Paper Info
Title
Fractal-based system for Arabic/Latin, printed/handwritten script identification
Abstract
In this paper, we present multilingual automatic identification of Arabic and Latin in both handwritten and printed script. The proposed scheme is based, Firstly, on morphological transform of line text images, secondly on fractal analysis features of both (i): original texture of 2-D images, (ii): vertical and horizontal profile projection. We used two techniques to obtain only 12 features based on fractal multidimension. The proposed system has been tested for 1000 prototypes with various typefaces, scriptors styles and sizes. The accuracy discrimination rate is about of 96.64% by using KNN, and 98.72% by using RBF. Experimental results show the importance of the proposed approach.
Year
DOI
Venue
2008
10.1109/ICPR.2008.4761838
ICPR
Keywords
Field
DocType
feature extraction,fractals,handwriting recognition,image texture,linguistics,natural languages,radial basis function networks,text analysis,transforms,Arabic,K-nearest neighbour,KNN,Latin,RBF,fractal-based system,handwritten script identification,image texture,line text image,morphological transform,multilingual automatic identification,printed script identification,radial basis function
Fractal analysis,Computer vision,Pattern recognition,Computer science,Image texture,Fractal,Handwriting recognition,Feature extraction,Natural language,Artificial intelligence,Statistical classification,Typeface
Conference
ISSN
Citations 
PageRank 
1051-4651
11
0.57
References 
Authors
17
4
Name
Order
Citations
PageRank
Sami Ben Moussa1331.80
Abderrazak Zahour228214.83
Abdellatif Benabdelhafid3384.08
Mohamed Adel Alimi41947217.16