Gesture Recognition for American Sign Language Using Pytorch and Convolutional Neural Network

Human-computer interaction (HCI) is the most prevalent topic of active research due to the demand for machine learning and computer vision. American Sign Language (ASL) is one of the most popular languages used by deaf and dumb people in the world. The deaf and dumb people use hand gestures to communicate. Hand gestures vary from person to person in shape, size, scale, and image quality. Hence, nonlinearity exists in this problem. In the area of image processing, there has been tremendous progress made recently, and it's proven that neural networks have numerous applications in interpreting sign language. The recognition of ASL in real-time motion is employed using an efficient artificial intelligence tool, and Convolutional Neural Network (CNN) has been proposed in this work. The dataset of 27,455 images of 25 English alphabets has been used to train and validate our model. The model is tested on 7172 images which were divided into many classes. The maximum validation accuracy of the model with enhanced data was found to be 99.8% which is better than many existing methods in real-time motion.