Static and Dynamic Hand Gesture Recognition for Indian Sign Language

Sign language recognition offers better types of assistance to the hard of hearing as it avoids the gap of communication between the deaf and mutes and the remaining people in the society. Hand signals, the essential mode of communication via gestures correspondence, plays a critical part in improving communication through gestures. Approaches for image detection, analysis and classification are available in glut, but the distinction between such approaches continues to be esoteric. It is essential that proper distinctions between such techniques should be interpreted and they should be analyzed. Standard Indian Sign Language (ISL) images of a person's hand photographed under several different environmental conditions are taken as the dataset. In this work, the system has been designed and developed which can recognize gestures in front of a web camera. The main aim is to acknowledge and classify hand gestures to their correct which means with the most accuracy doable. A unique approach for same has been planned and a few different wide standard models have compared with it. The novel model is made using canny edge detection, dilation, threshold and ORB. The preprocessed information is passed through many classifiers to draw effective results. The accuracy of the new models has been found considerably higher than the prevailing model.