Detection and tracking of facial features under a complex background

Li Zhuang; Guang-you Xu; Haizhou Ai; Gang Song

doi:10.1117/12.469544

30 May 2002 Detection and tracking of facial features under a complex background

Li Zhuang, Guang-you Xu, Haizhou Ai, Gang Song

Proceedings Volume 4662, Human Vision and Electronic Imaging VII; (2002) https://doi.org/10.1117/12.469544
Event: Electronic Imaging, 2002, San Jose, California, United States

Abstract

A coarse-to-fine facial feature detection and tracking system which is used under complex background is introduced in this paper. The system uses stereo cameras for video input. By stereovision technique, face is roughly and quickly segmented from complex background. Then, the multiple template matching method is applied to find the accurate face region from this rough segmentation. Facial organ candidates are extracted from the detected face region at a specific scale space called organ scale for Sobel filter. Finally, eyes, nose and mouth corners are detected. Techniques for checking and correcting errors in facial feature detection based on multiple cues are developed to make the algorithm more robust in facial feature detection and tracking in video sequence. Experiments on 189 video sequences demonstrate its effectiveness.

Citation Download Citation

Li Zhuang, Guang-you Xu, Haizhou Ai, and Gang Song "Detection and tracking of facial features under a complex background", Proc. SPIE 4662, Human Vision and Electronic Imaging VII, (30 May 2002); https://doi.org/10.1117/12.469544

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available