{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T11:18:51Z","timestamp":1774437531393,"version":"3.50.1"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2017,3,1]],"date-time":"2017-03-01T00:00:00Z","timestamp":1488326400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61472102"],"award-info":[{"award-number":["61472102"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672194"],"award-info":[{"award-number":["61672194"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2017,3]]},"DOI":"10.1109\/tip.2017.2656474","type":"journal-article","created":{"date-parts":[[2017,1,20]],"date-time":"2017-01-20T20:54:03Z","timestamp":1484945643000},"page":"1509-1520","source":"Crossref","is-referenced-by-count":97,"title":["Scene Text Detection and Segmentation Based on Cascaded Convolution Neural Networks"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8719-3375","authenticated-orcid":false,"given":"Youbao","family":"Tang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0956-8757","authenticated-orcid":false,"given":"Xiangqian","family":"Wu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.74"},{"key":"ref38","article-title":"Accurate text localization in natural image with cascaded convolutional text network","author":"he","year":"2016"},{"key":"ref33","first-page":"195","article-title":"Scene text detection based on robust stroke width transform and deep belief network","author":"xu","year":"2014","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2012.11.002"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.44"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.102"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1007\/s10032-015-0237-z","article-title":"Scene text extraction based on edges and support vector regression","volume":"18","author":"lu","year":"2015","journal-title":"Int J Document Anal Recognit"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2547588"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0239-x"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.514"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.515"},{"key":"ref29","first-page":"366","article-title":"Detecting and reading text in natural scenes","author":"chen","year":"2004","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.296"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477663"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.528"},{"key":"ref21","first-page":"56","article-title":"Detecting text in natural image with connectionist text proposal network","author":"tian","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref24","first-page":"591","article-title":"Word spotting in the wild","author":"wang","year":"2010","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.178"},{"key":"ref26","doi-asserted-by":"crossref","first-page":"2296","DOI":"10.1109\/TIP.2013.2249082","article-title":"Scene text detection via connected component clustering and nontext filtering","volume":"22","author":"koo","year":"2013","journal-title":"IEEE Trans Image Process"},{"key":"ref25","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.98"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2014.467"},{"key":"ref56","year":"2016","journal-title":"Result of ICDAR2015 Robust Reading Competition"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654889"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.164"},{"key":"ref52","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc AISTATS"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2012.09.019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.451"},{"key":"ref12","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":"ref13","first-page":"770","article-title":"A method for text localization and recognition in real-world images","author":"neumann","year":"2010","journal-title":"Proc Asian Conf Comput Vis"},{"key":"ref14","first-page":"497","article-title":"Robust scene text detection with convolution neural network induced MSER trees","author":"huang","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2302896"},{"key":"ref16","first-page":"91","article-title":"Text localization based on fast feature pyramids and multi-resolution maximally stable extremal regions","author":"zamberletti","year":"2014","journal-title":"Proc Asian Conf Comput Vis Workshops"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2353813"},{"key":"ref18","first-page":"512","article-title":"Deep features for text spotting","author":"jaderberg","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref6","doi-asserted-by":"crossref","first-page":"2594","DOI":"10.1109\/TIP.2011.2126586","article-title":"Text string detection from natural scenes by structure-based partition and grouping","volume":"20","author":"yi","year":"2011","journal-title":"IEEE Trans Image Process"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248097"},{"key":"ref7","first-page":"1083","article-title":"Detecting texts of arbitrary orientations in natural images","author":"yao","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.157"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247990"},{"key":"ref45","first-page":"1457","article-title":"End-to-end scene text recognition","author":"wang","year":"2011","journal-title":"Proc Int Conf Comput Vis"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ACPR.2015.7486484"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2014.34"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.254"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.388"},{"key":"ref44","doi-asserted-by":"crossref","first-page":"1631","DOI":"10.1109\/TPAMI.2003.1251157","article-title":"Texture-based approach for text detection in images using support vector machines and continuously adaptive mean shift algorithm","volume":"25","author":"kim","year":"2003","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2014.2366765"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/7855880\/07828014.pdf?arnumber=7828014","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,1,12]],"date-time":"2022-01-12T16:13:28Z","timestamp":1642004008000},"score":1,"resource":{"primary":{"URL":"http:\/\/ieeexplore.ieee.org\/document\/7828014\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3]]},"references-count":56,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tip.2017.2656474","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,3]]}}}