An Efficient Real-Time Indian Sign Language (ISL) Detection using Deep Learning

Indian Sign Language (ISL) detection has become crucially important due to the growing need to bridge the communication gap between the hearing and the non-hearing people. For the deaf and hard-of-hearing community in India, ISL is the main form of communication. However, since the majority of the population does not understand ISL, communication can become a challenge. Indian sign language detection system that uses deep convolutional neural networks (CNNs), Media Pipe, and OpenCV in real-time. The system is designed to detect and classify Indian sign language gestures in real-time using hand detection and tracking, gesture segmentation, feature extraction, and a trained CNN model. The system also includes a user-friendly interface and accessibility features such as text-to-speech, image to speech, text to image and webcam input to text display. The proposed system has the potential to enhance communication between deaf and hearing users and can be deployed in real-world settings to facilitate communication in different ways.