Development of a Sign Language recognizer using LSTM

Development of a Sign Language recognizer using LSTM

Raghav Jethaliya, Pratishta Holkar, Rishi Yadav, Rhythm Khandelwal

Acropolis Institute of Technology and Research

Abstract
Sign language recognition plays a crucial role in bridging communication gaps between the deaf community and the hearing population. This paper presents the development of a sign language recognizer using Long Short-Term Memory (LSTM) networks, a type of recurrent neural network well-suited for sequence prediction tasks. The proposed model aims to accurately     interpret hand gestures into text, enhancing accessibility and communication for individuals with hearing impairments.

Our approach utilizes a custom-built dataset of sign language gestures, which undergoes preprocessing to extract relevant features such as hand position, orientation, and movement. The LSTM-based architecture is designed to capture the temporal dynamics of these gestures, enabling the recognition of complex sign language patterns. We train the model using a supervised learning approach.
Our method demonstrates superior accuracy in recognizing sign language gestures compared to traditional machine learning methods and other deep learning architectures. This advancement contributes significantly to the field of assistive technologies. Future work will explore the integration of additional modalities, such as facial expressions and body movements, to further enhance the system's performance and usability.