Sign Language Interpretation using Machine Learning

Sign Language Interpretation using Machine Learning

Aniruddha Jathar (B212036) Omkar Kodmur (B213043) Prathamesh Belurkar (B212007)

Shrikant Bhandalkar (B211012) Dipali Pawar (Professor)

Assistant Professor, Department of Computer Engineering, Zeal College of Engineering and Research, Pune.

BE Students, Department of Computer Engineering, Zeal College of Engineering and Research, Pune

Abstract-- Every day we see many people with disabilities like the deaf, the dumb and the blind, etc. There are around 500 million people with loss of hearing disability. Sign language is one of the communication tools for the deaf people's community and common people's community. But normal people find it hard to understand the sign language and gestures of the deaf. Many tools can be used to translate the sign language created by the disabled into a form that normal people can understand. The studies are based on various image acquisition, preprocessing, hand gesture segmentation, extraction of features, and classification methods. This paper aims to research and examine the use of LSTM for creating a application to detect sign language using a webcam. Due to the latest advancement in classification methods, we can use TensorFlow library which has various machine learning models for creating a neural network for sign language detection. This paper specializes in the classification strategies utilized in earlier Sign Language Recognition. Based on our review, HMM-based techniques were explored significantly in previous studies, which include modifications. Deep learning consisting of convolutional neural   networks has become popular over the past five years.

Keywords:

Sign language, Recognition, TensorFlow, Media Pipe, Neural networks, Deep learning, LSTM.