Sign language is a visual language that uses hand gesture, change of hand shape and track information to express meaning, and is the main communication tool for people with hearing and language impairment. Recently, there has been an increase in research in the field of deep learning and creation of deep learning libraries like tensorflow, keras etc. have made it easy to make use of convolutional neural networks. It has made it easy to create different layers like convolutional layers, pooling layers, fully connected layers etc. Based on the recent developments and technology we are proposing a system for sign language recognition of alphabets and numbers based on CNN. We have used CNN because it increases the accuracy of the system by recognizing hidden patterns and correlation in raw data.

Keywords : Convolution Neural Network (CNN), tensorflow, Keras, Indian Sign Language(ISL), American Sign Language(ASL)