DocumentCode
3439942
Title
Texture approach for nets extraction application to old Arab newspapers images structuring
Author
Charrada, Mohamed Aymen ; Ben Amara, Najoua Essoukri
Author_Institution
Adv. Syst. in Electr. Eng. Res. unit (SAGE), Nat. Eng. Sch. of Sousse, Sousse, Tunisia
fYear
2012
fDate
15-18 Oct. 2012
Firstpage
212
Lastpage
216
Abstract
In this paper, we give an overview on approaches for nets extraction from printed documents. We present also our contribution to this area operating on historical Arab periodicals. The developed method is based on Gabor filters exploration followed by post-processing steps. It allows the extraction of different nets types such as slightly erased lines or lines with inclinations and curvatures. The various tests and experiments were performed on images database obtained from historical documents with complex structure, collected from various newspapers coming from the Tunisian National Library archives. The obtained results show many interesting perspectives.
Keywords
Gabor filters; document image processing; feature extraction; image texture; publishing; visual databases; Arab newspapers image structuring; Gabor filter; Tunisian National Library archives; historical Arab periodical; image database; line curvature; line inclination; nets extraction application; printed document; slightly erased line; texture approach; Artificial intelligence; Electrical engineering; Image databases; Image resolution; Image segmentation; US Department of Defense; Gabor filters; Segmentation; degradations; historical Arab periodicals; post-processing;
fLanguage
English
Publisher
ieee
Conference_Titel
Image Processing Theory, Tools and Applications (IPTA), 2012 3rd International Conference on
Conference_Location
Istanbul
ISSN
2154-5111
Print_ISBN
978-1-4673-2585-1
Type
conf
DOI
10.1109/IPTA.2012.6469530
Filename
6469530
Link To Document