International Research Journal of Education and Technology

Sign language (SL) serves as the primary mode of communication for millions of individuals with hearing and speech impairments globally. However, it remains a language that is largely inaccessible to the general public, which poses a barrier to effective communication. This paper presents a static hand gesture-based sign language recognition system using Convolutional Neural Networks (CNNs). We utilize a dataset consisting of Indian Sign Language (ISL) gestures, including 26 alphabets and 10 digits. Our system uses image processing techniques for hand segmentation, followed by CNN-based classification. With a testing accuracy of 99.89% and validation accuracy of 99.85% over 5 epochs, our system proves to be effective and reliable in recognizing ISL gestures. This work provides a robust foundation for real-time applications aimed at facilitating communication between the hearing impaired and the general public.

Keywords—CNN, Sign Language Recognition, Indian Sign Language, Gesture Recognition, Deep Learning