REAL TIME MALAYSIAN SIGN LANGUAGE TRANSLATOR – TUTURJOM

Abstract

Malaysian Sign Language (MSL) is a vital language that is used as the primary means of communication between the deaf and mute and hearing communities in Malaysia. Malaysians are currently very unfamiliar with MSL, and the present platform for learning the language is scarce, not to mention the lack of efficacy of the available mobile and web learning tools. Therefore, the aim of this study is to propose software for real-time translation of MSL through a Long Short-Term Memory (LSTM) model. The following paper explains six phases of CRISP-DM in creating the application while looking through various findings and important algorithms. This article also intends to provide a clear understanding of hand gesture and pose recognition, LSTM networks and its uses in understanding sign languages.
Keywords: LSTM, Malaysian sign language, CRISP-DM, gesture recognition, sign language recognition