131118 20260113073116.0 doi 10.1007/s11042-023-17476-2 sideral 136709 ART-2024-136709 eng (orcid)0000-0003-3595-005X Neji, Hala Universidad de Zaragoza Doc-Attentive-GAN: attentive GAN for historical document denoising 2024 Access copy available to the general public Unrestricted Image denoising attempts to restore images that have been degraded. Historical document denoising is specially challenging because there is considerable background noise or variation in contrast and illumination in handwritten literature and the first times of the printing press. The main objective of this work is to propose a new method for historical document denoising based on an Attentive Generative Adversarial Network (Attentive-GAN). Our proposed model for historical document denoising is named Doc-Attentive GAN , and it employs an attention map generated by a deep network to help the generator to learn and focus on the modification between the target image and its noisy version. It has been trained and tested with different historical document collections such as well-known DIBCO datasets, Arabic Historical Documents from the Tunisian National Library, and Incunabula books. The experiments demonstrate a clear improvement in the visual quality of the images obtained by Doc-Attentive-GAN with respect to the state-of-the-art. info:eu-repo/semantics/openAccess All rights reserved http://www.europeana.eu/rights/rr-f/ 0.777 2024 Media Technology 2024 Q1 Software 2024 Q2 Computer Networks and Communications 2024 Q2 Hardware and Architecture 2024 Q2 7.7 2024 info:eu-repo/semantics/article info:eu-repo/semantics/acceptedVersion Ben Halima, Mohamed (orcid)0000-0002-1279-0367 Nogueras-Iso, Javier Universidad de Zaragoza Hamdani, Tarek M. (orcid)0000-0003-3071-5819 Lacasta, Javier Universidad de Zaragoza Chabchoub, Habib Alimi, Adel M. 5007 570 Universidad de Zaragoza Dpto. Informát.Ingenie.Sistms. Área Lenguajes y Sistemas Inf. 83 (2024), 55509–55525 Multimed. Tools Appl. Multimedia Tools and Applications 1380-7501 12066378 http://zaguan.unizar.es/record/131118/files/texto_completo.pdf Postprint info:eu-repo/date/embargoEnd/2024-11-17 1274767 http://zaguan.unizar.es/record/131118/files/texto_completo.jpg?subformat=icon icon Postprint info:eu-repo/date/embargoEnd/2024-11-17 oai:zaguan.unizar.es:131118 articulos driver 2026-01-12-12:38:05 ARTICLE