ABSTRACT

VISUAL SPEECH RECOGNITION BY LIP READING

This project proposes the system design of VISUAL SPEECH RECOGNITION

BY LIP READING. Visual speech information plays an important role in lipreading under
noisy conditions or for listeners with a hearing impairment. Lip reading a perception of
speech for listeners with hearing impairment is purely based on observing the lip movements
under noisy conditions where visual speech information plays an important role. Lip reading
is a visual modality which involves watching the movement of lips constitutes 1/3 of the
conveyed message. This study investigates the use of two feature extraction methodologies
for recognizing isolated words. The first type is based on a geometric approach which
extracts the features like inner height, inner width, outer height and outer width of the lips
while the second type is based on a set of Block-Based Gabor-Wavelet co-efficient extracted
from each frame. Then these two features are given as input into the Support Vector Machine
Model for recognizing the words. In comparison with other methods on AV Letters database,
the accuracy, 62.8%, of our method clearly outperforms the others. The advantages of our
approach include local processing and robustness to monotonic gray-scale changes.
Moreover, no error prone segmentation of moving lips is needed.

INTERNAL GUIDE
K.Saravanamoorthy Er.J.Vijayaraghavan
M.E. Communication Systems Asst. Prof, ECE,
21108403005 Rajalakshmi Engineering College