A Blind Indic Script Recognizer for Multi-script Documents

Author

Pati, Peeta Basa ; Ramakrishnan, A.G.

Author_Institution

Indian Inst. of Sci., Bangalore

Volume

2

fYear

2007

fDate

23-26 Sept. 2007

Firstpage

1248

Lastpage

1252

Abstract

We report a hierarchical blind script identifier for 11 different Indian scripts. An initial grouping of the 11 scripts is accomplished at the first level of this hierarchy. At the subsequent level, we recognize the script in each group. The various nodes of this tree use different feature-classifier combinations. A database of 20,000 words of different font styles and sizes is collected and used for each script. Effectiveness of Gabor and Discrete Cosine Transform features has been independently evaluated using nearest neighbor, linear discriminant and support vector machine classifiers. The minimum and maximum accuracies obtained, using this hierarchical mechanism, are 92.2% and 97.6%, respectively.

Keywords

discrete cosine transforms; document image processing; image classification; natural language processing; support vector machines; Gabor transform; blind Indie script recognizer; discrete cosine transform; feature-classifier combinations; linear discriminant classifiers; multi-script documents; nearest neighbor classifiers; support vector machine classifiers; Biomedical imaging; Discrete cosine transforms; Filter bank; Frequency; Gabor filters; Laboratories; Nearest neighbor searches; Spatial databases; Support vector machine classification; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on

Conference_Location

Parana

ISSN

1520-5363

Print_ISBN

978-0-7695-2822-9

Type

conf

DOI

10.1109/ICDAR.2007.4377115

Filename

4377115