Presentation 2002/9/13
Rapid Estimation of Facial Position and Scale
Takatsugu HIRAYAMA, Yoshio IWAI, Masahiko YACHIDA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The face detection needs the largest computational cost in processes of automatic face recognition. An estimation of facial position and scale has the trade-off problem between accuracy and efficiency. In this paper, we propose a method that estimates facial position in parallel with facial scale. The method estimates facial position by iterating three processes: estimation using global features, estimation using local features, verification. Facial scale is estimated by using the Scale conversion in the above iteration process. We demonstrate the advantages of the proposed method through facial detection experiments.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Maximum-Likelihood Estimation / Dynamic Link Architecture (DLA) / Scale conversion / Beam Search
Paper # WIT2002-33
Date of Issue

Conference Information
Committee WIT
Conference Date 2002/9/13(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 Well-being Information Technology(WIT)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Rapid Estimation of Facial Position and Scale
Sub Title (in English)
Keyword(1) Maximum-Likelihood Estimation
Keyword(2) Dynamic Link Architecture (DLA)
Keyword(3) Scale conversion
Keyword(4) Beam Search
1st Author's Name Takatsugu HIRAYAMA
1st Author's Affiliation Graduate School of Engineering Science, Osaka University()
2nd Author's Name Yoshio IWAI
2nd Author's Affiliation Graduate School of Engineering Science, Osaka University
3rd Author's Name Masahiko YACHIDA
3rd Author's Affiliation Graduate School of Engineering Science, Osaka University
Date 2002/9/13
Paper # WIT2002-33
Volume (vol) vol.102
Number (no) 320
Page pp.pp.-
#Pages 6
Date of Issue