Wavelet transform based facial feature points detection

In this paper, we focus our attention on the detection and tracking feature points algorithm for video sequence environment. For face image extraction, modified face detector based on Haar-like features is used. For feature points detection, we develop a new method based on the wavelet decomposition. For more accuracy, good features can be identified using Shi and Thomasi alogorithm around the detected points. Pyramidal Lucas-Kanade algorithm is used to track those points. Results show that our method extracts facial features points from video's sequence with a good accuracy.

[1]  P. Ekman,et al.  Facial action coding system , 2019 .

[2]  Alain Pruski,et al.  Gradient based method for static facial features localization , 2007 .

[3]  Carlo Tomasi,et al.  Good features to track , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Frank Y. Shih,et al.  Automatic extraction of head and face boundaries and facial features , 2004, Inf. Sci..

[5]  Paul A. Viola,et al.  Robust Real-Time Face Detection , 2001, International Journal of Computer Vision.

[6]  Masakazu Matsugu,et al.  Subject independent facial expression recognition with robust face detection using a convolutional neural network , 2003, Neural Networks.

[7]  Erik Hjelmås,et al.  Face Detection: A Survey , 2001, Comput. Vis. Image Underst..

[8]  Sadhna Sharma Template Matching Approach for Face Recognition System , 2013, SiPS 2013.

[9]  Andreas Ranftl,et al.  Face Tracking Using Optical Flow , 2015, 2015 International Conference of the Biometrics Special Interest Group (BIOSIG).