Performance Analysis Framework for Layout Analysis Methods
- 1 September 2007
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in Ninth International Conference on Document Analysis and Recognition (ICDAR 2007)
- Vol. 2 (15205363), 1258-1262
- https://doi.org/10.1109/icdar.2007.4377117
Abstract
This paper presents a new framework for in-depth analysis of the performance of layout analysis methods. Contrary to existing approaches aimed at evaluation or benchmarking, the proposed framework provides detailed information at various levels that can be used by method developers to identify specific problems and improve their work. Complex layouts are supported as well as the flexible configuration of goal-oriented performance analysis scenarios. The comparison of segmentation results against the ground truth is performed in a very efficient way based on a decomposition of any region shape into an interval-based description. The framework has been validated using the dataset and method results of the ICDAR2005 Page Segmentation Competition.Keywords
This publication has 12 references indexed in Scilit:
- Pixel-Accurate Representation and Evaluation of Page Segmentation in Document ImagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- ICDAR 2003 page segmentation competitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- ICDAR2005 page segmentation competitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Representation and classification of complex-shaped printed regions using white tilesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Software architecture of PSET: a page segmentation evaluation toolkitInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- An empirical measure of the performance of a document image segmentation algorithmInternational Journal on Document Analysis and Recognition (IJDAR), 2002
- Methodology for flexible and efficient analysis of the performance of page segmentation algorithmsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- PINK PANTHER: A COMPLETE ENVIRONMENT FOR GROUND-TRUTHING AND BENCHMARKING DOCUMENT PAGE SEGMENTATIONPattern Recognition, 1998
- Automated performance evaluation of document image analysis systems: Issues and practiceInternational Journal of Imaging Systems and Technology, 1996
- Automated evaluation of OCR zoningIeee Transactions On Pattern Analysis and Machine Intelligence, 1995