{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T14:58:50Z","timestamp":1769266730274,"version":"3.49.0"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T00:00:00Z","timestamp":1632268800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T00:00:00Z","timestamp":1632268800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100005619","name":"Ministerstvo Kultury","doi-asserted-by":"publisher","award":["DG18P02OVV055"],"award-info":[{"award-number":["DG18P02OVV055"]}],"id":[{"id":"10.13039\/501100005619","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001823","name":"Ministerstvo \u0160kolstv\u00ed, Ml\u00e1de\u017ee a Telov\u00fdchovy","doi-asserted-by":"publisher","award":["LQ1602"],"award-info":[{"award-number":["LQ1602"]}],"id":[{"id":"10.13039\/501100001823","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s10032-021-00387-z","type":"journal-article","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T13:02:52Z","timestamp":1632315772000},"page":"15-28","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["$$\\hbox {TG}^2$$: text-guided transformer GAN for restoring document readability and perceived quality"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3873-1672","authenticated-orcid":false,"given":"Old\u0159ich","family":"Kodym","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michal","family":"Hradi\u0161","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"387_CR1","doi-asserted-by":"publisher","unstructured":"Bal, G., Agam, G., Frieder, O., Frieder, G.: Interactive degraded document enhancement and ground truth generation. In: Yanikoglu BA, Berkner K (eds) Document Recognition and Retrieval XV, SPIE. (2008). https:\/\/doi.org\/10.1117\/12.767203","DOI":"10.1117\/12.767203"},{"key":"387_CR2","doi-asserted-by":"publisher","unstructured":"Chen, X., He, X., Yang, J., Wu, Q.: An effective document image deblurring algorithm. In: CVPR 2011. IEEE. (2011). https:\/\/doi.org\/10.1109\/cvpr.2011.5995568","DOI":"10.1109\/cvpr.2011.5995568"},{"issue":"2","key":"387_CR3","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1109\/tpami.2015.2439281","volume":"38","author":"C Dong","year":"2016","unstructured":"Dong, C., Loy, C.C., He, K., Tang, X.: Image super-resolution using deep convolutional networks. IEEE Trans. Pattern Anal. Mach. Intell. 38(2), 295\u2013307 (2016). https:\/\/doi.org\/10.1109\/tpami.2015.2439281","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"3","key":"387_CR4","doi-asserted-by":"publisher","first-page":"997","DOI":"10.1109\/tcyb.2018.2876511","volume":"50","author":"X Fang","year":"2018","unstructured":"Fang, X., Zhou, Q., Shen, J., Jacquemin, C., Shao, L.: Text image deblurring using kernel sparsity prior. IEEE Trans. Cybern. 50(3), 997\u20131008 (2018). https:\/\/doi.org\/10.1109\/tcyb.2018.2876511","journal-title":"IEEE Trans. Cybern."},{"key":"387_CR5","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. In: Ghahramani, Z., Welling, M., Cortes, C., Lawrence, N.D., Weinberger, K.Q. (eds) Advances in Neural Information Processing Systems 27, pp. 2672\u20132680. Curran Associates Inc., http:\/\/papers.nips.cc\/paper\/5423-generative-adversarial-nets.pdf (2014)"},{"key":"387_CR6","doi-asserted-by":"publisher","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification. In: Proceedings of the 23rd international conference on Machine learning\u2014ICML 2006. ACM Press (2006). https:\/\/doi.org\/10.1145\/1143844.1143891","DOI":"10.1145\/1143844.1143891"},{"key":"387_CR7","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., Courville, A.C.: Improved training of wasserstein gans. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds) Advances in Neural Information Processing Systems 30, pp. 5767\u20135777. Curran Associates Inc. (2017)"},{"key":"387_CR8","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1016\/j.patcog.2019.01.025","volume":"91","author":"S He","year":"2019","unstructured":"He, S., Schomaker, L.: DeepOtsu: Document enhancement and binarization using iterative deep learning. Pattern Recogn. 91, 379\u2013390 (2019). https:\/\/doi.org\/10.1016\/j.patcog.2019.01.025","journal-title":"Pattern Recogn."},{"key":"387_CR9","doi-asserted-by":"publisher","unstructured":"Hradi\u0161, M., Kotera, J., Zem\u010d\u00edk, P., \u0160roubek, F.: Convolutional neural networks for direct text deblurring. In: Presented at the (2015). In: Proceedings of the British Machine Vision Conference 2015, British Machine Vision Association https:\/\/doi.org\/10.5244\/c.29.6","DOI":"10.5244\/c.29.6"},{"key":"387_CR10","doi-asserted-by":"crossref","unstructured":"Hu, X., Naiel, M.A., Wong, A., Lamm, M., Fieguth, P.: Runet: A robust UNET architecture for image super-resolution. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2019)","DOI":"10.1109\/CVPRW.2019.00073"},{"key":"387_CR11","doi-asserted-by":"publisher","unstructured":"Jiao, J., Sun, J., Satoshi, N.: A convolutional neural network based two-stage document deblurring. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE (2017). https:\/\/doi.org\/10.1109\/icdar.2017.120","DOI":"10.1109\/icdar.2017.120"},{"key":"387_CR12","doi-asserted-by":"publisher","unstructured":"Kahle, P., Colutto, S., Hackl, G., Muhlberger, G.: Transkribus\u2014a service platform for transcription, recognition and retrieval of historical documents. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR). IEEE (2017). https:\/\/doi.org\/10.1109\/icdar.2017.307","DOI":"10.1109\/icdar.2017.307"},{"key":"387_CR13","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: CoRR arxiv:1812.04948 (2018)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"387_CR14","doi-asserted-by":"crossref","unstructured":"Kinoshita, K., Delcroix, M., Ogawa, A., Nakatani, T.: Text-informed speech enhancement with deep neural networks (2015)","DOI":"10.21437\/Interspeech.2015-409"},{"key":"387_CR15","doi-asserted-by":"publisher","unstructured":"Kiss, M., Hradis, M., Kodym, O.: Brno mobile OCR dataset. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE (2019). https:\/\/doi.org\/10.1109\/icdar.2019.00218","DOI":"10.1109\/icdar.2019.00218"},{"key":"387_CR16","doi-asserted-by":"publisher","unstructured":"Kupyn, O., Budzan, V., Mykhailych, M., Mishkin, D., Matas, J.: DeblurGAN: Blind motion deblurring using conditional adversarial networks. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE (2018). https:\/\/doi.org\/10.1109\/cvpr.2018.00854","DOI":"10.1109\/cvpr.2018.00854"},{"key":"387_CR17","unstructured":"Lahiri, A., Jain, A., Biswas, P.K., Mitra, P.: Improving consistency and correctness of sequence inpainting using semantically guided generative adversarial network. arXiv:1711.06106 (2017)"},{"key":"387_CR18","doi-asserted-by":"publisher","unstructured":"Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., Shi, W.: Photo-realistic single image super-resolution using a generative adversarial network. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), IEEE (2017). https:\/\/doi.org\/10.1109\/cvpr.2017.19","DOI":"10.1109\/cvpr.2017.19"},{"key":"387_CR19","unstructured":"Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., Aila, T.: Noise2Noise: Learning image restoration without clean data. In: Dy, J., Krause, A. (eds) Proceedings of the 35th International Conference on Machine Learning, PMLR, Stockholmsm\u00e4ssan, Stockholm Sweden, Proceedings of Machine Learning Research, vol.\u00a080, pp. 2965\u20132974. http:\/\/proceedings.mlr.press\/v80\/lehtinen18a.html (2018)"},{"issue":"6","key":"387_CR20","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1016\/j.patrec.2004.09.032","volume":"26","author":"CC Leung","year":"2005","unstructured":"Leung, C.C., Chan, K.S., Chan, H.M., Tsui, W.K.: A new approach for image enhancement applied to low-contrast-low-illumination IC and document images. Pattern Recogn. Lett. 26(6), 769\u2013778 (2005). https:\/\/doi.org\/10.1016\/j.patrec.2004.09.032","journal-title":"Pattern Recogn. Lett."},{"key":"387_CR21","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.21437\/Interspeech.2019-1777","volume":"2019","author":"CF Liao","year":"2019","unstructured":"Liao, C.F., Tsao, Y., Lu, X., Kawai, H.: Incorporating symbolic sequential modeling for speech enhancement. Proc. Interspeech 2019, 2733\u20132737 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-1777","journal-title":"Proc. Interspeech"},{"issue":"1\u20132","key":"387_CR22","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/s10032-018-0299-9","volume":"21","author":"D Lu","year":"2018","unstructured":"Lu, D., Huang, X., Sui, L.: Binarization of degraded document images based on contrast enhancement. Int. J. Document Anal. Recognit. (IJDAR) 21(1\u20132), 123\u2013135 (2018). https:\/\/doi.org\/10.1007\/s10032-018-0299-9","journal-title":"Int. J. Document Anal. Recognit. (IJDAR)"},{"key":"387_CR23","doi-asserted-by":"publisher","unstructured":"Madam, N.T., Kumar, S., Rajagopalan, A.N.: Unsupervised class-specific deblurring. In: Computer Vision\u2014ECCV 2018, pp. 358\u2013374. Springer International Publishing (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_22","DOI":"10.1007\/978-3-030-01249-6_22"},{"key":"387_CR24","doi-asserted-by":"publisher","unstructured":"Mujumdar, S., Gupta, N., Jain, A., Burdick, D.: Simultaneous optimisation of image quality improvement and text content extraction from scanned documents. In: 2019 International Conference on Document Analysis and Recognition (ICDAR). IEEE (2019). https:\/\/doi.org\/10.1109\/icdar.2019.00189","DOI":"10.1109\/icdar.2019.00189"},{"key":"387_CR25","doi-asserted-by":"publisher","unstructured":"Murray, R.L.: Toward a metadata standard for digitized historical newspapers. In: Proceedings of the 5th ACM\/IEEE-CS Joint Conference on Digital Libraries\u2014JCDL 2005. ACM Press (2005). https:\/\/doi.org\/10.1145\/1065385.1065459","DOI":"10.1145\/1065385.1065459"},{"key":"387_CR26","unstructured":"Mustafa, W.A., Yazid, H.: Illumination and contrast correction strategy using bilateral filtering and binarization comparison (2016)"},{"key":"387_CR27","doi-asserted-by":"publisher","unstructured":"Pan, J., Hu, Z., Su, Z., Yang, M.H.: Deblurring text images via l0-regularized intensity and gradient prior. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition. IEEE (2014). https:\/\/doi.org\/10.1109\/cvpr.2014.371","DOI":"10.1109\/cvpr.2014.371"},{"key":"387_CR28","doi-asserted-by":"publisher","unstructured":"Pandey, R.K., Ramakrishnan, A.G.: Improving the perceptual quality of document images using deep neural network, In: Advances in Neural Networks\u2014ISNN 2019. Springer International Publishing, pp. 448\u2013459 (2019). https:\/\/doi.org\/10.1007\/978-3-030-22808-8_44","DOI":"10.1007\/978-3-030-22808-8_44"},{"key":"387_CR29","doi-asserted-by":"publisher","unstructured":"Papadopoulos, C., Pletschacher, S., Clausner, C., Antonacopoulos, A.: The impact dataset of historical document images, pp. 123\u2013130 (2013). https:\/\/doi.org\/10.1145\/2501115.2501130","DOI":"10.1145\/2501115.2501130"},{"key":"387_CR30","doi-asserted-by":"crossref","unstructured":"Pathak, D., Kr\u00e4henb\u00fchl, P., Donahue, J., Darrell, T., Efros, A.: Context encoders: feature learning by inpainting (2016)","DOI":"10.1109\/CVPR.2016.278"},{"key":"387_CR31","doi-asserted-by":"publisher","unstructured":"Ramakrishnan, S., Pachori, S., Gangopadhyay, A., Raman, S.: Deep generative filter for motion deblurring. In: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW). IEEE (2017). https:\/\/doi.org\/10.1109\/iccvw.2017.353","DOI":"10.1109\/iccvw.2017.353"},{"key":"387_CR32","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., PFischer, Brox, T.: U-net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention (MICCAI), Springer, LNCS, vol 9351, pp. 234\u2013241. http:\/\/lmb.informatik.uni-freiburg.de\/Publications\/2015\/RFB15a, arXiv:1505.04597 [cs.CV] (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"issue":"11","key":"387_CR33","doi-asserted-by":"publisher","first-page":"2298","DOI":"10.1109\/TPAMI.2016.2646371","volume":"39","author":"B Shi","year":"2017","unstructured":"Shi, B., Bai, X., Yao, C.: An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(11), 2298\u20132304 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"387_CR34","doi-asserted-by":"publisher","first-page":"48","DOI":"10.3390\/jimaging5040048","volume":"5","author":"Omar Nasrudin Sulaiman","year":"2019","unstructured":"Sulaiman, Omar Nasrudin: Degraded historical document binarization: A review on issues, challenges, techniques, and future directions. J. Imaging 5(4), 48 (2019). https:\/\/doi.org\/10.3390\/jimaging5040048","journal-title":"J. Imaging"},{"key":"387_CR35","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is all you need. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds) Advances in Neural Information Processing Systems 30. Curran Associates Inc., pp. 5998\u20136008, http:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need.pdf (2017)"},{"key":"387_CR36","unstructured":"Wang, W., Xie, E., Sun, P., Wang, W., Tian, L., Shen, C., Luo, P.: Textsr: Content-aware text super-resolution guided by recognition. arXiv:1909.07113 (2019)"},{"key":"387_CR37","doi-asserted-by":"crossref","unstructured":"Yu, J., Lin, Z., Yang, J., Shen, X., Lu, X., Huang, T.S.: Generative image inpainting with contextual attention. arXiv:1801.07892 (2018)","DOI":"10.1109\/CVPR.2018.00577"},{"issue":"1","key":"387_CR38","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1109\/tci.2016.2644865","volume":"3","author":"H Zhao","year":"2017","unstructured":"Zhao, H., Gallo, O., Frosio, I., Kautz, J.: Loss functions for image restoration with neural networks. IEEE Trans. Comput. Imaging 3(1), 47\u201357 (2017). https:\/\/doi.org\/10.1109\/tci.2016.2644865","journal-title":"IEEE Trans. Comput. Imaging"},{"key":"387_CR39","doi-asserted-by":"crossref","unstructured":"Zhu, J.Y., Park, T., Isola, P., Efros, A.A.: Unpaired image-to-image translation using cycle-consistent adversarial networks. In: The IEEE International Conference on Computer Vision (ICCV) (2017)","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-021-00387-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-021-00387-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-021-00387-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,15]],"date-time":"2022-03-15T08:08:49Z","timestamp":1647331729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-021-00387-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,22]]},"references-count":39,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["387"],"URL":"https:\/\/doi.org\/10.1007\/s10032-021-00387-z","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,22]]},"assertion":[{"value":"4 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 April 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 September 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}