Presentation 1997/11/20
Realtime Face Detection and Tracking System Using Color Images
Gang Xu, Takeo SUGIMOTO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper describes a practical system that can robustly detect multiple human faces with unknown sizes and positions in complex backgrounds from color images in real time. It can also track one face in realtime. Skin color is modeled as a Gaussian distribution among different persons within the same race. Detected skin pixels are grouped into regions whose centroids and areas are recorded. If dark regions for eyes and eyebrows are also detected within these regions. the they are regarded as faces. Experimental results show that this approach is very fast and robust. The detection phase takes 0.3 sec. and the tracking takes 0.17 sec. per frame, both including the image tranfer time 0.13 sec.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Face Detection / Face Tracking / Realtime / Color Images / Skin Color Model
Paper # HIP97-11
Date of Issue

Conference Information
Committee HIP
Conference Date 1997/11/20(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) Realtime Face Detection and Tracking System Using Color Images
Sub Title (in English)
Keyword(1) Face Detection
Keyword(2) Face Tracking
Keyword(3) Realtime
Keyword(4) Color Images
Keyword(5) Skin Color Model
1st Author's Name Gang Xu
1st Author's Affiliation Computer Vision Laboratory, Department of Computer Science Ritsumeikan University()
2nd Author's Name Takeo SUGIMOTO
2nd Author's Affiliation Computer Vision Laboratory, Department of Computer Science Ritsumeikan University
Date 1997/11/20
Paper # HIP97-11
Volume (vol) vol.97
Number (no) 388
Page pp.pp.-
#Pages 8
Date of Issue