{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T12:45:10Z","timestamp":1740141910226,"version":"3.37.3"},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2017,4,3]],"date-time":"2017-04-03T00:00:00Z","timestamp":1491177600000},"content-version":"unspecified","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":[[2017,6]]},"DOI":"10.1007\/s10032-017-0283-9","type":"journal-article","created":{"date-parts":[[2017,4,3]],"date-time":"2017-04-03T09:33:37Z","timestamp":1491212017000},"page":"105-121","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Unsupervised refinement of color and stroke features for text binarization"],"prefix":"10.1007","volume":"20","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4050-2465","authenticated-orcid":false,"given":"Anand","family":"Mishra","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1838-5936","authenticated-orcid":false,"given":"Karteek","family":"Alahari","sequence":"additional","affiliation":[]},{"given":"C. V.","family":"Jawahar","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,4,3]]},"reference":[{"key":"283_CR1","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, L.: Broken and degraded document images binarization. Neurocomputing 237, 272\u2013280 (2017)","DOI":"10.1016\/j.neucom.2016.12.058"},{"key":"283_CR2","doi-asserted-by":"crossref","unstructured":"Jia, F., Shi, C., He, K., Wang, C., Xiao, B.: Document image binarization using structural symmetry of strokes. In: ICFHR, pp. 411\u2013416 (2016)","DOI":"10.1109\/ICFHR.2016.0083"},{"issue":"18","key":"283_CR3","first-page":"3011","volume":"14","author":"P Stathis","year":"2008","unstructured":"Stathis, P., Kavallieratou, E., Papamarkos, N.: An evaluation technique for binarization algorithms. J. Univers. Comput. Sci. 14(18), 3011\u20133030 (2008)","journal-title":"J. Univers. Comput. Sci."},{"key":"283_CR4","doi-asserted-by":"crossref","unstructured":"Howe, N.R.: A Laplacian energy for document binarization. In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.11"},{"issue":"3","key":"283_CR5","doi-asserted-by":"crossref","first-page":"247","DOI":"10.1007\/s10032-012-0192-x","volume":"16","author":"NR Howe","year":"2013","unstructured":"Howe, N.R.: Document binarization with automatic parameter tuning. Int. J. Doc. Anal. Recognit. 16(3), 247\u2013258 (2013)","journal-title":"Int. J. Doc. Anal. Recognit."},{"issue":"1","key":"283_CR6","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1007\/s10032-010-0142-4","volume":"15","author":"M Valizadeh","year":"2012","unstructured":"Valizadeh, M., Kabir, E.: Binarization of degraded document image based on feature space partitioning and classification. Int. J. Doc. Anal. Recognit. 15(1), 57\u201369 (2012)","journal-title":"Int. J. Doc. Anal. Recognit."},{"issue":"2","key":"283_CR7","doi-asserted-by":"crossref","first-page":"105","DOI":"10.1007\/s10032-013-0209-0","volume":"17","author":"G Lazzara","year":"2014","unstructured":"Lazzara, G., G\u00e9raud, T.: Efficient multiscale Sauvola\u2019s binarization. Int. J. Doc. Anal. Recognit. 17(2), 105\u2013123 (2014)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"283_CR8","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.V.: An MRF model for binarization of natural scene text. In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.12"},{"issue":"2","key":"283_CR9","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1007\/s10032-015-0240-4","volume":"18","author":"S Milyaev","year":"2015","unstructured":"Milyaev, S., Barinova, O., Novikova, T., Kohli, P., Lempitsky, V.: Fast and accurate scene text understanding with image binarization and off-the-shelf OCR. Int. J. Doc. Anal. Recognit. 18(2), 169\u2013182 (2015)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"283_CR10","doi-asserted-by":"crossref","unstructured":"Pratikakis, I., Gatos, B., Ntirogiannis, K.: ICDAR 2013 document image binarization contest (DIBCO 2013). In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.219"},{"key":"283_CR11","doi-asserted-by":"crossref","unstructured":"Pratikakis, I., Gatos, B., Ntirogiannis, K.: ICFHR 2012 competition on handwritten document image binarization. In: ICFHR (2012)","DOI":"10.1109\/ICFHR.2012.216"},{"key":"283_CR12","doi-asserted-by":"crossref","unstructured":"Ntirogiannis, K., Gatos, B., Pratikakis, I.: ICFHR2014 competition on handwritten document image binarization (H-DIBCO 2014). In: ICFHR (2014)","DOI":"10.1109\/ICFHR.2014.141"},{"key":"283_CR13","unstructured":"Boykov, Y.Y., Jolly, M.-P.: Interactive graph cuts for optimal boundary and region segmentation of objects in ND images. In: ICCV (2001)"},{"issue":"3","key":"283_CR14","doi-asserted-by":"crossref","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V., Blake, A.: GrabCut: interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. 23(3), 309\u2013314 (2004)","journal-title":"ACM Trans. Graph."},{"key":"283_CR15","doi-asserted-by":"crossref","unstructured":"Blake, A., Rother, C., Brown, M., Perez, P., Torr, P.: Interactive image segmentation using an adaptive GMMRF model. In: ECCV (2004)","DOI":"10.1007\/978-3-540-24670-1_33"},{"issue":"2","key":"283_CR16","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1016\/0734-189X(85)90093-3","volume":"30","author":"J Kittler","year":"1985","unstructured":"Kittler, J., Illingworth, J., F\u00f6glein, J.: Threshold selection based on a simple image statistic. Comput. Vis. Graph. Image Process. 30(2), 125\u2013147 (1985)","journal-title":"Comput. Vis. Graph. Image Process."},{"issue":"285\u2013296","key":"283_CR17","first-page":"23","volume":"11","author":"N Otsu","year":"1975","unstructured":"Otsu, N.: A threshold selection method from gray-level histograms. Automatica 11(285\u2013296), 23\u201327 (1975)","journal-title":"Automatica"},{"key":"283_CR18","unstructured":"Kasar, T., Kumar, J., Ramakrishnan, A.: Font and background color independent text binarization. In: CBDAR (2007)"},{"key":"283_CR19","unstructured":"Niblack, W.: An Introduction to Digital Image Processing. Strandberg Publishing Company (1985)"},{"issue":"2","key":"283_CR20","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1016\/S0031-3203(99)00055-2","volume":"33","author":"J Sauvola","year":"2000","unstructured":"Sauvola, J., Pietik\u00e4inen, M.: Adaptive document image binarization. Pattern Recognit. 33(2), 225\u2013236 (2000)","journal-title":"Pattern Recognit."},{"key":"283_CR21","doi-asserted-by":"crossref","unstructured":"Wolf, C., Doermann, D.: Binarization of low quality text using a Markov random field model. In: ICPR (2002)","DOI":"10.1109\/ICPR.2002.1047819"},{"key":"283_CR22","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i\u00a0Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almaz\u00e1n, J., de\u00a0las Heras, L.: ICDAR 2013 robust reading competition. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"283_CR23","unstructured":"Tesseract OCR. http:\/\/code.google.com\/p\/tesseract-ocr\/"},{"key":"283_CR24","unstructured":"Project website. http:\/\/cvit.iiit.ac.in\/projects\/SceneTextUnderstanding\/"},{"key":"283_CR25","doi-asserted-by":"crossref","unstructured":"Thillou, C., Gosselin, B.: Color binarization for complex camera-based images. In: Electronic imaging (2005)","DOI":"10.1117\/12.586618"},{"key":"283_CR26","doi-asserted-by":"crossref","unstructured":"Kita, K., Wakahara, T.: Binarization of color characters in scene images using k-means clustering and support vector machines. In: ICPR (2010)","DOI":"10.1109\/ICPR.2010.779"},{"issue":"4","key":"283_CR27","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. Int. J. Doc. Anal. Recognit. 13(4), 303\u2013314 (2010)","journal-title":"Int. J. Doc. Anal. Recognit."},{"key":"283_CR28","doi-asserted-by":"crossref","unstructured":"Kuk, J.G., Cho, N.I.: Feature based binarization of document images degraded by uneven light condition. In: ICDAR (2009)","DOI":"10.1109\/ICDAR.2009.157"},{"key":"283_CR29","doi-asserted-by":"crossref","unstructured":"Peng, X., Setlur, S., Govindaraju, V., Sitaram, R.: Markov random field based binarization for hand-held devices captured document images. In: ICVGIP (2010)","DOI":"10.1145\/1924559.1924569"},{"key":"283_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, H., Liu, C., Yang, C., Ding, X., Wang, K.: An improved scene text extraction method using conditional random field and optical character recognition. In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.148"},{"key":"283_CR31","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 (2009)","DOI":"10.1109\/ICDAR.2009.97"},{"key":"283_CR32","doi-asserted-by":"crossref","unstructured":"Hebert, D., Nicolas, S., Paquet, T.: Discrete CRF based combination framework for document image binarization. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.236"},{"key":"283_CR33","unstructured":"Gatos, B., Pratikakis, I., Kepene, K., Perantonis, S.: Text detection in indoor\/outdoor scene images. In: CBDAR (2005)"},{"key":"283_CR34","doi-asserted-by":"crossref","unstructured":"Ezaki, N., Bulacu, M., Schomaker, L.: Text detection from natural scene images: towards a system for visually impaired persons. In: ICPR (2004)","DOI":"10.1109\/ICPR.2004.1334351"},{"key":"283_CR35","unstructured":"Gomez, L., Karatzas, D.: A fast hierarchical method for multi-script and arbitrary oriented scene text extraction. arXiv preprint arXiv:1407.7504 (2014)"},{"key":"283_CR36","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":"283_CR37","unstructured":"Feild, J., Learned-Miller, E.: Scene text recognition with bilateral regression. University of Massachusetts-Amherst, Computer Science Research Center, Tech. Rep. UM-CS-2012-021 (2013)"},{"key":"283_CR38","doi-asserted-by":"crossref","unstructured":"Dalal, N., Triggs, B.: Histograms of oriented gradients for human detection. In: CVPR (2005)","DOI":"10.1109\/CVPR.2005.177"},{"key":"283_CR39","doi-asserted-by":"crossref","unstructured":"Tian, S., Lu, S., Su, B., Tan, C.L.: Scene text segmentation with multi-level maximally stable extremal regions. In: ICPR (2014)","DOI":"10.1109\/ICPR.2014.467"},{"key":"283_CR40","doi-asserted-by":"crossref","unstructured":"Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: BMVC (2002)","DOI":"10.5244\/C.16.36"},{"issue":"9","key":"283_CR41","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."},{"issue":"2","key":"283_CR42","doi-asserted-by":"crossref","first-page":"147","DOI":"10.1109\/TPAMI.2004.1262177","volume":"26","author":"V Kolmogorov","year":"2004","unstructured":"Kolmogorov, V., Zabin, R.: What energy functions can be minimized via graph cuts? IEEE Trans. Pattern Anal. Mach. Intell. 26(2), 147\u2013159 (2004)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"283_CR43","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/S0166-218X(01)00341-9","volume":"123","author":"E Boros","year":"2002","unstructured":"Boros, E., Hammer, P.L.: Pseudo-boolean optimization. Discrete Appl. Math. 123(1), 155\u2013225 (2002)","journal-title":"Discrete Appl. Math."},{"key":"283_CR44","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A.: Gaussian mixture models. In: Encyclopedia of Biometrics, Second Edition, pp. 827\u2013832 (2015)","DOI":"10.1007\/978-1-4899-7488-4_196"},{"key":"283_CR45","unstructured":"Sosa, L.P., Lucas, S.M., Panaretos, A., Sosa, L., Tang, A., Wong, S., Young, R.: ICDAR 2003 robust reading competitions. In: ICDAR (2003)"},{"key":"283_CR46","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Dengel, A.: ICDAR 2011 robust reading competition challenge 2: reading text in scene images. In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.296"},{"key":"283_CR47","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Mestre, S.R., Mas, J., Nourbakhsh, F., Roy, P.P.: ICDAR 2011 robust reading competition\u2014challenge 1: reading text in born-digital images (web and email). In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.295"},{"key":"283_CR48","doi-asserted-by":"crossref","unstructured":"Wang, K., Belongie, S.: Word spotting in the wild. In: ECCV (2010)","DOI":"10.1007\/978-3-642-15549-9_43"},{"key":"283_CR49","unstructured":"ICDAR 2015 Competition on Video Script Identification. http:\/\/www.ict.griffith.edu.au\/cvsi2015\/"},{"key":"283_CR50","unstructured":"ICDAR 2003 dataset. http:\/\/algoval.essex.ac.uk\/icdar\/RobustWord.html"},{"key":"283_CR51","unstructured":"ICDAR 2011 dataset. http:\/\/robustreading.opendfki.de\/trac\/wiki\/SceneText"},{"key":"283_CR52","doi-asserted-by":"crossref","unstructured":"Kumar, D., Prasad, M., Ramakrishnan, A.: Benchmarking recognition results on camera captured word image data sets. In: DAR (2012)","DOI":"10.1145\/2432553.2432572"},{"key":"283_CR53","doi-asserted-by":"crossref","unstructured":"Milyaev, S., Barinova, O., Novikova, T., Kohli, P., Lempitsky, V.: Image binarization for end-to-end text understanding in natural images. In: ICDAR (2013)","DOI":"10.1109\/ICDAR.2013.33"},{"key":"283_CR54","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: DAS (2010)","DOI":"10.1145\/1815330.1815333"},{"issue":"2\u20133","key":"283_CR55","doi-asserted-by":"crossref","first-page":"177","DOI":"10.1023\/A:1009954710479","volume":"2","author":"D Lopresti","year":"2000","unstructured":"Lopresti, D., Zhou, J.: Locating and recognizing text in WWW images. Inf. Retr. 2(2\u20133), 177\u2013206 (2000)","journal-title":"Inf. Retr."},{"issue":"5","key":"283_CR56","doi-asserted-by":"crossref","first-page":"564","DOI":"10.1016\/j.imavis.2006.05.003","volume":"25","author":"D Karatzas","year":"2007","unstructured":"Karatzas, D., Antonacopoulos, A.: Colour text segmentation in web images based on human perception. Image Vis. Comput. 25(5), 564\u2013577 (2007)","journal-title":"Image Vis. Comput."},{"key":"283_CR57","doi-asserted-by":"crossref","unstructured":"Kumar, D., Prasad, M.A., Ramakrishnan, A.: NESP: nonlinear enhancement and selection of plane for optimal segmentation and recognition of scene word images. In: IS&T\/SPIE Electronic Imaging (2013)","DOI":"10.1117\/12.2008519"},{"key":"283_CR58","doi-asserted-by":"crossref","unstructured":"Smith, E.H.B.: An analysis of binarization ground truthing. In: DAS (2010)","DOI":"10.1145\/1815330.1815334"},{"key":"283_CR59","volume-title":"Digital Image Process","author":"RC Gonzalez","year":"2005","unstructured":"Gonzalez, R.C., Woods, R.E.: Digital Image Process. Prentice-Hall of India Pvt. Ltd, Delhi (2005)"},{"key":"283_CR60","unstructured":"ABBYY Finereader 8.0. http:\/\/www.abbyy.com\/"},{"key":"283_CR61","doi-asserted-by":"crossref","unstructured":"Shahab, A., Shafait, F., Dengel, A.: ICDAR2011 robust reading competition challenge 2: Reading text in scene images. In: ICDAR (2011)","DOI":"10.1109\/ICDAR.2011.296"},{"key":"283_CR62","unstructured":"Lu, Z., Wu, Z., Brown, M.S.: Directed assistance for ink-bleed reduction in old documents. In: CVPR (2009)"},{"key":"283_CR63","unstructured":"Lu, Z., Wu, Z., Brown, M.S.: Interactive degraded document binarization: an example (and case) for interactive computer vision. In: WACV (2009)"},{"key":"283_CR64","doi-asserted-by":"crossref","unstructured":"Mishra, A., Alahari, K., Jawahar, C.: Top-down and bottom-up cues for scene text recognition. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"283_CR65","doi-asserted-by":"crossref","unstructured":"Jaderberg, M., Vedaldi, A., Zisserman, A.: Deep features for text spotting. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"283_CR66","doi-asserted-by":"crossref","unstructured":"Novikova, T., Barinova, O., Kohli, P., Lempitsky, V.: Large-lexicon attribute-consistent text recognition in natural images. In: ECCV (2012)","DOI":"10.1007\/978-3-642-33783-3_54"},{"key":"283_CR67","doi-asserted-by":"crossref","unstructured":"Shi, C., Wang, C., Xiao, B., Zhang, Y., Gao, S., Zhang, Z.: Scene text recognition using part-based tree-structured character detection. In: CVPR (2013)","DOI":"10.1109\/CVPR.2013.381"},{"key":"283_CR68","doi-asserted-by":"crossref","unstructured":"Jahangiri, M., Heesch, D.: Modified grabcut for unsupervised object segmentation. In: ICIP (2009)","DOI":"10.1109\/ICIP.2009.5414500"},{"key":"283_CR69","doi-asserted-by":"crossref","unstructured":"Khattab, D., Ebied, H.M., Hussein, A.S., Tolba, M.F.: Multi-label automatic grabcut for image segmentation. In: HIS (2014)","DOI":"10.1109\/HIS.2014.7086189"},{"key":"283_CR70","doi-asserted-by":"crossref","unstructured":"Khattab, D., Ebied, H.M., Hussein, A.S., Tolba, M.F.: Color image segmentation based on different color space models using automatic GrabCut. Sci. World J. 2014, 10 (2014)","DOI":"10.1155\/2014\/126025"},{"key":"283_CR71","doi-asserted-by":"crossref","unstructured":"Jegelka, S., Bilmes, J.: Submodularity beyond submodular energies: coupling edges in graph cuts. In: CVPR (2011)","DOI":"10.1109\/CVPR.2011.5995589"}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-017-0283-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-017-0283-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-017-0283-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,20]],"date-time":"2019-09-20T11:02:12Z","timestamp":1568977332000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-017-0283-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,3]]},"references-count":71,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2017,6]]}},"alternative-id":["283"],"URL":"https:\/\/doi.org\/10.1007\/s10032-017-0283-9","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2017,4,3]]}}}