Hand gesture recognition of English alphabets using artificial neural network

Human computer interaction (HCI) and sign language recognition (SLR), aimed at creating a virtual reality, 3D gaming environment, helping the deaf-and-mute people etc., extensively exploit the use of hand gestures. Segmentation of the hand part from the other body parts and background is the primary need of any hand gesture based application system; but gesture recognition systems are often plagued by different segmentation problems, and by the ones like co-articulation, movement epenthesis, recognition of similar gestures etc. The principal objective of this paper is to address a few of the said problems. In this paper, we propose a method for recognizing isolated as well as continuous English alphabet gestures which is a step towards helping and educating the hearing and speech-impaired people. We have performed the classification of the gestures with artificial neural network. Recognition rate (RR) of the isolated gestures is found to be 92.50% while that of continuous gestures is 89.05% with multilayer perceptron and 87.14% with focused time delay neural network. These results, when compared with other such system in the literature, go into showing the effectiveness of the system.