Wavelet transform based facial feature points detection
Choubeila Maaoui, F. Abdat, Alain Pruski · 2017
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.