000131118 001__ 131118
000131118 005__ 20241220133820.0
000131118 0247_ $$2doi$$a10.1007/s11042-023-17476-2
000131118 0248_ $$2sideral$$a136709
000131118 037__ $$aART-2024-136709
000131118 041__ $$aeng
000131118 100__ $$0(orcid)0000-0003-3595-005X$$aNeji, Hala$$uUniversidad de Zaragoza
000131118 245__ $$aDoc-Attentive-GAN: attentive GAN for historical document denoising
000131118 260__ $$c2024
000131118 5060_ $$aAccess copy available to the general public$$fUnrestricted
000131118 5203_ $$aImage 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 Historical document denoising is specially challenging because there is considerable background noise or variation in contrast and illumination in handwritten literature and the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 The main objective of this work is to propose a new method for historical document denoising based on an Attentive Generative Adversarial Network (Attentive-GAN). Our proposed model for historical document denoising is named Doc-Attentive GAN , and it employs an attention map generated by a deep network to help the generator to learn and focus on the modification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 It has been trained and tested with different historical document collections such as well-known DIBCO datasets, Arabic Historical Documents from the Tunisian National Library, and Incunabula books.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.
000131118 540__ $$9info:eu-repo/semantics/openAccess$$aAll rights reserved$$uhttp://www.europeana.eu/rights/rr-f/
000131118 592__ $$a0.801$$b2023
000131118 593__ $$aMedia Technology$$c2023$$dQ1
000131118 593__ $$aSoftware$$c2023$$dQ2
000131118 593__ $$aComputer Networks and Communications$$c2023$$dQ2
000131118 593__ $$aHardware and Architecture$$c2023$$dQ2
000131118 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/acceptedVersion
000131118 700__ $$aBen Halima, Mohamed
000131118 700__ $$0(orcid)0000-0002-1279-0367$$aNogueras-Iso, Javier$$uUniversidad de Zaragoza
000131118 700__ $$aHamdani, Tarek M.
000131118 700__ $$0(orcid)0000-0003-3071-5819$$aLacasta, Javier$$uUniversidad de Zaragoza
000131118 700__ $$aChabchoub, Habib
000131118 700__ $$aAlimi, Adel M.
000131118 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf.
000131118 773__ $$g83 (2024), 55509–55525$$pMultimed. Tools Appl.$$tMultimedia Tools and Applications$$x1380-7501
000131118 8564_ $$s12066378$$uhttps://zaguan.unizar.es/record/131118/files/texto_completo.pdf$$yPostprint$$zinfo:eu-repo/semantics/openAccess
000131118 8564_ $$s1274767$$uhttps://zaguan.unizar.es/record/131118/files/texto_completo.jpg?subformat=icon$$xicon$$yPostprint$$zinfo:eu-repo/semantics/openAccess
000131118 909CO $$ooai:zaguan.unizar.es:131118$$particulos$$pdriver
000131118 951__ $$a2024-12-20-13:37:43
000131118 980__ $$aARTICLE