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

被引:16
作者
Lamiroy, Bart [1 ]
Lopresti, Daniel [2 ]
机构
[1] Nancy Univ, LORIA, INPL, Nancy, France
[2] Lehigh Univ, Comp Sci & Engn, Bethlehem, PA 18015 USA
来源
11TH INTERNATIONAL CONFERENCE ON DOCUMENT ANALYSIS AND RECOGNITION (ICDAR 2011) | 2011年
关键词
benchmark; web services; document analysis; performance evaluation;
D O I
10.1109/ICDAR.2011.18
中图分类号
TP18 [人工智能理论];
学科分类号
140502 [人工智能];
摘要
In this paper, we present a fully operational, scalable and open architecture allowing end-to-end document analysis benchmarking without needing to develop the whole pipeline. By decomposing the analysis process into coarsegrained tasks, and by building upon community provided state-of-the art algorithms, our architecture allows any combination of elementary document analysis algorithms, regardless their running system environment, programming language or data structures. Its flexible structure makes it straightforward to plug in new algorithms, compare them to other algorithms, and observe the effects on end-to-end tasks without need to install, compile or otherwise interact with any other software than one's own.
引用
收藏
页码:42 / 47
页数:6
相关论文
共 21 条
[1]
Agam G., 2006, COMPLEX DOCUMENT IMA
[2]
[Anonymous], 1934, LOGIC SCI DISCOVERY
[3]
[Anonymous], 2010, 9 IAPR INT WORKSH DO
[4]
[Anonymous], 11 INT C DOC AN REC
[5]
BOOTH D., 2006, Web services description language (wsdl)
[6]
The OCRopus open source OCR system [J].
Breuel, Thomas M. .
DOCUMENT RECOGNITION AND RETRIEVAL XV, 2008, 6815
[7]
Jaeger S, 2006, INT C DOC REC RETR S, P1
[8]
Kanungo T., 2002, IJDAR, V4, P139
[9]
Lamiroy B., 2010, ACM INT C P SERIES I
[10]
Lamiroy B., 2011, SPIE P, V7874