Human face segmentation and tracking using connected operators and partition projection

A new technique for segmenting and tracking human faces in video sequences is presented. The algorithm uses a connected operator to extract the connected component that more likely belongs to a face. Such a connected operator is implemented by means of a binary partition tree. A set of connected regions (a node in the tree) is selected maximizing an estimation of the likelihood of being part of a face. Faces are tracked through the sequence based on the partition projection approach. A face and a non-face core component are obtained in the current image by projecting the previous partition. The technique has been successfully assessed using several test sequences from the MPEG-4 database (raw format) as well as from the MPEG-7 database (MPEG-1 format).

[1]  Verónica Vilaplana,et al.  Region-based segmentation and tracking of human faces , 1998, 9th European Signal Processing Conference (EUSIPCO 1998).

[2]  Verónica Vilaplana,et al.  Face segmentation using connected operators , 1998 .

[3]  Philippe Salembier,et al.  Binary partition tree as an efficient representation for filtering, segmentation and information retrieval , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[4]  David García,et al.  Extensive operators in partition lattices for image sequence analysis , 1998, Signal Process..

[5]  Ferran Marqués,et al.  Tracking of generic objects for video object generation , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[6]  Montse Pardàs,et al.  Coding-Oriented Segmentation of Video sequences , 1996 .

[7]  Rama Chellappa,et al.  Human and machine recognition of faces: a survey , 1995, Proc. IEEE.

[8]  Alex Pentland,et al.  Probabilistic Visual Learning for Object Representation , 1997, IEEE Trans. Pattern Anal. Mach. Intell..