DocumentCode
3020605
Title
Logical labeling of Arabic newspapers using artificial neural nets
Author
Hadjar, Karim ; Ingold, Rolf
Author_Institution
DIUF, Fribourg Univ., Switzerland
fYear
2005
fDate
29 Aug.-1 Sept. 2005
Firstpage
426
Abstract
Logical structure analysis is an important phase in the process of document image understanding. In this paper we propose a learning-based method to label logical components on Arabic newspaper documents. The labeling is driven by artificial neural nets. Each one is specialized in a document class. The first prototype of LUNET has been tested on a set of Arabic newspapers of three document classes. Some promising experimental results are reported.
Keywords
document image processing; learning (artificial intelligence); neural nets; text analysis; Arabic newspaper document; LUNET; artificial neural net; document image process; learning-based method; logical labeling method; logical structure analysis; Artificial neural networks; Image analysis; Information retrieval; Labeling; Learning systems; Natural languages; Planets; Prototypes; Testing; Text analysis;
fLanguage
English
Publisher
ieee
Conference_Titel
Document Analysis and Recognition, 2005. Proceedings. Eighth International Conference on
ISSN
1520-5263
Print_ISBN
0-7695-2420-6
Type
conf
DOI
10.1109/ICDAR.2005.155
Filename
1575582
Link To Document