Combined online and offline information for tracking facial feature points

Authors:
Xin Wang;Yequn Zhang;Chunlei Chai
Affiliations:
College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou, China;College of Information Engineering, Zhejiang University of Technology, Hangzhou, China;College of Computer Science and Technology, Zhejiang University, Hangzhou, China
Venue:
ICIRA'12 Proceedings of the 5th international conference on Intelligent Robotics and Applications - Volume Part I
Year:
2012

Citing 7
Cited 0

Model-based object pose in 25 lines of code

International Journal of Computer Vision - Special issue: image understanding research at the University of Maryland
Face Recognition by Elastic Bunch Graph Matching

IEEE Transactions on Pattern Analysis and Machine Intelligence
Tracking Facial Features using Gabor Wavelet Networks

SIBGRAPI '00 Proceedings of the 13th Brazilian Symposium on Computer Graphics and Image Processing
Bundle Adjustment - A Modern Synthesis

ICCV '99 Proceedings of the International Workshop on Vision Algorithms: Theory and Practice
View-Based Active Appearance Models

FG '00 Proceedings of the Fourth IEEE International Conference on Automatic Face and Gesture Recognition 2000
Stable Real-Time 3D Tracking Using Online and Offline Information

IEEE Transactions on Pattern Analysis and Machine Intelligence
Visual tracking and recognition using probabilistic appearance manifolds

Computer Vision and Image Understanding

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper proposes a novel real-time facial feature points tracking method. A 3D geometric face model is used to give a robust tracking which includes offline information that the movement constraints of facial feature points in 3D space. The iterative frame-to-frame tracking method with Gabor wavelet is used to give a high accuracy which is robust to homogeneous illumination changing and affine deformation of the face image. The former tracking method based offline information and the latter tracking method based on online information are integrated with the bundle adjustment method. We compare our method with three other typical methods. The experimental results show that it can be used for robust, real-time and wide-angle facial feature tracking.