• Shibhu
• Kokila. B
• Raju. K

Human action recognition is detection of the action and movements caused by an individual which will be classified using structure, position, behaviour etc. Sign language is an action based natural language which comes under human action recognition. Sign language is the primary mode of communication between hearing and the vocally impaired population. The government of India has enacted the Rights of Persons with Disabilities Act 2016 (RPwD Act 2016) which recognises Indian Sign Language (ISL) as an important communication medium for communicating with hearing impaired people. This also insists on the need for sign language interpreters in all Government organisations and public sector undertakings in order to abide by RPwD Act 2016. In recent years, due to the widespread usage of various sensors, action recognition is becoming more popular in many fields such as person surveillance, human-robot interaction etc. Using action recognition, recognising Indian sign language gestures (alphabets, numerals and specific words) will be done in real time using deep learning LSTM model. In this project video will be collected in real time through a web camera which will be taken as an input for the model. Given input which is collected as key points from video frames will be passed through the model. The model predicts the output which is the translation of the given input video. User interface is created for hearing impaired individuals which will act as a sign language interpreter. This project is focusing to achieve the maximum accuracy with no loss.

Deep learning, LSTM, MediaPipe, Indian sign language, Natural language processing, Action recognition

"Indian Sign Language Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.9, Issue 5, page no.j164-j168, May-2022, Available :http://www.jetir.org/papers/JETIR2205A26.pdf

"Indian Sign Language Recognition", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.9, Issue 5, page no. ppj164-j168, May-2022, Available at : http://www.jetir.org/papers/JETIR2205A26.pdf