Tifinagh Printed Character Recognition through Structural Feature Extraction

Tifinagh Printed Character Recognition through Structural Feature Extraction

Youssef Ouadid (Department of Computer Science, University Sultan Moulay Slimane, Beni Mellal, Morocco), Mohamed Fakir (Department of Computer Science, University Sultan Moulay Slimane, Beni Mellal, Morocco) and Brahim Minaoui (University Sultan Moulay Slimane, Beni Mellal, Morocco)
Copyright: © 2016 |Pages: 12
DOI: 10.4018/IJCVIP.2016070103

Abstract

In this paper a system for the recognition of printed Tifinagh characters is presented. It is divided into three main steps: preprocessing, feature extraction, and classification. Image quality is enhanced through preprocessing which are: binarization, normalization and thinning. Then the image is given to a proposed structural feature extracting algorithm where the character is divided into several geometrically sample shapes which are segments, then transformed into an undirected graph with unique coordinate of all nodes. The character is classified by matching the graph of the character and its counterpart graph which is generated from the images in the IRCAM database using an efficient spectral graph matching algorithm. Experimental results and analysis are accomplished by the use of 3267 random characters to test the effectiveness. The system shows good results in term of accuracy and CPU time.
Article Preview

1. Introduction

Optical Character Recognition system is a tool that facilitates man-machine interaction. It is a procedure that convert a text image into readable and easy to modify text by computer or similar material. Many researches has been concentrated into creating an efficient Optical Character Recognition system, especially Latina, Chinese (Mansi, 2013) and Arabic (Lorigo, 2006) characters. It is used in several areas where the work is based on the text documents, mainly in office for indexing purposes, automatic archiving of documents and banks to facilitate the reading of the amounts of checks. In the other hand, the recognition of the Amazigh characters, called Tifinagh, remains less explored.

Amazigh is a Chamito-Semitic language derived from ancient Berber. It includes a variety of dialects present from Morocco to Egypt, passing through Algeria, Tunisia, Mali, Niger and Libya. Berbers, mainly Tuaregs, use Tifinagh alphabet. It was formerly a consonantal alphabet. This alphabet has undergone modifications and variations inevitable since its origin until today. The Tifinagh characters normally written from left to right and vertically from top to bottom. Figure 1 illustrates Tifinagh characters adopted by IRCAM (Royal Institute of Amazigh Culture). It is composed of thirty-three character representing consonants and vowels. Several researches studies have been performed on the computerization of Tifinagh characters. Most of these researches are concentrated in Morocco and Algeria.

Figure 1.

Tifinagh of the Royal Institute of Amazigh Culture, IRCAM

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2019): Forthcoming, Available for Pre-Order
Volume 8: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 7: 4 Issues (2017)
Volume 6: 2 Issues (2016)
Volume 5: 2 Issues (2015)
Volume 4: 2 Issues (2014)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing