Title:	REAL-TIME 2D FACE DETECTION AND FEATURES-BASED TRACKING IN VIDEO
Author(s):	Guillaume Lemaître, Eloisa Vargiu, José Antonio Lorenzo Fernández, Felip Miralles
ISBN:	978-972-8939-74-8
Editors:	Yingcai Xiao
Year:	2012
Edition:	Single
Keywords:	Real-time, face detection- tracking, multimedia videos, hard-cut detection.
Type:	Full Paper
First Page:	91
Last Page:	98
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In this paper, we propose a system aimed at detecting and tracking 2D human faces. The system is designed to perform in real-time and to be robust to partial occlusions and illumination changes and non-rigid transformation of the faces. After detection of video shot boundaries, multi-view detectors allow to localize frontal and profile faces and a features-based tracking algorithm track them over time even with non-rigid deformations. The system is validated on different video sequences performing at an average frame rate of 20 fps. Results show a clear improvement (i.e. recall, precision and time processing) over the results of tracking-by-detection.
	Go Back