Fusion of VGG16 and ResNet50 for Enhanced Sign Language Recognition

Sign language recognition (SLR) enables improved communication for people who are deaf or hard of hearing. This study examines how two popular deep learning models, VGG16 and ResNet50, perform in SLR tasks. By applying VGG16 and ResNet50, we achieved high accuracy in recognizing sign language gestures, reaching 99.92% and 99.95%, respectively. Our findings demonstrate that these models can reliably interpret hand movements and gestures, enhancing communication for sign language users. This research leverages advanced deep learning techniques to improve SLR systems, opening new opportunities for accessibility and inclusive communication.