Robust Facial Feature Tracking Using Shape-Constrained Multiresolution-Selected Linear Predictors

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 33; no. 9; pp. 1844 - 1859
• Main Authors: Eng-Jon Ong, Bowden, Richard
• Format: Journal Article
• Language: English
• Published: Los Alamitos, CA IEEE 01.09.2011; IEEE Computer Society; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Applied sciences; Artificial intelligence; Biometric Identification - methods; Computer science; control theory; systems; Databases, Factual; Exact sciences and technology; Face - anatomy & histology; Facial; Facial feature tracking; Facial features; Failure; Feature extraction; Humans; Image Processing, Computer-Assisted - methods; Intelligence; learning; linear predictors; Linear programming; Mathematical models; Models, Statistical; Mouth; multiple resolution; Pattern analysis; Pattern recognition. Digital image processing. Computational geometry; probabilistic selection; Studies; Target tracking; Tracking; Visual; Visualization; probabilistic selection; Tracking; Image processing; linear predictors; Linear group; learning; Data driven modelling; Modeling; Multiresolution analysis; Deformable body; Linear prediction; Visual cue; Robustness; Computer vision; Probabilistic approach; Motion estimation; Point shape; Face recognition; multiple resolution; Large displacement; Real time; Facial feature tracking; Visual stimulus; A priori estimation; Hierarchical system; Biased estimation
• ISSN: 0162-8828; 1939-3539; 2160-9292; 1939-3539
• DOI: 10.1109/TPAMI.2010.205

This paper proposes a learned data-driven approach for accurate, real-time tracking of facial features using only intensity information. The task of automatic facial feature tracking is nontrivial since the face is a highly deformable object with large textural variations and motion in certain regio...