Fractal and Multi-Fractal Dimensions for Farsi/Arabic Font Type and Size Recognition

Author

Hajiannezhad, Akram Alsadat ; Mozaffari, Saeed

Author_Institution

Electr. & Comput. Eng. Dept., Semnan Univ., Semnan, Iran

fYear

2011

fDate

16-17 Nov. 2011

Firstpage

1

Lastpage

4

Abstract

In this paper, a new method based on fractal geometry is proposed for Farsi/Arabic font recognition. The feature extraction does not depend on the document contents which considers font recognition problem as texture identification task The main features are obtained by combining the BCD, DCD, and DLA techniques. Dataset includes 2000 samples of 10 typefaces, each containing four sizes. The average recognition rates obtained for these 10 fonts and 4 sizes (40 classes) using RBF and KNN classifiers are 96% and 91% respectively. The dimension of feature vectors extracted by the proposed fractal approach is very low. This property obviates the need for numerous training samples. Experimental results show that this algorithm is robust against skew. Simultaneously identifying type and size of the font is the most important innovation of this paper.

Keywords

document image processing; feature extraction; fractals; image classification; image texture; optical character recognition; radial basis function networks; BCD technique; DCD technique; DLA technique; Farsi-Arabic font recognition problem; KNN classifier; RBF classifier; document content; feature extraction; feature vector dimension; fractal geometry; multifractal dimension; size recognition rate; texture identification task; Classification algorithms; Feature extraction; Fractals; Linear regression; Mathematical model; Optical character recognition software; Robustness;

fLanguage

English

Publisher

ieee

Conference_Titel

Machine Vision and Image Processing (MVIP), 2011 7th Iranian

Conference_Location

Tehran

Print_ISBN

978-1-4577-1533-4

Type

conf

DOI

10.1109/IranianMVIP.2011.6121597

Filename

6121597