Constructed model for micro-content recognition in lip reading based deep learning

Communication between human beings has several ways, one of the most known and used is speech, both visual acoustic perceptions sensory are involved, because that, speech considered as a multi-sensory process. Micro contents small pieces information that can be to boost learning Deep an approach dives into deep texture layers learn fine grained details. The convolution neural network (CNN) technique employed complementary model with micro hold achieve special In This paper proposed for lip reading system presented video dataset. receives (the English alphabet) in input recognize them, role CNN clearly appeared perform two tasks, first feature extraction second recognition implementation results show efficient accuracy rate various dataset contains variety reader many persons age range from 11 63 years old, gives high reach 98%.