Deep Learning Based Recognition of Sign Language

Sign language recognition plays a crucial role in bridging communication barriers for individuals with hearing impairments. This paper presents a novel approach to sign language recognition leveraging deep learning techniques. We propose a multi-stage framework comprising hand detection, hand tracking, and sign classification. Convolutional Neural Networks (CNNs) are employed for hand detection and tracking to accurately localize and track hand movements in real-time. Subsequently, a Long Short-Term Memory (LSTM) network is utilized for temporal modeling to capture the sequential nature of sign language gestures. Our proposed method achieves promising results on benchmark datasets, demonstrating its effectiveness in real-world sign language recognition applications. This research contributes to the advancement of assistive technologies for the hearing-impaired community, facilitating inclusive communication and interaction. 46 various gestures are considered which resulted in 98.8% best case recognition accuracy rate.