Hand Anatomy and Neural Network-Based Recognition for Sign Language

This paper presents a model based on hand anatomy and neural network for the recognition of sign language. Feature extraction is done by using FAST and SIFT techniques. Out of these extracted features, only essential hand landmarks are selected using hand anatomy. NN is then used for the training and testing of the model. The proposed model is evaluated on sign language gestures used for medical purposes, general purposes, and family & relative purposes. The results prove that the proposed model has achieved fast and highly accurate results when compared with other available models. The model has achieved a recognizable accuracy of 99.85%, 97.55%, and 98.85%, on medical purposes, general purposes, and family & relative purposes, respectively.