Presentation 2014-01-24
Person Identification with FREAK
Peng Li, Yankun Long, Qian Chen, Haiyuan Chen,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In medical institution or welfare facility, in order to track and recognize the behaviors of the people who have been taken care of, it is necessary to indentify the tracked objects by switching over the multiple active cameras which do not share the view. In this paper, we proposed an identification system which corresponds to the change in the posture of the head. By using the OKAO library of the OMRON, various face postures and features of the face parts, which are represented by FREAK (Fast Retina Keypoint), will be detected. To identify arbitrary face postures, we registering and updating the models of the multiple face postures online. By using a discriminate function consists of the matching probability of the features of each face part and the dependency matching probability of the features between the parts, the personal identification will be achieved.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Multi-Active Camera / Tracking / Person / FREAK / face model
Paper # PRMU2013-116,MVE2013-57
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/1/16(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Person Identification with FREAK
Sub Title (in English)
Keyword(1) Multi-Active Camera
Keyword(2) Tracking
Keyword(3) Person
Keyword(4) FREAK
Keyword(5) face model
1st Author's Name Peng Li
1st Author's Affiliation Faculty of Systems Engineering, Wakayama University()
2nd Author's Name Yankun Long
2nd Author's Affiliation Faculty of Systems Engineering, Wakayama University
3rd Author's Name Qian Chen
3rd Author's Affiliation Faculty of Systems Engineering, Wakayama University
4th Author's Name Haiyuan Chen
4th Author's Affiliation Faculty of Systems Engineering, Wakayama University
Date 2014-01-24
Paper # PRMU2013-116,MVE2013-57
Volume (vol) vol.113
Number (no) 403
Page pp.pp.-
#Pages 6
Date of Issue