Performance Evaluation Tools for Zone Segmentation and Classification (PETS)

Author

Seo, Wontaek ; Agrawal, Mudit ; Doermann, David

Author_Institution

Inst. of Adv. Comput. Studies, Univ. of Maryland, College Park, MD, USA

fYear

2010

fDate

23-26 Aug. 2010

Firstpage

503

Lastpage

506

Abstract

This paper describes a set of Performance Evaluation Tools (PETS) for document image zone segmentation and classification. The tools allow researchers and developers to evaluate, optimize and compare their algorithms by providing a variety of quantitative performance metrics. The evaluation of segmentation quality is based on the pixel-based overlaps between two sets of zones proposed by Randriamasy and Vincent. PETS extends the approach by providing a set of metrics for overlap analysis, RLE and polygonal representation of zones and introduces type-matching to evaluate zone classification. The software is available for research use.

Keywords

document image processing; image classification; image matching; image segmentation; RLE analysis; document image zone classification; document image zone segmentation; performance evaluation tool; pixel-based overlap; polygonal representation; quantitative performance metrics; segmentation quality; type-matching; Image segmentation; Performance evaluation; Pixel; Positron emission tomography; Text analysis; XML; evaluation document image segmentation detection classification;

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.2010.1123

Filename

5597427