Sciweavers

54 search results - page 2 / 11
» Automatic Ground-truth Generation for Document Image Analysi...
Sort
View
ICDAR
2003
IEEE
13 years 10 months ago
Evaluating SEE - A Benchmarking System for Document Page Segmentation
The decomposition of a document into segments such as text regions and graphics is a significant part of the document analysis process. The basic requirement for rating and impro...
Stefan Agne, Andreas Dengel, Bertin Klein
IPM
2006
84views more  IPM 2006»
13 years 5 months ago
Qualitative evaluation of automatic assignment of keywords to images
In image retrieval, most systems lack user-centred evaluation since they are assessed by some chosen ground truth dataset. The results reported through precision and recall assess...
Chih-Fong Tsai, Kenneth McGarry, John Tait
ICDAR
2007
IEEE
13 years 7 months ago
Automatic Ground-truth Generation for Document Image Analysis and Understanding
Performance evaluation for document image analysis and understanding is a recurring problem. Many groundtruthed document image databases are now used to evaluate general algorithm...
Pierre Héroux, Eugen Barbu, Sébastie...
MICCAI
2008
Springer
14 years 6 months ago
A Bayesian Approach for Liver Analysis: Algorithm and Validation Study
Abstract. We present a new method for the simultaneous, nearly automatic segmentation of liver contours, vessels, and metastatic lesions from abdominal CTA scans. The method repeat...
Moti Freiman, Ofer Eliassaf, Yoav Taieb, Leo Jo...
ICDAR
2009
IEEE
14 years 3 days ago
A New Arabic Printed Text Image Database and Evaluation Protocols
We report on the creation of a database composed of images of Arabic Printed words. The purpose of this database is the large-scale benchmarking of openvocabulary, multi-font, mul...
Fouad Slimane, Rolf Ingold, Slim Kanoun, Adel M. A...