• Krupa Gawde
• Smita Kadam
• Vanita Varadkar
• Ruchi Mhaddalkar
• Swapnil Kadam

Sign language serves as a communication bridge between normal and hard-of-hearing communities. People with difficulty communicating through speech rely on sign language to exchange language in society and with other people. Developing a sign language recognition system fills the communication gaps and enhances accessibility. Sign language recognition is a tool that can recognize and interpret hand gestures and convert them into text. Sign Language Recognition (SLR) systems take input from non-native English speakers and put it into a form for normal people. In this paper, we present an approach for real-time American Sign Language(ASL) recognition leveraging computer vision techniques and machine learning algorithms. Our system utilizes convolutional neural network (CNN) architecture for feature extraction and to achieve high accuracy. In addition, we created our dataset to train and evaluate our model, containing 2990 ASL characters in all. After training the model using TensorFlow, the CNN model outperformed the pre-trained model on the American Sign Language (ASL) dataset. The proposed system achieves effectiveness making it suitable for practical application in education and communication aids for the deaf and hard-of-hearing individuals.

ASL, Computer Vision, Tensor Flow, CNN

"EMPOWERING INCLUSIVE COMMUNICATION: SIGN LANGUAGE RECOGNITION THROUGH COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 3, page no.i18-i25, March-2024, Available :http://www.jetir.org/papers/JETIR2403804.pdf

"EMPOWERING INCLUSIVE COMMUNICATION: SIGN LANGUAGE RECOGNITION THROUGH COMPUTER VISION", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 3, page no. ppi18-i25, March-2024, Available at : http://www.jetir.org/papers/JETIR2403804.pdf