Style Quantification of Scanned Multi-source Digits

Author

Zhang, Xiaoli ; Nagy, George

Author_Institution

Dept. of Electr., Comput., & Syst. Eng., Rensselaer Polytech. Inst., Troy, NY

Volume

2

fYear

0

fDate

0-0 0

Firstpage

1018

Lastpage

10121

Abstract

The co-occurring patterns in a group carrying the traits of common origin are statistically dependent via an underlying style context. Exploiting style consistency in groups of patterns from multiple sources can increase OCR accuracy. The accuracy gains obtained by a style consistent classifier depend on the amount of style in isogenous (same-source) fields. We present mathematical models to quantify the amount of single-class and multi-class style using entropy, correlation and mutual information. We also demonstrate a method for style homogenization that allows testing our metrics on real data

Keywords

correlation methods; entropy; optical character recognition; pattern classification; OCR accuracy; cooccurring patterns; correlation; entropy; mutual information; scanned multisource digits; style consistent classifier; style quantification; Cost benefit analysis; Entropy; Forensics; Mathematical model; Mutual information; Optical character recognition software; Printers; Shape; Testing; Writing;

fLanguage

English

Publisher

ieee

Conference_Titel

Pattern Recognition, 2006. ICPR 2006. 18th International Conference on

Conference_Location

Hong Kong

ISSN

1051-4651

Print_ISBN

0-7695-2521-0

Type

conf

DOI

10.1109/ICPR.2006.1087

Filename

1699380