Publication Date: 2023/11/23
Abstract: For the Deaf and hard of hearing people, sign language is an essential form of communication. However, because it is visual in nature, it poses special difficulties for automated detection. The use of convolutional neural networks (CNNs) for sign language gesture identification is investigated in this paper. CNNs are a viable option for understanding sign language because of their impressive performance in a variety of computer vision tasks. To prepare sign language images for training and testing with a CNN model, this study explores their preparation, which includes scaling, normalization, and grayscale conversion. Multiple convolutional and pooling layers precede dense layers for classification in this TensorFlow and Keras-built model. The model was trained and validated using a sizable dataset of sign language movements that represented a wide variety of signs. For many indications, the CNN performs well, achieving accuracy levels that are comparable to those of human recognition. It highlights how deep learning approaches can help the Deaf community communicate more effectively and overcome linguistic barriers.
Keywords: Sign Language Recognition, Convolutional Neural Networks (CNNs), Visual Communication, Deaf Community, Assistive Technology, Inclusive Communication.
DOI: https://doi.org/10.5281/zenodo.10200393
PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23NOV943.pdf
REFERENCES