Skip to Main content Skip to Navigation
New interface
Conference papers

An Open Architecture for End-to-End Document Analysis Benchmarking

Bart Lamiroy 1 Daniel Lopresti 2 
1 QGAR - Querying Graphics through Analysis and Recognition
LORIA - Laboratoire Lorrain de Recherche en Informatique et ses Applications
Abstract : In this paper we present a fully operational, scalable and open architecture allowing to perform end-to-end document analysis benchmarking without needing to develop the whole pipeline. By decomposing the whole analysis process into coarse grained tasks, and by building upon community provided state-of-the art algorithms, our architecture allows virtually any combination of elementary document analysis algorithms, regardless their running system environment, programming language or data structures. Its flexible structure makes it very straightforward to plug in new experimental algorithms, compare them to equivalent other algorithms, and observe its effects on end-to-end tasks without need to install, compile or otherwise interact with any other software than one's own.
Document type :
Conference papers
Complete list of metadata
Contributor : Bart Lamiroy Connect in order to contact the contributor
Submitted on : Tuesday, July 12, 2011 - 8:44:27 PM
Last modification on : Friday, February 26, 2021 - 3:28:08 PM
Long-term archiving on: : Thursday, March 30, 2017 - 1:11:09 PM


Files produced by the author(s)




Bart Lamiroy, Daniel Lopresti. An Open Architecture for End-to-End Document Analysis Benchmarking. 11th International Conference on Document Analysis and Recognition - ICDAR 2011, International Association for Pattern Recognition, Sep 2011, Beijing, China. pp.42-47, ⟨10.1109/ICDAR.2011.18⟩. ⟨inria-00598907v2⟩



Record views


Files downloads