Improve the recognition of spoken Arabic letter based on statistical features

Abstract EN

-The recognition and classification of languages represent a vital factor in the computer interaction.

This paper presents Arabic Sign Language recognition, which is represented as an appealing application.

The work in this paper is based on three steps; preprocessing, feature extraction and classification (Recognition).

The statistical features have been used than the physical features, while Multilayer feed-forward neural network as classification methods.

The recognition percent is 96.33% has been gained over-perform the earlier works.

The simulation has been made by using Matlab 2015b.