• Ms. Girija V
• Akshay Kumar Singh
• Nayab Sahil
• Shibu Singh
• Tulika Paul

A key communication tool for those with hearing loss is sign language, facilitating their interaction with the world. Convolutional Neural Networks have become an effective tool for a number of image processing applications, such as the recognition of sign language. This study suggests an innovative CNN-based method for translating sign language to text. The suggested CNN model is designed to efficiently extract spatial and temporal characteristics from video sequences containing sign language. It employs convolutional layers to extract hierarchical features and pooling layers to reduce spatial dimensions while retaining crucial information. A large collection of images in sign language is used to train the model, enabling robust representation learning for precise translation. Test results show that the suggested CNN model is effective at translating sign language movement into text. The model achieves high accuracy and outperforms existing approaches on American Sign Language datasets. Overall, the proposed CNN-based sign language to text translation system offers a solution for addressing the communication gap between those who use sign language and those who do not. This technology can improve accessibility and inclusivity for the deaf community in a variety of contexts, including ordinary communication, healthcare, and education, by offering real-time translation capabilities. This study advances assistive technologies and encourages more equality and integration for people with hearing impairments.

Sign language recognition, Image processing, Deaf communication, Gesture-to-text conversion.

"Sign Language To Text Conversion Using CNN Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 4, page no.a737-a742, April-2024, Available :http://www.jetir.org/papers/JETIR2404092.pdf

"Sign Language To Text Conversion Using CNN Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 4, page no. ppa737-a742, April-2024, Available at : http://www.jetir.org/papers/JETIR2404092.pdf