Arabic sign language recognition using neural network and graph matching techniques

Authors:
M. Saied Abdel-Wahab;Magdy Aboul-Ela;Ahmed Samir
Affiliations:
Faculty of Computers and Information, Ain-Shams University, Cairo, Egypt;Sadat Academy for Management Sciences, Maadi, Cairo, Egypt;Faculty of Computers and Information, Ain-Shams University, Cairo, Egypt
Venue:
AIC'06 Proceedings of the 6th WSEAS International Conference on Applied Informatics and Communications
Year:
2006

Citing 2
Cited 1

Fingerprint classification: a review

Pattern Analysis & Applications
Graph partition for matching

GbRPR'03 Proceedings of the 4th IAPR international conference on Graph based representations in pattern recognition

A proposed PCNN features quality optimization technique for pose-invariant 3D Arabic sign language recognition

Applied Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sign Language Recognition (SLR) is the most structured field in gesture recognition applications, such that each gesture has assigned a well-defined meaning. SLR can be defined as a translation system, which translates the signs, performed by deaf and dump people to the natural language. The proposed system aims to recognize Arabic sign language (ASL) and converts it to the natural Arabic language. Artificial Neural Network (ANN) is a very powerful tool for pattern recognition applications. The ANN model is a multistage classifier that guarantees the ability generalization. Graphs are a general and powerful data structure useful for the representation of various objects and concepts. This work focuses on how a sequence of gestures can be represented as a graph. Also how the input gestures sequence is segmented and classified. This work addresses the scalability objective.