Generalized likelihood ratio-based face detection and extraction of mouth features

• Published in: Pattern recognition letters Vol. 18; no. 9; pp. 899 - 912
• Main Authors: Kervrann, C., Davoine, F., Pérez, P., Forchheimer, R., Labit, C.
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01-09-1997; Elsevier
• Subjects: Computer Science; Computer Vision and Pattern Recognition; Face detection and tracking; Mouth features extraction; Principal components analysis; Simulated annealing; Mouth features extraction; Principal components analysis; Face detection and tracking; Simulated annealing
• ISSN: 0167-8655; 1872-7344
• DOI: 10.1016/S0167-8655(97)00065-2

We describe a system to detect the speaker's face and mouth in videophone sequences. A statistical scheme based on a subspace method is described for detecting and tracking faces under varying poses. A matching criterion based on a Generalized Likelihood Ratio is optimized efficiently with respect to a perspective transformation using a coarse-to-fine search strategy combined with a simulated annealing algorithm. Moreover, we analyze the amplitude projections around the speaker's mouth to describe the shape of the lips. All computations are performed on lossy H263-coded images. The proposed algorithms are well-suited to a further real-time implementation.