A rotation-robust script identification based on BEMD and LBP

Author

Pan, Jianjia ; Tang, Yuanyan

Author_Institution

Dept. of Comput. Sci., Hong Kong Baptist Univ., Hong Kong, China

fYear

2011

fDate

10-13 July 2011

Firstpage

165

Lastpage

170

Abstract

Script identification is very important part to develop the scripts OCR systems. In this paper, we proposed a new algorithm for script identification based on the global and local texture of document images. The bidimensional empirical mode decomposition (BEMD) method is used to decompose the image to some components (IMFs) and then the Local Binary Patterns (LBP) method is used to detect the features. Experiments shown the recognition rate based on BEMD-LBP is as well as the LBPV and wavelet based energy feature in 0 angles. At the same time, for the different angles rotation script, the BEMD-LBP feature present some robust adaptive to the rotation script.

Keywords

document image processing; feature extraction; image texture; optical character recognition; singular value decomposition; wavelet transforms; BEMD; LBFV; LBP; OCR systems; angles rotation script; bidimensional empirical mode decomposition; document images; feature detection; global texture; local binary patterns; local texture; rotation-robust identification; script identification; wavelet transform; Feature extraction; Kernel; Nickel; Support vector machines; Empirical mode decomposition (EMD); Local Binary Patterns; Script identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Wavelet Analysis and Pattern Recognition (ICWAPR), 2011 International Conference on

Conference_Location

Guilin

ISSN

2158-5695

Print_ISBN

978-1-4577-0283-9

Type

conf

DOI

10.1109/ICWAPR.2011.6014479

Filename

6014479