Recognition of Indian Sign Language Alphabets for Hearing and Speech Impaired People using Deep Learning

Pardeshi, Kirtee; Sreemathy, R.; Velapure, Akshay P.

doi:10.2139/ssrn.3430055

Cited by 4 publications

(1 citation statement)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As a result, AIBN has the ability not only to give early warning of many application scenarios but to modify our way of life through "smart" applications. Applications of AIBN can assist hearing challenged people in recognising hand gestures (Pardeshi, Sreemathy and Velapure, 2019). Thus, a compact and reliable SLR system is needed necessary to actually help the deaf people to interact with the normal individuals at any place.…”

Section: Ai-biosensor Network (Aibn)mentioning

confidence: 99%

Artificial Intelligence Biosensing System on Hand Gesture Recognition for the Hearing Impaired

Padmanandam¹,

Rajesh

Upadhyaya³

et al. 2022

International Journal of Operations Research and Information Systems

View full text Add to dashboard Cite

AI technologies have the potential to help deaf individuals communicate. Due to the complexity of sign fragmentation and the inadequacy of capturing hand gestures, the authors present a sign language recognition (SLR) system and wearable surface electromyography (sEMG) biosensing device based on a Deep SLR that converts sign language into printed message or speech, allowing people to better understand sign language and hand motions. On the forearms, two armbands containing a biosensor and multi-channel sEMG sensors are mounted to capture quite well arm and finger actions. Deep SLR was tested on an Android and iOS smartphone, and its usefulness was determined by comprehensive testing. Sign Speaker has a considerable limitation in terms of recognising two-handed signs with smartphone and smartwatch. To solve these issues, this research proposes a new real-time end-to-end SLR method. The average word error rate of continuous sentence recognition is 9.6%, and detecting signals and recognising a sentence with six sign words takes less than 0.9 s, demonstrating Deep SLR's recognition.

show abstract

Section: Ai-biosensor Network (Aibn)mentioning

confidence: 99%