Lip Detection Using Confidence-Based Adaptive Thresholding

In this paper we propose a lip detector based on adaptive thresholding for hue-transformed face images. The adaptation is performed according to the confidence values of the estimated lip regions. The confidence of lip means how much similarity exists between the detected lip region and a true lip. We construct simple fuzzy rules of the confidence using true lip statistics of center position, width and height. The threshold value is adaptively changed so that the confidence of a renewed lip region is maximized. By lip detection experiments with VidTimit database we demonstrate the performance enhancement of our proposed method.

[1]  Jin Young Kim,et al.  Skin-Color Based Human Tracking Using a Probabilistic Noise Model Combined with Neural Network , 2006, ISNN.

[2]  Ian R. Fasel,et al.  A generative framework for real time object detection and classification , 2005, Comput. Vis. Image Underst..

[3]  Léon J. M. Rothkrantz,et al.  Using aerial and geometric features in automatic lip-reading , 2001, INTERSPEECH.

[4]  Alice Caplier.  Lip detection and tracking , 2001, Proceedings 11th International Conference on Image Analysis and Processing.

[5]  Jeff A. Bilmes,et al.  DBN based multi-stream models for audio-visual speech recognition , 2004, 2004 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[6]  Yongzhao Zhan,et al.  A real-time approach to the lip-motion extraction in video sequence , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[7]  Petr Císař,et al.  Using of lip-reading for speech recognition in noisy environments , 2003 .

[8]  Marc Lievin,et al.  Lip motion automatic detection , 1997 .

[9]  Ara V. Nefian,et al.  Audio-visual speaker identification using coupled hidden Markov models , 2003, Proceedings 2003 International Conference on Image Processing (Cat. No.03CH37429).