Facial Feature Points Tracking Based on AAM With Optical Flow Constrained Initialization
Full Text
Close
The Journal of Pattern Recognition Research (JPRR) provides an international forum for the electronic publication of high-quality research and industrial experience articles in all areas of pattern recognition, machine learning, and artificial intelligence. JPRR is committed to rigorous yet rapid reviewing. Final versions are published electronically
(ISSN 1558-884X) immediately upon acceptance.
Facial Feature Points Tracking Based on AAM With Optical Flow Constrained Initialization
Ying Cui, Zhong Jin
JPRR Vol 7, No 1 (2012); doi:10.13176/11.373 
Download
Ying Cui, Zhong Jin
Abstract
A facial feature points tracking method is proposed by adding Lucas-Kanade optical flow constraint on the face alignment algorithm, Active Appearance Model (AAM). The optical flow considers the inter-frame correspondence and uses it to estimate AAM initial shape more accurately with similarity preservation. Experiments show that the proposed method can successfully track the frames that general AAM tracks failed. The method achieves not only the accuracy but also the computation time improvement.
JPRR Vol 7, No 1 (2012); doi:10.13176/11.373 | Full Text  | Share this paper: