Year: 2025
Type: article
Abstract: — Sign language serves as a vital mode of communication for individuals with hearing and speech impairments. With the advancement in computer vision and deep learning, real-time gesture recognition has become increasingly viable, facilitating smoother interaction between humans and machines. This paper presents a vision-based approach for the recognition of isolated Kannada Sign Language (KSL) gestures using Convolutional Neural Networks (CNN). The system employs image processing techniques to extract relevant features from hand gestures captured via a webcam. These features are then classified using a trained CNN model to predict corresponding sign language alphabets. The proposed method achieves high accuracy and demonstrates robustness against background variation and lighting conditions, offering a promising solution for sign language interpretation without the use of external hardware like gloves or sensors..
DOI: 10.55041/ijsrem47874
Authors: author, Dr. Arjun B C
Language: English
Subfield: Human-Computer Interaction
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4410409605