Noise Tolerant Script Identification of Printed Oriental and English Documents Using a Downgraded Pixel Density Feature

Author

Wang, Ning ; Lam, Louisa ; Suen, Ching Y.

Author_Institution

Centre for Pattern Recognition & Machine Intell., Concordia Univ., Montreal, QC, Canada

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

2037

Lastpage

2040

Abstract

Document Script Identification (DSI) is a very useful application in document processing. This paper presents a method for this application that uses a new noise tolerant feature, the Downgraded Pixel Density feature. Compared to other features widely used in existing DSI solutions, this new feature is much more robust to variations in slant, font and style of printed documents. Experimental results show that the method achieves promising identification performances.

Keywords

document image processing; feature extraction; natural language processing; DSI; document processing; document script identification; downgraded pixel density feature; noise tolerant feature; noise tolerant script identification; printed English documents; printed oriental documents; Artificial neural networks; Databases; Feature extraction; Pixel; Principal component analysis; Support vector machines; Training; document analysis; downgraded pixel density feature; script identification;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition (ICPR), 2010 20th International Conference on

Conference_Location

Istanbul

ISSN

1051-4651

Print_ISBN

978-1-4244-7542-1

Type

conf

DOI

10.1109/ICPR.2010.502

Filename

5595914