Application of Principal Component Analysis Method and Artificial Neural Network for Identifying Sign Language

Sign language is used in the deaf community to replace the traditional spoken language. In addition, sign language is also used in the interaction between people and machines. In this paper, we propose a solution to recognize sign language using the principal component analysis method and artificial neural network. At first, the hand is detected, then some preprocessing steps are taken to improve the image quality, then we determine a new space to represent the hand image with fewer dimensions than the original space and characteristics of the image are kept, and the artificial neural network is used for training and testing with the mapped input image. This solution has low computational cost, and can execute in real-time. The proposed approach has been tested with high accuracy and stability