{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T01:09:08Z","timestamp":1760404148932,"version":"3.40.5"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,2,4]],"date-time":"2015-02-04T00:00:00Z","timestamp":1423008000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2015,6]]},"DOI":"10.1007\/s10032-015-0240-4","type":"journal-article","created":{"date-parts":[[2015,2,3]],"date-time":"2015-02-03T05:13:10Z","timestamp":1422940390000},"page":"169-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Fast and accurate scene text understanding with image binarization and off-the-shelf OCR"],"prefix":"10.1007","volume":"18","author":[{"given":"Sergey","family":"Milyaev","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Olga","family":"Barinova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatiana","family":"Novikova","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pushmeet","family":"Kohli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Lempitsky","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,2,4]]},"reference":[{"issue":"3","key":"240_CR1","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1145\/1531326.1531327","volume":"28","author":"A Adams","year":"2009","unstructured":"Adams, A., Gelfand, N., Dolson, J., Levoy, M.: Gaussian KD-trees for fast high-dimensional filtering. ACM Trans. Graph. (TOG) 28(3), 21 (2009)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"240_CR2","doi-asserted-by":"crossref","unstructured":"Badekas, E., Papamarkos, N.: Automatic evaluation of document binarization results. In: CIARP, pp. 1005\u20131014 (2005)","DOI":"10.1007\/11578079_103"},{"key":"240_CR3","doi-asserted-by":"crossref","unstructured":"Boykov, Y., Jolly, M.P.: Interactive graph cuts for optimal boundary and region segmentation of objects in n-d images. In: ICCV, pp. 105\u2013112 (2001)","DOI":"10.1109\/ICCV.2001.937505"},{"key":"240_CR4","doi-asserted-by":"crossref","unstructured":"Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut\/max-flow algorithms for energy minimization in vision. In: IEEE Transactions on Pattern Analysis and Machine Intelligence (2004)","DOI":"10.1109\/TPAMI.2004.60"},{"issue":"9","key":"240_CR5","doi-asserted-by":"crossref","first-page":"1124","DOI":"10.1109\/TPAMI.2004.60","volume":"26","author":"Y Boykov","year":"2004","unstructured":"Boykov, Y., Kolmogorov, V.: An experimental comparison of min-cut\/max-flow algorithms for energy minimization in vision. IEEE Trans. Pattern Anal. Mach. Intell. 26(9), 1124\u20131137 (2004)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"240_CR6","doi-asserted-by":"crossref","unstructured":"Clavelli, A., Karatzas, D., Llad\u00f3s, J.: A framework for the assessment of text extraction algorithms on complex colour images. In: Document Analysis Systems, pp. 19\u201326 (2010)","DOI":"10.1145\/1815330.1815333"},{"key":"240_CR7","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: CVPR (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"240_CR8","doi-asserted-by":"crossref","unstructured":"Ezaki, N.: Text detection from natural scene images: towards a system for visually impaired persons. In. International Conference on Pattern Recognition, pp. 683\u2013686 (2004)","DOI":"10.1109\/ICPR.2004.1334351"},{"key":"240_CR9","doi-asserted-by":"crossref","unstructured":"Friedman, J., Hastie, T., Tibshirani, R.: Additive logistic regression: a statistical view of boosting. Ann. Stat. 38(2), 337\u2013407 (2000)","DOI":"10.1214\/aos\/1016218223"},{"key":"240_CR10","doi-asserted-by":"crossref","unstructured":"Gatos, B., Ntirogiannis, K., Pratikakis, I.: Icdar 2009 document image binarization contest (dibco 2009). In: ICDAR, pp. 1375\u20131382 (2009)","DOI":"10.1109\/ICDAR.2009.246"},{"key":"240_CR11","unstructured":"Gatos, B., Pratikakis, I., Perantonis, S.J.: Text detection in indoor\/outdoor scene images. In: CBDAR\u201905, pp. 127\u2013132 (2005)"},{"key":"240_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Sun, J., Tang, X.: Guided image filtering. In: Computer vision-ECCV 2010, pp. 1\u201314. Springer (2010)","DOI":"10.1007\/978-3-642-15549-9_1"},{"key":"240_CR13","doi-asserted-by":"crossref","unstructured":"Howe, N.: A laplacian energy for document binarization. In: ICDAR, pp. 6\u201310 (2011)","DOI":"10.1109\/ICDAR.2011.11"},{"key":"240_CR14","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., de las Heras, L.P.: ICDAR 2013 robust reading competition. In: 2013 International Conference on Document Analysis and Recognition (ICDAR). IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"issue":"3","key":"240_CR15","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1023\/A:1023030907417","volume":"53","author":"R Kimmel","year":"2003","unstructured":"Kimmel, R., Bruckstein, A.M.: Regularized Laplacian zero crossings as optimal edge integrators. Int. J. Comput. Vis. 53(3), 225\u2013243 (2003)","journal-title":"Int. J. Comput. Vis."},{"key":"240_CR16","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/0031-3203(86)90030-0","volume":"19","author":"J Kittler","year":"1986","unstructured":"Kittler, J., Illingworth, J.: Minimum error thresholding. Pattern Recogn. 19, 41\u201347 (1986)","journal-title":"Pattern Recogn."},{"issue":"4","key":"240_CR17","doi-asserted-by":"crossref","first-page":"303","DOI":"10.1007\/s10032-010-0130-8","volume":"13","author":"S Lu","year":"2010","unstructured":"Lu, S., Su, B., Tan, C.L.: Document image binarization using background estimation and stroke edges. IJDAR 13(4), 303\u2013314 (2010)","journal-title":"IJDAR"},{"key":"240_CR18","doi-asserted-by":"crossref","unstructured":"Milyaev, S., Barinova, O., Novikova, T., Lempitsky, V., Kohli, P.: Image binarization for end-to-end text understanding in natural images. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.33"},{"key":"240_CR19","doi-asserted-by":"crossref","unstructured":"Minetto, R., Thome, N., Cord, M., Stolfi, J., Precioso, F., Guyomard, J., Leite, N.J.: Text detection and recognition in urban scenes. In: ICCV Workshops, pp. 227\u2013234 (2011)","DOI":"10.1109\/ICCVW.2011.6130247"},{"key":"240_CR20","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: An mrf model for binarization of natural scene text. In: ICDAR, pp. 11\u201316 (2011)","DOI":"10.1109\/ICDAR.2011.12"},{"key":"240_CR21","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Estimating hidden parameters for text localization and recognition. In: Computer Vision Winter Workshop (2011)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"240_CR22","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Real-time scene text localization and recognition. In: CVPR, pp. 3538\u20133545 (2012)","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"240_CR23","doi-asserted-by":"crossref","unstructured":"Neumann, L., Matas, J.: Scene text localization and recognition with oriented stroke detection. In: 2013 IEEE International Conference on Computer Vision (ICCV 2013), pp. 97\u2013104 (2013)","DOI":"10.1109\/ICCV.2013.19"},{"key":"240_CR24","volume-title":"An introduction to digital image processing","author":"W Niblack","year":"1985","unstructured":"Niblack, W.: An introduction to digital image processing. Strandberg Publishing, Denmark (1985)"},{"key":"240_CR25","doi-asserted-by":"crossref","unstructured":"Ntirogiannis, K., Gatos, B., Pratikakis, I.: An objective evaluation methodology for document image binarization techniques. In: DAS, pp. 217\u2013224 (2008)","DOI":"10.1109\/DAS.2008.41"},{"key":"240_CR26","doi-asserted-by":"crossref","first-page":"62","DOI":"10.1109\/TSMC.1979.4310076","volume":"9","author":"N Otsu","year":"1979","unstructured":"Otsu, N.: A threshold selection method from gray level histograms. IEEE Trans. Syst. Man Cybern. 9, 62\u201366 (1979)","journal-title":"IEEE Trans. Syst. Man Cybern."},{"key":"240_CR27","doi-asserted-by":"crossref","unstructured":"Pan, Y.F., Hou, X., Liu, C.L.: Text localization in natural scene images based on conditional random field. In: ICDAR, pp. 6\u201310 (2009)","DOI":"10.1109\/ICDAR.2009.97"},{"key":"240_CR28","doi-asserted-by":"crossref","unstructured":"Pratikakis, I., Gatos, B., Ntirogiannis, K.: ICDAR 2011 document image binarization contest (DIBCO 2011). In: ICDAR, pp. 1506\u20131510 (2011)","DOI":"10.1109\/ICDAR.2011.299"},{"key":"240_CR29","doi-asserted-by":"crossref","unstructured":"Sauvola, J., Pietikinen, M.: Adaptive document image binarization. Pattern Recogn. 33, 225\u2013236 (2000)","DOI":"10.1016\/S0031-3203(99)00055-2"},{"key":"240_CR30","doi-asserted-by":"crossref","unstructured":"Wakahara, T., Kita, K.: Binarization of color character strings in scene images using k-means clustering and support vector machines. In: ICDAR, pp. 274\u2013278 (2011)","DOI":"10.1109\/ICDAR.2011.63"},{"key":"240_CR31","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: IEEE International Conference on Computer Vision (ICCV). Barcelona, Spain (2011)"},{"key":"240_CR32","unstructured":"Wang, T., Wu, D.J., Coates, A., Ng, A.Y.: End-to-end text recognition with convolutional neural networks. In: 21st International Conference on Pattern Recognition (ICPR), pp. 3304\u20133308 (2012)"},{"key":"240_CR33","doi-asserted-by":"crossref","unstructured":"Wolf, C., Doermann, D.: Binarization of low quality text using a markov random field model. In: Proceedings of International Conference on Pattern Recognition, pp. 160\u2013163 (2002)","DOI":"10.1109\/ICPR.2002.1047819"},{"issue":"4","key":"240_CR34","doi-asserted-by":"crossref","first-page":"280","DOI":"10.1007\/s10032-006-0014-0","volume":"8","author":"C Wolf","year":"2006","unstructured":"Wolf, C., Jolion, J.M.: Object count\/area graphs for the evaluation of object detection and segmentation algorithms. Int. J. Doc. Anal. Recogn. 8(4), 280\u2013296 (2006)","journal-title":"Int. J. Doc. Anal. Recogn."},{"key":"240_CR35","doi-asserted-by":"crossref","unstructured":"Yamazoe, T., Etoh, M., Yoshimura, T., Tsujino, K.: Hypothesis preservation approach to scene text recognition with weighted finite-state transducer. In: ICDAR, pp. 359\u2013363 (2011)","DOI":"10.1109\/ICDAR.2011.80"},{"key":"240_CR36","unstructured":"Yang, Q., Tan, K.H., Ahuja, N.: Real-time o (1) bilateral filtering. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 557\u2013564. IEEE (2009)"},{"key":"240_CR37","doi-asserted-by":"crossref","unstructured":"Yang, Q.: Recursive bilateral filtering. In: ECCV (1), pp. 399\u2013413 (2012)","DOI":"10.1007\/978-3-642-33718-5_29"},{"key":"240_CR38","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: ICDAR 2011 document image binarization contest (DIBCO 2011). In: CVPR (2012)"},{"issue":"4","key":"240_CR39","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1109\/TPAMI.2006.70","volume":"28","author":"KJ Yoon","year":"2006","unstructured":"Yoon, K.J., Kweon, I.S.: Adaptive support-weight approach for correspondence search. IEEE Trans. Pattern Anal. Mach. Intell. 28(4), 650\u2013656 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"240_CR40","unstructured":"Zhu, K., Qi, F., Jiang, R., Xu, L., Kimaci, M., Wu, Y., Aizawa, T.: Using adaboost to detect and segment characters from natural scenes. In: Camera-Based Document Analysis and Recognition (CBDAR) (2005)"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-015-0240-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-015-0240-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-015-0240-4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,18]],"date-time":"2025-05-18T06:34:13Z","timestamp":1747550053000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-015-0240-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,2,4]]},"references-count":40,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2015,6]]}},"alternative-id":["240"],"URL":"https:\/\/doi.org\/10.1007\/s10032-015-0240-4","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2015,2,4]]}}}