Bridging the Gap with MobileNetV2 : A Framework for ASL Gesture Translation

This paper presents a real-time American Sign Language (ASL) translation using MobileNetV2, a lightweight convolutional neural network model American Sign Language, a mode of communication for the deaf and mute community, that requires efficient and accurate translation methods to bridge the communication gap between American Sign Language (ASL) users and the hearing population. The model is trained on a dataset of American Sign Language signs and evaluated for its accuracy in recognizing and translating individual signs and gestures. The results demonstrate that MobileNetV2 can achieve a good level of accuracy of 84.56%, with a reduced model size, which makes it suitable for practical applications in sign language translation.