Intelligent Sign Language Recognition Using Image Processing Techniques: A Case of Hausa Sign Language

Abstract

Hausa sign language (HSL) is one of the main sign language in Nigeria. It is a means of communication medium among deaf-mute Hausas in northern Nigeria. HSL includes static and dynamic hand gestures. In this paper we present an intelligent recognition of static, manual and non-manual HSL using a Particle Swarm Optimization (PSO) to enhanced Fourier descriptor. A vision-based approach was used. A Red Green Blue (RGB) digital camera was used for image acquisition and Fourier descriptor was used for features extraction. The features extracted were enhanced by PSO and fed into artificial neural network (ANN) which was used for classification. High average recognition accuracy of 93.9% was achieved; hence, intelligent recognition of HSL was successful.