Arabic Font Recognition Based on a Texture Analysis

Author

Jaiem, Faten Kallel ; Kanoun, Slim ; Eglin, Veronique

Author_Institution

MIRACL Lab., Univ. of Sfax, Sfax, Tunisia

fYear

2014

fDate

1-4 Sept. 2014

Firstpage

673

Lastpage

677

Abstract

Existing works on the font recognition and based on texture analysis often used Gray Level Cooccurence Matrix (GLCM), Gabor Filters (GF) and wavelet. In this paper, we use Steer able Pyramid (SP) for texture analysis of Arabic homogeneous and normalized text block in order to font recognition. In this frameworks, we use K Nearest Neighbors (KNN) and Back-propagation Artificial Neural Network (BpANN) for classification. The Obtained experimental results on the APTID/MF database (Arabic Printed Text Image/ Multi-Font) are encouragents.

Keywords

backpropagation; feature extraction; image classification; image texture; natural language processing; neural nets; APTID/MF database; Arabic Printed Text Image/MultiFont database; Arabic font recognition; Arabic homogeneous normalized text block; BpANN; KNN; SP; backpropagation artificial neural network; data classification; k-nearest neighbors; steerable pyramid; texture analysis; Feature extraction; Filter banks; Image recognition; Text recognition; Wavelet transforms; Arabic Font recognition; The Back-propagation Artificial Neural Network; steerable pyramids; texture Analysis technique;

fLanguage

English

Publisher

ieee

Conference_Titel

Frontiers in Handwriting Recognition (ICFHR), 2014 14th International Conference on

Conference_Location

Heraklion

ISSN

2167-6445

Print_ISBN

978-1-4799-4335-7

Type

conf

DOI

10.1109/ICFHR.2014.118

Filename

6981097