Nonlinear Color Space and Spatiotemporal MRF for Hierarchical Segmentation of Face Features in Video
- 30 January 2004
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Image Processing
- Vol. 13 (1), 63-71
- https://doi.org/10.1109/tip.2003.818013
Abstract
This paper deals with the low-level joint processing of color and motion for robust face analysis within a feature-based approach. To gain robustness and contrast under unsupervised viewing conditions, a nonlinear color transform relevant for hue segmentation is derived from a logarithmic model. A hierarchical segmentation scheme is based on Markov random field modeling, that combines hue and motion detection within a spatiotemporal neighborhood. Relevant face regions are segmented without parameter tuning. The accuracy of the label fields enables not only face detection and tracking but also geometrical measurements on facial feature edges, such as lips or eyes. Results are shown both on typical test sequences and on various sequences acquired from micro- or mobile-cameras. The efficiency of the method makes it suitable for real-time applications aiming at audiovisual communication in unsupervised environments.Keywords
This publication has 28 references indexed in Scilit:
- Geodesic illumination basis: compensating for illumination variations in any pose for face recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Combining information using hard constraintsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Real time tracking and modeling of faces: an EKF-based analysis by synthesis approachPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Emotion recognition in human-computer interactionIEEE Signal Processing Magazine, 2001
- Segmentation and tracking of facial regions in color image sequencesPublished by SPIE-Intl Soc Optical Eng ,2000
- Coding, analysis, interpretation, and recognition of facial expressionsIeee Transactions On Pattern Analysis and Machine Intelligence, 1997
- Lip synchronization using speech-assisted video processingIEEE Signal Processing Letters, 1995
- Recovery of moving object masks in an image sequence using local spatiotemporal contextual informationOptical Engineering, 1993
- Snakes: Active contour modelsInternational Journal of Computer Vision, 1988
- Stochastic Relaxation, Gibbs Distributions, and the Bayesian Restoration of ImagesIeee Transactions On Pattern Analysis and Machine Intelligence, 1984