Evaluation of SVM, MLP and GMM Classifiers for Layout Analysis of Historical Documents

Author

Hao Wei ; Baechler, Micheal ; Slimane, Fouad ; Ingold, Rolf

Author_Institution

Dept. of Inf., Univ. of Fribourg, Fribourg, Switzerland

fYear

2013

fDate

25-28 Aug. 2013

Firstpage

1220

Lastpage

1224

Abstract

This paper presents a comparison between three classifiers based on Support Vector Machines, Multi-Layer Perceptrons and Gaussian Mixture Models respectively to detect physical structure of historical documents. Each classifier segments a scaled image of historical document into four classes, i.e., areas of periphery, background, text and decoration. We evaluate them on three data sets of historical documents. Depending on data sets, the best classification rates obtained vary from 90.35% to 97.47%.

Keywords

Gaussian processes; document image processing; history; image classification; image segmentation; multilayer perceptrons; object detection; support vector machines; GMM classifier; Gaussian mixture model; MLP classifier; SVM classifier; background area; classification rates; decoration area; historical document physical structure detection; historical documents layout analysis; multilayer perceptrons; periphery area; scaled image segmentation; support vector machines; text area; Feature extraction; Image segmentation; Layout; Support vector machines; Text analysis; Training; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Document Analysis and Recognition (ICDAR), 2013 12th International Conference on

Conference_Location

Washington, DC

ISSN

1520-5363

Type

conf

DOI

10.1109/ICDAR.2013.247

Filename

6628808