Kazutaka SHIMADA
2nd Author's Affiliation Kyushu Institute of Technology, Department of Artificial Intelligence
3rd Author's Name Shuichi ENOKIDA
3rd Author's Affiliation Kyushu Institute of Technology, Department of Artificial Intelligence
4th Author's Name Toshiaki EJIMA
4th Author's Affiliation Kyushu Institute of Technology, Department of Artificial Intelligence
5th Author's Name Tsutomu ENDO
5th Author's Affiliation Kyushu Institute of Technology, Department of Artificial Intelligence
Date 2010-03-15
Paper # PRMU2009-237,HIP2009-122
Volume (vol) vol.109
Number (no) 471
Page pp.pp.-
#Pages 6
Date of Issue