Automatic combined lip segmentation in color images
Hamed Talea, Khashayar Yaghmaie · 2011
Automatic speech recognition (ASR) performs well under restricted conditions. Lipreading is a main part of audio-visual speech recognition systems and an accurate algorithm for lip detection and motion tracking helps to improve the recognition rate efficiently. This paper proposes a new combined method from combination of a new method and red exclusion algorithm. Accuracy of the proposed method is verified by applying it to several images.