Presentation 1999/11/18
Feature selection experiments on the FAVRET face tracking and recognition system
Simon CLIPPINGDALE, Takayuki ITO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We describe a new system (RAVRET) for the detection, tracking and recognition of faces in unconstrained video sequences. The system updates running hypotheses based on the results of multiresolution deformable template matching, and performs recognition by integrating identity information while tracking changes in face position, size, and pose. We discuss the effects of variations in feature type and matching regime on recognition performance and robustness to facial deformations.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face recognition / feature extraction / tracking / deformable templates
Paper # PRMU99-109
Date of Issue

Conference Information
Committee PRMU
Conference Date 1999/11/18(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) Feature selection experiments on the FAVRET face tracking and recognition system
Sub Title (in English)
Keyword(1) face recognition
Keyword(2) feature extraction
Keyword(3) tracking
Keyword(4) deformable templates
1st Author's Name Simon CLIPPINGDALE
1st Author's Affiliation NHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories()
2nd Author's Name Takayuki ITO
2nd Author's Affiliation NHK (Japan Broadcasting Corporation) Science & Technology Research Laboratories
Date 1999/11/18
Paper # PRMU99-109
Volume (vol) vol.99
Number (no) 448
Page pp.pp.-
#Pages 8
Date of Issue