Sign Language Hand Gesture Identification Using Yolov3

The community of hearing and speech-impaired people has been dependent on sign language as a medium to communicate with people. It has always been difficult to communicate between a verbally impaired person and a normal person. The Sign Language Identifier will be very essential in communicating with deaf people. It will help people to communicate with verbally impaired people by detecting the signs and providing the output in real time. The model is based on You Only Look Once(YOLO). We would be building the model with Yolov3 version. The existing recognition systems are less reliable as they detect letters and take time to make a single word or they detect very few words. Our model will solve this problem as it will recognize words directly. The dataset will be built using LabelImg software and detect sign language through a live feed. The system is a Graphical User Interface (GUI) that is built by drag and drop functionality through PAGE tool. The identification of signs will take place by two methods, one by uploading an image and the other through a live feed. These images and live inputs will be taken by using OpenCV.