Multi features Active Shape Models for lip contours detection

We propose and evaluate a novel method for enhancing performance of lip contours detection, which is based on the concept of Active Shape Models and optimization of multi features. A single feature-based ASM presents good performance only in particular conditions but gets stuck in local minima for noisy conditions (like beard, wrinkle, poor texture, low contrast between lip and skin, etc). To enhance the convergence, we propose to use 3 features: normal profile, grey level patches and Gabor wavelets, and combine them by using a voting approach to derive a robust method (MF-ASM) for lip contours detection. Initial experimental results using popular audiovisual Databases show that our method resolves the local minima and gives a higher accuracy than traditional single feature ASM in lip contours detection.