{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,20]],"date-time":"2026-09-20T20:49:23Z","timestamp":1789937363002,"version":"4.0.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2016,6,1]],"date-time":"2016-06-01T00:00:00Z","timestamp":1464739200000},"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":["61222308"],"award-info":[{"award-number":["61222308"]}],"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":["61572207"],"award-info":[{"award-number":["61572207"]}],"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":["61573160"],"award-info":[{"award-number":["61573160"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Open Project Program of the State Key Laboratory of Digital Publishing Technology","award":["F2016001"],"award-info":[{"award-number":["F2016001"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1109\/tip.2016.2555080","type":"journal-article","created":{"date-parts":[[2016,4,15]],"date-time":"2016-04-15T18:15:36Z","timestamp":1460744136000},"page":"2789-2802","source":"Crossref","is-referenced-by-count":86,"title":["Strokelets: A Learned Multi-Scale Mid-Level Representation for Scene Text Recognition"],"prefix":"10.1109","volume":"25","author":[{"given":"Xiang","family":"Bai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6564-4796","authenticated-orcid":false,"given":"Cong","family":"Yao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","first-page":"1","article-title":"Deep structured output learning for unconstrained text recognition","author":"jaderberg","year":"2015","journal-title":"Proc ICLR"},{"key":"ref72","article-title":"Reading text in the wild with convolutional neural networks","author":"jaderberg","year":"2014"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-006-0014-0"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2005.231"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref77","first-page":"273","article-title":"Character recognition in natural images","author":"de campos","year":"2009","journal-title":"Proc VISAPP"},{"key":"ref74","year":"2016","journal-title":"ABBYY Finereader 9 0"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref75","first-page":"1","article-title":"Synthetic data and artificial neural networks for natural scene text recognition","author":"jaderberg","year":"2014","journal-title":"NIPS Deep Learning Workshop"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.177"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.110"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-015-4488-0"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2015.01.023"},{"key":"ref31","article-title":"Label embedding for text recognition","author":"rodriguez-serrano","year":"2013","journal-title":"Proc BMVC"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.87"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","article-title":"Robust text detection in natural scene images","volume":"36","author":"yin","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2484028.2484197"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2013.2249082"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2011.6116200"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/34.400568"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2006.68"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_17"},{"key":"ref63","first-page":"1794","article-title":"Linear spatial pyramid matching using sparse coding for image classification","author":"yang","year":"2009","journal-title":"Proc CVPR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref64","first-page":"647","article-title":"DeCAF: A deep convolutional activation feature for generic visual recognition","author":"donahue","year":"2014","journal-title":"Proc ICML"},{"key":"ref27","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"neumann","year":"2010","journal-title":"Proc ACCV"},{"key":"ref65","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"deng","year":"2009","journal-title":"Proc CVPR"},{"key":"ref66","author":"deng","year":"2012","journal-title":"ImageNet Large Scale Visual Recognition Competition 2012 (ILSVRC2012)"},{"key":"ref29","first-page":"737","article-title":"Text recognition in natural images using multiclass Hough forests","author":"yildirim","year":"2013","journal-title":"Proc VISAPP"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2012.10.009"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.296"},{"key":"ref2","author":"remias","year":"1996","journal-title":"A Real-Time Image Understanding System for an Autonomous Mobile Robot"},{"key":"ref1","author":"webster","year":"1921","journal-title":"A World History"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.516"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.16"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206740"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.124"},{"key":"ref26","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"2010","journal-title":"Proc ECCV"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227749"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.95"},{"key":"ref51","first-page":"3304","article-title":"End-to-end text recognition with convolutional neural networks","author":"wang","year":"2012","journal-title":"Proc ICPR"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-007-0095-3"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15567-3_13"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459303"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"ref55","first-page":"204","article-title":"Spatially local coding for object recognition","author":"mccann","year":"2012","journal-title":"Proc ACCV"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1006\/csla.2001.0184"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref10","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc ICCV"},{"key":"ref11","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"Proc CVPR"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2009.167"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33783-3_54"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.126"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2317980"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.969"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2388210"},{"key":"ref81","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":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0070173"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0640-1"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.12"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.11.005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.381"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.44"},{"key":"ref4","first-page":"3005","article-title":"Mobile product search with bag of hash bits and boundary reranking","author":"feng","year":"2012","journal-title":"Proc CVPR"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TLT.2014.2307305"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/34.982903"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-006-9088-7"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2441954"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2424863"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1117\/12.184094"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref46","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref45","first-page":"396","article-title":"Handwritten digit recognition with a back-propagation network","author":"le cun","year":"1990","journal-title":"Proc NIPS"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.231"},{"key":"ref42","first-page":"73","article-title":"Unsupervised discovery of mid-level discriminative patches","author":"singh","year":"2012","journal-title":"Proc ECCV"},{"key":"ref41","first-page":"282","article-title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","author":"lafferty","year":"2005","journal-title":"Proc ICML"},{"key":"ref44","first-page":"846","article-title":"Max-margin multiple-instance dictionary learning","author":"wang","year":"2013","journal-title":"Proc ICML"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.406"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7452455\/07453176.pdf?arnumber=7453176","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:01:50Z","timestamp":1642003310000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7453176\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,6]]},"references-count":86,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tip.2016.2555080","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2016,6]]}}}