Real Time Sign Language Recognition using Knowledge Assisted Method

As we are aware that verbal communication can be hampered by speech impairment, and sign language is one of the best systems for resolving this problem. The goal of our paper is to create a system or application that can recognize sign language motions in order to reduce the gap between persons with disabilities and others, such as deaf and mute people. The suggested system uses machine learning and image processing to create a real-time system. Preprocessing photos and removing hand motions from the backdrop are both done via image processing. The 24 English alphabets are then included in a dataset created using these photos. Both a specially created dataset and live hand gestures produced by people of different ages are used to evaluate the Faster(R-CNN) that we proposed in our research. The accuracy comes near to 95%.