SIGNFORMER: DeepVision Transformer for Sign Language Recognition

Sign language is the most common form of communication for hearing impaired. To bridge gap with such impaired people, a normal people should be able to recognize signs. Therefore, it necessary introduce sign recognition system assist people. This paper proposes Transformer Encoder as useful tool recognition. For static Indian signs, authors have implemented vision transformer. language, proposed methodology archives noticeable performance over other state-of-the-art convolution architecture. The suggested divides into series positional embedding patches, which are then sent transformer block four self-attention layers and multilayer perceptron network. Experimental results show satisfactory identification gestures under various augmentation methods. Moreover, approach only requires very small number training epochs achieve 99.29 percent accuracy.