Presentation 2012/1/12
Skin region extraction and person-independent deformable templates for fast face tracking
Simon CLIPPINGDALE, Mahito FUJII,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We describe a prototype face detection, tracking and pose estimation system for automatic face metadata extraction. An early version of the system scanned entire input frames with a face detector, leading to slow processing and many false positive detections. Tracking and pose estimation was performed by matching against deformable templates of all registered indiviiduals, which could also be computationally intensive. In order to tackle these issues, we (i) restrict face detection processing to regions identified as containing skin color, and (ii) we construct a relatively small number of "person-independent" deformable templates, and use these for tracking and pose estimation. We show experimental results, discuss performance and identify remaining issues.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) face tracking / face pose estimation / deformable template matching / skin region extraction
Paper # MVE2011-89,PRMU2011-180
Date of Issue

Conference Information
Committee MVE
Conference Date 2012/1/12(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) Skin region extraction and person-independent deformable templates for fast face tracking
Sub Title (in English)
Keyword(1) face tracking
Keyword(2) face pose estimation
Keyword(3) deformable template matching
Keyword(4) skin region extraction
1st Author's Name Simon CLIPPINGDALE
1st Author's Affiliation NHK Science & Technology Research Laboratories()
2nd Author's Name Mahito FUJII
2nd Author's Affiliation NHK Science & Technology Research Laboratories
Date 2012/1/12
Paper # MVE2011-89,PRMU2011-180
Volume (vol) vol.111
Number (no) 380
Page pp.pp.-
#Pages 6
Date of Issue