Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers
Joint Authors
Obaidullah, Sk Md
Mondal, Anamika
Das, Nibaran
Roy, Kaushik
Source
Applied Computational Intelligence and Soft Computing
Issue
Vol. 2014, Issue 2014 (31 Dec. 2014), pp.1-12, 12 p.
Publisher
Hindawi Publishing Corporation
Publication Date
2014-12-07
Country of Publication
Egypt
No. of Pages
12
Main Subjects
Information Technology and Computer Science
Abstract EN
Identification of script from document images is an active area of research under document image processing for a multilingual/ multiscript country like India.
In this paper the real life problem of printed script identification from official Indian document images is considered and performances of different well-known classifiers are evaluated.
Two important evaluating parameters, namely, AAR (average accuracy rate) and MBT (model building time), are computed for this performance analysis.
Experiment was carried out on 459 printed document images with 5-fold cross-validation.
Simple Logistic model shows highest AAR of 98.9% among all.
BayesNet and Random Forest model have average accuracy rate of 96.7% and 98.2% correspondingly with lowest MBT of 0.09 s.
American Psychological Association (APA)
Obaidullah, Sk Md& Mondal, Anamika& Das, Nibaran& Roy, Kaushik. 2014. Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers. Applied Computational Intelligence and Soft Computing،Vol. 2014, no. 2014, pp.1-12.
https://search.emarefa.net/detail/BIM-1015259
Modern Language Association (MLA)
Obaidullah, Sk Md…[et al.]. Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers. Applied Computational Intelligence and Soft Computing No. 2014 (2014), pp.1-12.
https://search.emarefa.net/detail/BIM-1015259
American Medical Association (AMA)
Obaidullah, Sk Md& Mondal, Anamika& Das, Nibaran& Roy, Kaushik. Script Identification from Printed Indian Document Images and Performance Evaluation Using Different Classifiers. Applied Computational Intelligence and Soft Computing. 2014. Vol. 2014, no. 2014, pp.1-12.
https://search.emarefa.net/detail/BIM-1015259
Data Type
Journal Articles
Language
English
Notes
Includes bibliographical references
Record ID
BIM-1015259