{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:44:07Z","timestamp":1775277847253,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T00:00:00Z","timestamp":1716336000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T00:00:00Z","timestamp":1716336000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s10032-024-00476-9","type":"journal-article","created":{"date-parts":[[2024,5,22]],"date-time":"2024-05-22T12:01:36Z","timestamp":1716379296000},"page":"433-446","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Am I readable? Transfer learning based document image rectification"],"prefix":"10.1007","volume":"27","author":[{"given":"Pooja","family":"Kumari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sukhendu","family":"Das","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,5,22]]},"reference":[{"issue":"12","key":"476_CR1","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan, V., Kendall, A., Cipolla, R.: Segnet: a deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans. Pattern Anal. Mach. Intell. 39(12), 2481\u20132495 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"476_CR2","doi-asserted-by":"crossref","unstructured":"Bosch, M., Foster, K., Christie, G., Wang, S., Hager, G.\u00a0D., Brown, M. Semantic stereo for incidental satellite images. In: 2019 IEEE Winter Conference on Applications of Computer Vision (WACV) (2019), 1524\u20131532","DOI":"10.1109\/WACV.2019.00167"},{"key":"476_CR3","doi-asserted-by":"crossref","unstructured":"Brown, M.\u00a0S., Seales, W.\u00a0B. Document restoration using 3d shape: a general deskewing algorithm for arbitrarily warped documents. In: Proceedings Eighth IEEE International Conference on Computer Vision. ICCV 2001 (2001), 2, IEEE, 367\u2013374","DOI":"10.1109\/ICCV.2001.937649"},{"issue":"11","key":"476_CR4","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2007.1118","volume":"29","author":"MS Brown","year":"2007","unstructured":"Brown, M.S., Sun, M., Yang, R., Yun, L., Seales, W.B.: Restoring 2d content from distorted documents. IEEE Trans. Pattern Anal. Mach. Intell. 29(11), 1904\u20131916 (2007)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"476_CR5","doi-asserted-by":"crossref","unstructured":"Courteille, F., Crouzil, A., Durou, J.D., Gurdjos, P.: Towards shape from shading under realistic photographic conditions. In: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004. 2, IEEE, pp. 277\u2013280. (2004)","DOI":"10.1109\/ICPR.2004.1334160"},{"key":"476_CR6","unstructured":"Dai, B., Xie, Q., Li, Y., Qin, X., Zhang, C., Yao, K., Han, J., et\u00a0al.: Matadoc: margin and text aware document dewarping for arbitrary boundary. arXiv preprint arXiv:2307.12571 (2023)"},{"key":"476_CR7","doi-asserted-by":"crossref","unstructured":"Das, S., Ma, K., Shu, Z., Samaras, D., Shilkrot, R.: Dewarpnet: single-image document unwarping with stacked 3d and 2d regression networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 131\u2013140. (2019)","DOI":"10.1109\/ICCV.2019.00022"},{"key":"476_CR8","doi-asserted-by":"crossref","unstructured":"Das, S., Singh, K.\u00a0Y., Wu, J., Bas, E., Mahadevan, V., Bhotika, R., Samaras, D.: End-to-end piece-wise unwarping of document images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 4268\u20134277. (2021)","DOI":"10.1109\/ICCV48922.2021.00423"},{"key":"476_CR9","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s10479-005-5724-z","volume":"134","author":"P-T De Boer","year":"2005","unstructured":"De Boer, P.-T., Kroese, D.P., Mannor, S., Rubinstein, R.Y.: A tutorial on the cross-entropy method. Ann. Oper. Res. 134, 19\u201367 (2005)","journal-title":"Ann. Oper. Res."},{"key":"476_CR10","doi-asserted-by":"crossref","unstructured":"Feng, H., Liu, S., Deng, J., Zhou, W., Li, H.: Deep unrestricted document image rectification. arXiv preprint arXiv:2304.08796 (2023)","DOI":"10.1109\/TMM.2023.3347094"},{"key":"476_CR11","doi-asserted-by":"crossref","unstructured":"Feng, H., Wang, Y., Zhou, W., Deng, J., Li, H.: Doctr: document image transformer for geometric unwarping and illumination correction. arXiv preprint arXiv:2110.12942 (2021)","DOI":"10.1145\/3474085.3475388"},{"key":"476_CR12","doi-asserted-by":"crossref","unstructured":"Feng, H., Zhou, W., Deng, J., Wang, Y., Li, H.: Geometric representation learning for document image rectification. In Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, October 23\u201327, 2022, Proceedings, Part XXXVII, Springer, pp. 475\u2013492. (2022)","DOI":"10.1007\/978-3-031-19836-6_27"},{"key":"476_CR13","doi-asserted-by":"crossref","unstructured":"Feng, H., Zhou, W., Deng, J., Wang, Y., Li, H. Geometric representation learning for document image rectification. In: S.\u00a0Avidan, G.\u00a0Brostow, M.\u00a0Ciss\u00e9, G.\u00a0M. Farinella, T.\u00a0Hassner, Eds., Computer Vision\u2013ECCV 2022 (Cham, 2022), Springer Nature Switzerland, pp. 475\u2013492","DOI":"10.1007\/978-3-031-19836-6_27"},{"issue":"10","key":"476_CR14","doi-asserted-by":"publisher","first-page":"389","DOI":"10.1177\/0145482X7907301002","volume":"73","author":"DGL Goodrich","year":"1979","unstructured":"Goodrich, D.G.L., Bennett, M.R.R., L\u2019aune, D.W.R.D., Lauer, H., Mowinski, L.: Kurzweil reading machine: a partial evaluation of its optical character recognition error rate. J. Vis. Impair. Blind. 73(10), 389\u2013399 (1979)","journal-title":"J. Vis. Impair. Blind."},{"issue":"9","key":"476_CR15","doi-asserted-by":"publisher","first-page":"1904","DOI":"10.1109\/TPAMI.2015.2389824","volume":"37","author":"K He","year":"2015","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Spatial pyramid pooling in deep convolutional networks for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 37(9), 1904\u20131916 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"476_CR16","doi-asserted-by":"crossref","unstructured":"He, Y., Pan, P., Xie, S., Sun, J., Naoi, S. A book dewarping system by boundary-based 3d surface reconstruction. In: 2013 12th International Conference on Document Analysis and Recognition, IEEE, pp. 403\u2013407. (2013)","DOI":"10.1109\/ICDAR.2013.88"},{"issue":"1","key":"476_CR17","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1006\/nimg.2001.1054","volume":"16","author":"C Hutton","year":"2002","unstructured":"Hutton, C., Bork, A., Josephs, O., Deichmann, R., Ashburner, J., Turner, R.: Image distortion correction in FMRI: a quantitative evaluation. Neuroimage 16(1), 217\u2013240 (2002)","journal-title":"Neuroimage"},{"key":"476_CR18","doi-asserted-by":"crossref","unstructured":"Jiang, X., Long, R., Xue, N., Yang, Z., Yao, C., Xia, G.S.: Revisiting document image dewarping by grid regularization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4543\u20134552. (2022)","DOI":"10.1109\/CVPR52688.2022.00450"},{"key":"476_CR19","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: B.\u00a0Leibe, J.\u00a0Matas, N.\u00a0Sebe, and M.\u00a0Welling, Eds. Computer Vision\u2013ECCV 2016, Springer International Publishing, pp. 694\u2013711. (Cham, 2016)","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"476_CR20","unstructured":"Levenshtein, V.\u00a0I. Binary codes capable of correcting deletions, insertions, and reversals. Soviet Phys. Doklady. Vol. 10. No. 8 (1966)"},{"key":"476_CR21","doi-asserted-by":"crossref","unstructured":"Li, H., Wu, X., Chen, Q., Xiang, Q. Foreground and text-lines aware document image rectification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19574\u201319583. (2023)","DOI":"10.1109\/ICCV51070.2023.01793"},{"key":"476_CR22","doi-asserted-by":"crossref","unstructured":"Li, P., Quan, W., Guo, J., Yan, D.M. Layout-aware single-image document flattening. ACM Trans. Graphics (2023)","DOI":"10.1145\/3627818"},{"issue":"6","key":"476_CR23","first-page":"1","volume":"38","author":"X Li","year":"2019","unstructured":"Li, X., Zhang, B., Liao, J., Sander, P.V.: Document rectification and illumination correction using a patch-based CNN. ACM Trans. Graphics (TOG) 38(6), 1\u201311 (2019)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"476_CR24","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, B., Sander, P.\u00a0V., Liao, J.: Blind geometric distortion correction on images through deep learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4855\u20134864. (2019)","DOI":"10.1109\/CVPR.2019.00499"},{"issue":"4","key":"476_CR25","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TPAMI.2007.70724","volume":"30","author":"J Liang","year":"2008","unstructured":"Liang, J., DeMenthon, D., Doermann, D.: Geometric rectification of camera-captured document images. IEEE Trans. Patt. Anal. Mach. Intell. 30(4), 591\u2013605 (2008)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"5","key":"476_CR26","doi-asserted-by":"publisher","first-page":"978","DOI":"10.1109\/TPAMI.2010.147","volume":"33","author":"C Liu","year":"2011","unstructured":"Liu, C., Yuen, J., Torralba, A.: Sift flow: Dense correspondence across scenes and its applications. IEEE Trans. Pattern Anal. Mach. Intell. 33(5), 978\u2013994 (2011)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"476_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107576","volume":"108","author":"X Liu","year":"2020","unstructured":"Liu, X., Meng, G., Fan, B., Xiang, S., Pan, C.: Geometric rectification of document images using adversarial gated unwarping network. Pattern Recogn. 108, 107576 (2020)","journal-title":"Pattern Recogn."},{"key":"476_CR28","doi-asserted-by":"crossref","unstructured":"Ma, K., Shu, Z., Bai, X., Wang, J., Samaras, D.: Docunet: document image unwarping via a stacked u-net. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134709. (2018)","DOI":"10.1109\/CVPR.2018.00494"},{"key":"476_CR29","doi-asserted-by":"crossref","unstructured":"Markovitz, A., Lavi, I., Perel, O., Mazor, S., Litman, R. Can you read me now? content aware rectification using angle supervision. In: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XII 16, Springer, pp. 208\u2013223. (2020)","DOI":"10.1007\/978-3-030-58610-2_13"},{"key":"476_CR30","doi-asserted-by":"crossref","unstructured":"Meng, G., Wang, Y., Qu, S., Xiang, S., Pan, C. Active flattening of curved document images via two structured beams. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014), 3890\u20133897","DOI":"10.1109\/CVPR.2014.497"},{"key":"476_CR31","doi-asserted-by":"crossref","unstructured":"Naor, E., Antebi, I., Bagon, S., Irani, M.: Combining internal and external constraints for unrolling shutter in videos. In: Computer Vision\u2013ECCV 2022: 17th European Conference, Tel Aviv, Israel, 2022, Proceedings, Part XVII, Springer, pp. 119\u2013134. (2022)","DOI":"10.1007\/978-3-031-19790-1_8"},{"key":"476_CR32","doi-asserted-by":"crossref","unstructured":"Pihlgren, G.\u00a0G., Sandin, F., Liwicki, M.: Improving image autoencoder embeddings with perceptual loss. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. (2020)","DOI":"10.1109\/IJCNN48605.2020.9207431"},{"key":"476_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404","volume":"106","author":"X Qin","year":"2020","unstructured":"Qin, X., Zhang, Z., Huang, C., Dehghan, M., Zaiane, O.R., Jagersand, M.: U2-net: going deeper with nested u-structure for salient object detection. Patt. Recogn. 106, 107404 (2020)","journal-title":"Patt. Recogn."},{"key":"476_CR34","doi-asserted-by":"crossref","unstructured":"Qin, Y.S., Sun, S.F., Ma, X.B., Hu, S., Lei, B.J.: A shadow removal algorithm for vibe in hsv color space. In 3rd International Conference on Multimedia Technology (ICMT-13), Atlantis Press, pp. 959\u2013966. (2013)","DOI":"10.2991\/icmt-13.2013.119"},{"key":"476_CR35","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, Proceedings, Part III 18, Springer, pp. 234\u2013241. (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"476_CR36","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract ocr engine. In: Ninth international conference on document analysis and recognition (ICDAR 2007), 2, IEEE, pp. 629\u2013633. (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"476_CR37","doi-asserted-by":"crossref","unstructured":"Tsoi, Y.C., Brown, M.S.: Multi-view document rectification using boundary. In: 2007 IEEE Conference on Computer Vision and Pattern Recognition, IEEE, pp. 1\u20138. (2007)","DOI":"10.1109\/CVPR.2007.383251"},{"key":"476_CR38","unstructured":"Verhoeven, F., Magne, T., Sorkine-Hornung, O.: Neural document unwarping using coupled grids. arXiv preprint arXiv:2302.02887. (2023)"},{"issue":"2","key":"476_CR39","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1023\/A:1007906904009","volume":"24","author":"T Wada","year":"1997","unstructured":"Wada, T., Ukida, H., Matsuyama, T.: Shape from shading with interreflections under a proximal light source: distortion-free copying of an unfolded book. Int. J. Comput. Vis. 24(2), 125 (1997)","journal-title":"Int. J. Comput. Vis."},{"key":"476_CR40","doi-asserted-by":"crossref","unstructured":"Wang, Z., Bovik, A., Sheikh, H., Simoncelli, E.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13(4), 600\u2013612 (2004)","DOI":"10.1109\/TIP.2003.819861"},{"key":"476_CR41","doi-asserted-by":"crossref","unstructured":"Wang, Z., Ji, X., Huang, J.B., Satoh, S., Zhou, X., Zheng, Y.: Neural global shutter: Learn to restore video from a rolling shutter camera with global reset feature. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17794\u201317803. (2022)","DOI":"10.1109\/CVPR52688.2022.01727"},{"key":"476_CR42","unstructured":"Wang, Z., Simoncelli, E., Bovik, A. Multiscale structural similarity for image quality assessment. In: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2, 1398\u20131402. Vol. 2. (2003)"},{"key":"476_CR43","doi-asserted-by":"crossref","unstructured":"Wu, C., Agam, G.: Document image de-warping for text\/graphics recognition. In Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR International Workshops SSPR 2002 and SPR 2002 Windsor, Ontario, Canada, August 6\u20139, 2002 Proceedings, Springer, pp. 348\u2013357. (2002)","DOI":"10.1007\/3-540-70659-3_36"},{"key":"476_CR44","doi-asserted-by":"crossref","unstructured":"Xie, G.W., Yin, F., Zhang, X.Y., Liu, C.L.: Dewarping document image by displacement flow estimation with fully convolutional network. In: Document Analysis Systems: 14th IAPR International Workshop, DAS 2020, Wuhan, China, Proceedings 14, Springer, pp. 131\u2013144. (2020)","DOI":"10.1007\/978-3-030-57058-3_10"},{"key":"476_CR45","doi-asserted-by":"crossref","unstructured":"Xie, G.W., Yin, F., Zhang, X.Y., Liu, C.L.: Document dewarping with control points. In: Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part I 16, Springer, pp. 466\u2013480. (2021)","DOI":"10.1007\/978-3-030-86549-8_30"},{"key":"476_CR46","doi-asserted-by":"crossref","unstructured":"Yang, L., Tse, Y.C., Sander, P.V., Lawrence, J., Nehab, D., Hoppe, H., Wilkins, C.L.: Image-based bidirectional scene reprojection. In Proceedings of the 2011 SIGGRAPH Asia Conference, pp. 1\u201310. (2011)","DOI":"10.1145\/2024156.2024184"},{"issue":"2","key":"476_CR47","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1109\/TPAMI.2017.2675980","volume":"40","author":"S You","year":"2017","unstructured":"You, S., Matsushita, Y., Sinha, S., Bou, Y., Ikeuchi, K.: Multiview rectification of folded documents. IEEE Trans. Patt. Anal. Mach. Intell. 40(2), 505\u2013511 (2017)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"issue":"2","key":"476_CR48","doi-asserted-by":"publisher","first-page":"505","DOI":"10.1109\/TPAMI.2017.2675980","volume":"40","author":"S You","year":"2018","unstructured":"You, S., Matsushita, Y., Sinha, S., Bou, Y., Ikeuchi, K.: Multiview rectification of folded documents. IEEE Trans. Patt. Anal. Mach. Intell. 40(2), 505\u2013511 (2018)","journal-title":"IEEE Trans. Patt. Anal. Mach. Intell."},{"key":"476_CR49","doi-asserted-by":"crossref","unstructured":"Zhang, J., Luo, C., Jin, L., Guo, F., Ding, K.: Marior: margin removal and iterative content rectification for document dewarping in the wild. arXiv preprint arXiv:2207.11515 (2022)","DOI":"10.1145\/3503161.3548214"},{"issue":"4","key":"476_CR50","doi-asserted-by":"publisher","first-page":"728","DOI":"10.1109\/TPAMI.2007.70831","volume":"30","author":"L Zhang","year":"2008","unstructured":"Zhang, L., Zhang, Y., Tan, C.: An improved physically-based method for geometric restoration of distorted document images. IEEE Trans. Pattern Anal. Mach. Intell. 30(4), 728\u2013734 (2008)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-024-00476-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-024-00476-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-024-00476-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T10:09:23Z","timestamp":1725098963000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-024-00476-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,22]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["476"],"URL":"https:\/\/doi.org\/10.1007\/s10032-024-00476-9","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,22]]},"assertion":[{"value":"14 November 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 February 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 May 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 May 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}