Title
Page Segmentation Competition
Abstract
There is an established need for objective evaluation of layout analysis methods, in realistic circumstances. This paper describes the Page Segmentation Competition (modus operandi, dataset and evaluation criteria) held in the context of ICDAR2005 and presents the results of the evaluation of four candidate methods. The main objective of the competition was to compare the performance of such methods using scanned documents from commonlyoccurring publications. The results indicate that although methods seem to be maturing, there is still a considerable need to develop robust methods that deal with everyday documents.
Year
DOI
Venue
2005
10.1109/ICDAR.2005.184
International Conference on Document Analysis and Recognition
Keywords
Field
DocType
everyday document,objective evaluation,layout analysis method,evaluation criterion,page segmentation competition,candidate method,established need,commonlyoccurring publication,main objective,considerable need,image segmentation
Computer vision,Scale-space segmentation,Information retrieval,Document image processing,Image texture,Computer science,Segmentation,Segmentation-based object categorization,Image segmentation,Artificial intelligence
Conference
ISSN
ISBN
Citations 
1520-5363
0-7695-2420-6
27
PageRank 
References 
Authors
2.19
11
3
Name
Order
Citations
PageRank
Apostolos Antonacopoulos137836.45
David Bridson21059.12
Basilios Gatos319317.36