Automated Evaluation of OCR Zoning
IEEE Transactions on Pattern Analysis and Machine Intelligence
Empirical Performance Evaluation of Graphics Recognition Systems
IEEE Transactions on Pattern Analysis and Machine Intelligence
A Performance Evaluation Protocol for Graphics Recognition Systems
GREC '97 Selected Papers from the Second International Workshop on Graphics Recognition, Algorithms and Systems
The Second International Graphics Recognition Contest - Raster to Vector Conversion: A Report
GREC '97 Selected Papers from the Second International Workshop on Graphics Recognition, Algorithms and Systems
DAN: An Automatic Segmentation and Classification Engine for Paper Documents
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
A Ground-Truthing Tool for Layout Analysis Performance Evaluation
DAS '02 Proceedings of the 5th International Workshop on Document Analysis Systems V
First International Newspaper Segmentation Contest
ICDAR '01 Proceedings of the Sixth International Conference on Document Analysis and Recognition
ICDAR '05 Proceedings of the Eighth International Conference on Document Analysis and Recognition
Text line detection in handwritten documents
Pattern Recognition
Text line and word segmentation of handwritten documents
Pattern Recognition
Automatic table detection in document images
ICAPR'05 Proceedings of the Third international conference on Advances in Pattern Recognition - Volume Part I
Ground truth for layout analysis performance evaluation
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
Performance comparison of six algorithms for page segmentation
DAS'06 Proceedings of the 7th international conference on Document Analysis Systems
| Hi-index | 0.01 |
There is a significant need to objectively evaluatelayout analysis (page segmentation and regionclassification) methods. This paper describes the PageSegmentation Competition (modus operandi, dataset andevaluation criteria) held in the context of ICDAR2003and presents the results of the evaluation of the candidatemethods. The main objective of the competition was toevaluate such methods using scanned documents fromcommonly-occurring publications. The results indicatethat although methods seem to be maturing, there is still aconsiderable need to develop robust methods that dealwith everyday documents.