{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T21:02:55Z","timestamp":1773090175866,"version":"3.50.1"},"reference-count":53,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"7","license":[{"start":{"date-parts":[[2014,7,1]],"date-time":"2014-07-01T00:00:00Z","timestamp":1404172800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61172103"],"award-info":[{"award-number":["61172103"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61271429"],"award-info":[{"award-number":["61271429"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["60933010"],"award-info":[{"award-number":["60933010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2012AA041312"],"award-info":[{"award-number":["2012AA041312"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2014,7]]},"DOI":"10.1109\/tcsvt.2014.2302522","type":"journal-article","created":{"date-parts":[[2014,6,30]],"date-time":"2014-06-30T14:31:00Z","timestamp":1404138660000},"page":"1235-1250","source":"Crossref","is-referenced-by-count":27,"title":["Scene Text Recognition Using Structure-Guided Character Detection and Linguistic Knowledge"],"prefix":"10.1109","volume":"24","author":[{"given":"Cun-Zhao","family":"Shi","sequence":"first","affiliation":[]},{"given":"Chun-Heng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bai-Hua","family":"Xiao","sequence":"additional","affiliation":[]},{"given":"Song","family":"Gao","sequence":"additional","affiliation":[]},{"given":"Jin-Long","family":"Hu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/34.993558"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.219"},{"key":"ref32","first-page":"1","article-title":"Character recognition in natural images","author":"de campos","year":"2009","journal-title":"Proc Int Joint Conf Comput Vis Imag Comput Graph Theory Appl"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819223"},{"key":"ref30","author":"niblack","year":"1985","journal-title":"An Introduction to Digital Image Processing"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.320"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995700"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.38"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.95"},{"key":"ref28","article-title":"Scene text recognition with bilateral regression","author":"feild","year":"2012"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.07.008"},{"key":"ref29","first-page":"285","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"otsu","year":"1975","journal-title":"Automatica"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459462"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.381"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICIS.2008.31"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-540-27814-6_28","article-title":"Unsupervised text segmentation using color and wavelet features","author":"gllavata","year":"2004","journal-title":"Image and Video Retrieval"},{"key":"ref24","first-page":"2905","article-title":"Automatic text segmentation from complex background","volume":"5","author":"ye","year":"2004","journal-title":"Proc ICIP"},{"key":"ref23","doi-asserted-by":"crossref","first-page":"227","DOI":"10.1109\/ICPR.2002.1047438","article-title":"Text segmentation and recognition in complex background based on Markov random field","volume":"4","author":"chen","year":"2002","journal-title":"Proc 16th Int Conf Pattern Recognit"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2012.15"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2010.05.031"},{"key":"ref50","author":"duda","year":"2012","journal-title":"Pattern Classification"},{"key":"ref51","first-page":"901","article-title":"SRILM—An extensible language modeling toolkit","volume":"2","author":"stolcke","year":"2002","journal-title":"Proc Int Conf Spoken Lang Process"},{"key":"ref53","year":"2014","journal-title":"ABBYY Finereader 9 0"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2012.11.002"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2012.2199327"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.166"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2012.26"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.09.019"},{"key":"ref13","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"2010","journal-title":"Proc 11th ECCV"},{"key":"ref14","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc ICCV"},{"key":"ref15","first-page":"1","article-title":"Scene text recognition using higher order langauge priors","author":"mishra","year":"2012","journal-title":"Proc 23rd BMVC"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref17","first-page":"752","article-title":"Large-lexicon attribute-consistent text recognition in natural images","author":"novikova","year":"2012","journal-title":"Proc 12th ECCV"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.126"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.125"},{"key":"ref4","first-page":"366","article-title":"Detecting and reading text in natural scenes","volume":"2","author":"chen","year":"2004","journal-title":"Proc IEEE CVPR"},{"key":"ref3","first-page":"1","article-title":"An adaptive algorithm for text detection from natural scenes","volume":"2","author":"gao","year":"2001","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2005.01.004"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.841653"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.264"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"800","DOI":"10.1109\/TIP.2010.2070803","article-title":"A hybrid approach to detect and localize texts in natural scene images","volume":"20","author":"pan","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995741"},{"key":"ref45","author":"everingham","year":"2009","journal-title":"The PASCAL Visual Object Classes Challenge 2009 (VOC2009) Results"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.296"},{"key":"ref47","first-page":"2879","article-title":"Face detection, pose estimation, and landmark localization in the wild","author":"xiangxin","year":"2011","journal-title":"Proc IEEE CVPR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1023\/B:VISI.0000042934.15159.49"},{"key":"ref41","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc 21st ICPR"},{"key":"ref44","author":"everingham","year":"2008","journal-title":"The PASCAL Visual Object Classes Challenge 2008 (VOC2008) results"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/6846390\/06727574.pdf?arnumber=6727574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T11:57:51Z","timestamp":1641988671000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/6727574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014,7]]},"references-count":53,"journal-issue":{"issue":"7"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2014.2302522","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014,7]]}}}