000109649 001__ 109649 000109649 005__ 20230519145424.0 000109649 0247_ $$2doi$$a10.2991/IJCIS.D.210407.001 000109649 0248_ $$2sideral$$a125504 000109649 037__ $$aART-2021-125504 000109649 041__ $$aeng 000109649 100__ $$aNeji, H. 000109649 245__ $$aBlur2sharp: A gan-based model for document image deblurring 000109649 260__ $$c2021 000109649 5060_ $$aAccess copy available to the general public$$fUnrestricted 000109649 5203_ $$aThe advances in mobile technology and portable cameras have facilitated enormously the acquisition of text images. However, the blur caused by camera shake or out-of-focus problems may affect the quality of acquired images and their use as input for optical character recognition (OCR) or other types of document processing. This work proposes an end-to-end model for document deblurring using cycle-consistent adversarial networks. The main novelty of this work is to achieve blind document deblurring, i.e., deblurring without knowledge of the blur kernel. Our method, named “Blur2Sharp CycleGAN, ” generates a sharp image from a blurry one and shows how cycle-consistent generative adversarial networks (CycleGAN) can be used in document deblurring. Using only a blurred image as input, we try to generate the sharp image. Thus, no information about the blur kernel is required. In the evaluation part, we use peak signal to noise ratio (PSNR) and structural similarity index (SSIM) to compare the deblurring images. The experiments demonstrate a clear improvement in visual quality with respect to the state-of-the-art using a dataset of text images. 000109649 536__ $$9info:eu-repo/grantAgreement/ES/DGA/T59-20R 000109649 540__ $$9info:eu-repo/semantics/openAccess$$aby-nc$$uhttp://creativecommons.org/licenses/by-nc/3.0/es/ 000109649 590__ $$a2.259$$b2021 000109649 592__ $$a0.492$$b2021 000109649 594__ $$a3.4$$b2021 000109649 591__ $$aCOMPUTER SCIENCE, INTERDISCIPLINARY APPLICATIONS$$b79 / 112 = 0.705$$c2021$$dQ3$$eT3 000109649 593__ $$aComputer Science (miscellaneous)$$c2021$$dQ2 000109649 591__ $$aCOMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE$$b102 / 146 = 0.699$$c2021$$dQ3$$eT3 000109649 593__ $$aComputational Mathematics$$c2021$$dQ2 000109649 655_4 $$ainfo:eu-repo/semantics/article$$vinfo:eu-repo/semantics/publishedVersion 000109649 700__ $$aHalima, M.B. 000109649 700__ $$aHamdani, T.M. 000109649 700__ $$0(orcid)0000-0002-1279-0367$$aNogueras-Iso, J.$$uUniversidad de Zaragoza 000109649 700__ $$aAlimi, A.M. 000109649 7102_ $$15007$$2570$$aUniversidad de Zaragoza$$bDpto. Informát.Ingenie.Sistms.$$cÁrea Lenguajes y Sistemas Inf. 000109649 773__ $$g14, 1 (2021), 1315-1321$$pInt. j. comput. intell. syst.$$tInternational Journal of Computational Intelligence Systems$$x1875-6891 000109649 8564_ $$s3088074$$uhttps://zaguan.unizar.es/record/109649/files/texto_completo.pdf$$yVersión publicada 000109649 8564_ $$s2671068$$uhttps://zaguan.unizar.es/record/109649/files/texto_completo.jpg?subformat=icon$$xicon$$yVersión publicada 000109649 909CO $$ooai:zaguan.unizar.es:109649$$particulos$$pdriver 000109649 951__ $$a2023-05-18-14:10:44 000109649 980__ $$aARTICLE