Sign Language Recognition Using Template Matching Technique

Abstract

There is an absence of communication with deaf people in our society. To overcome this barrier the introduction of Sign Language (SL) took place. To convey meaning to normal people, sign language makes use of patterns that are visually transmitted sign patterns. Sign language is also useful for people suffering with Autism Spectrum Disorder (ASD). Normal people cannot understand the signs used by deaf, as they do not know the meaning of a particular sign. The system proposed here aims at solving this problem. This system uses a camera, which captures various gestures of the hand. Then, processing of the image takes place by using various algorithms. First, pre-processing of the image takes place. Then, determination of edges occurs by using an edge detection algorithm. Finally, a template-matching algorithm identifies the sign and display the text. As the output is text, one can easily interpret the meaning of a particular sign. This also curtails the difficulty to communicate with the deaf. The implementation of the system is by using OpenCV-Python. The system uses various libraries.