{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:27:19Z","timestamp":1740122839946,"version":"3.37.3"},"reference-count":53,"publisher":"Springer Science and Business Media LLC","issue":"13","license":[{"start":{"date-parts":[[2017,3,9]],"date-time":"2017-03-09T00:00:00Z","timestamp":1489017600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61303171","61303175"],"award-info":[{"award-number":["61303171","61303175"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDA06031000"],"award-info":[{"award-number":["XDA06031000"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2017,7]]},"DOI":"10.1007\/s11042-017-4538-8","type":"journal-article","created":{"date-parts":[[2017,3,9]],"date-time":"2017-03-09T02:30:32Z","timestamp":1489026632000},"page":"15083-15103","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Detecting Uyghur text in complex background images with convolutional neural network"],"prefix":"10.1007","volume":"76","author":[{"given":"Shancheng","family":"Fang","sequence":"first","affiliation":[]},{"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Zhineng","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Shiai","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Xiaoyan","family":"Gu","sequence":"additional","affiliation":[]},{"given":"Xingyu","family":"Gao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,3,9]]},"reference":[{"key":"4538_CR1","doi-asserted-by":"crossref","unstructured":"Ahmad AMA, Alqutami A, Atoum J (2012) A robust algorithm for arabic video text detection. In: Proceedings of the 2011 2nd international congress on computer applications and computational science. Springer, pp 261\u2013266","DOI":"10.1007\/978-3-642-28308-6_35"},{"key":"4538_CR2","doi-asserted-by":"crossref","unstructured":"Bai J, Chen Z, Feng B, Xu B (2014) Chinese image text recognition on grayscale pixels. In: ICASSP. IEEE, pp 1380\u20131384","DOI":"10.1109\/ICASSP.2014.6853823"},{"key":"4538_CR3","doi-asserted-by":"crossref","unstructured":"Bai J, Chen Z, Feng B, Xu B (2014) Image character recognition using deep convolutional neural network learned from different languages. In: ICIP. IEEE, pp 2560\u20132564","DOI":"10.1109\/ICIP.2014.7025518"},{"key":"4538_CR4","doi-asserted-by":"crossref","unstructured":"Chen J, Song Y, Xie H, Chen X, Deng H, Liu Y (2016) Robust uyghur text localization in complex background images. In: PCM, volume 9917 of lecture notes in computer science. Springer, pp 406\u2013416","DOI":"10.1007\/978-3-319-48896-7_40"},{"key":"4538_CR5","doi-asserted-by":"crossref","unstructured":"Chen Z, Chen Y, Gao X, Wang S, Hu L, Yan C C, Lane N D, Miao C (2015) Unobtrusive sensing incremental social contexts using fuzzy class incremental learning. In: ICDM. IEEE Computer Society, pp 71\u201380","DOI":"10.1109\/ICDM.2015.156"},{"key":"4538_CR6","doi-asserted-by":"crossref","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform. In: CVPR. IEEE Computer Society, pp 2963\u20132970","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"4538_CR7","doi-asserted-by":"crossref","unstructured":"Girshick RB (2015) Fast R-CNN. In: ICCV. IEEE Computer Society, pp 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"4538_CR8","doi-asserted-by":"crossref","unstructured":"Girshick RB, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR. IEEE Computer Society, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"4538_CR9","doi-asserted-by":"crossref","unstructured":"Halima MB, Karray H, Alimi AM (2010) A comprehensive method for arabic video text detection, localization, extraction and recognition. In: PCM, volume 6298 of lecture notes in computer science. Springer, pp 648\u2013659","DOI":"10.1007\/978-3-642-15696-0_60"},{"key":"4538_CR10","unstructured":"He K, Zhang X, Ren S, Sun J (2015) Deep residual learning for image recognition. CoRR, arXiv: 1512.03385"},{"issue":"6","key":"4538_CR11","doi-asserted-by":"crossref","first-page":"2529","DOI":"10.1109\/TIP.2016.2547588","volume":"25","author":"T He","year":"2016","unstructured":"He T, Huang W, Qiao Y, Yao J (2016) Text-attentional convolutional neural network for scene text detection. IEEE Trans Image Process 25(6):2529\u20132541","journal-title":"IEEE Trans Image Process"},{"key":"4538_CR12","doi-asserted-by":"crossref","unstructured":"Huang W, Lin Z, Yang J, Wang J (2013) Text localization in natural images using stroke feature transform and text covariance descriptors. In: ICCV. IEEE Computer Society, pp 1241\u20131248","DOI":"10.1109\/ICCV.2013.157"},{"key":"4538_CR13","doi-asserted-by":"crossref","unstructured":"Huang W, Qiao Y, Tang X (2014) Robust scene text detection with convolution neural network induced MSER trees. In: ECCV, volume 8692 of lecture notes in computer science. Springer, pp 497\u2013511","DOI":"10.1007\/978-3-319-10593-2_33"},{"issue":"1","key":"4538_CR14","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11263-015-0823-z","volume":"116","author":"M Jaderberg","year":"2016","unstructured":"Jaderberg M, Simonyan K, Vedaldi A, Zisserman A (2016) Reading text in the wild with convolutional neural networks. Int J Comput Vis 116(1):1\u201320","journal-title":"Int J Comput Vis"},{"key":"4538_CR15","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Deep features for text spotting. In: ECCV, volume 8692 of lecture notes in computer science. Springer, pp 512\u2013528","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"4538_CR16","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick RB, Guadarrama So, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: ACM multimedia. ACM, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"key":"4538_CR17","doi-asserted-by":"crossref","unstructured":"Kang L, Li Y, Doermann DS (2014) Orientation robust text line detection in natural images. In: CVPR. IEEE Computer Society, pp 4034\u20134041","DOI":"10.1109\/CVPR.2014.514"},{"key":"4538_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas D, Shafait F, Uchida S, Iwamura M, Gomez i Bigorda L, Mestre SR, Mas J, Mota DF, Almaz\u00e1n J, de las Heras L-P (2013) ICDAR 2013 robust reading competition. In: ICDAR. IEEE Computer Society, pp 1484\u20131493","DOI":"10.1109\/ICDAR.2013.221"},{"key":"4538_CR19","unstructured":"Lin M, Chen Q, Yan S (2013) Network in network. arXiv: 1312.4400"},{"key":"4538_CR20","doi-asserted-by":"crossref","unstructured":"Long J, Shelhamer E, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR. IEEE Computer Society, pp 3431\u20133440","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"4538_CR21","doi-asserted-by":"crossref","unstructured":"Moradi M, Mozaffari S, Orouji AA (2010) Farsi\/arabic text extraction from video images by corner detection. In: 2010 6th Iranian conference on machine vision and image processing. IEEE, pp 1\u20136","DOI":"10.1109\/IranianMVIP.2010.5941145"},{"key":"4538_CR22","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2012) Real-time scene text localization and recognition. In: CVPR. IEEE Computer Society, pp 3538\u20133545","DOI":"10.1109\/CVPR.2012.6248097"},{"issue":"9","key":"4538_CR23","doi-asserted-by":"crossref","first-page":"1872","DOI":"10.1109\/TPAMI.2015.2496234","volume":"38","author":"L Neumann","year":"2016","unstructured":"Neumann L, Matas J (2016) Real-time lexicon-free scene text localization and recognition. IEEE Trans Pattern Anal Mach Intell 38(9):1872\u20131885","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4538_CR24","unstructured":"Ren S, He K, Girshick RB, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: NIPS, pp 91\u201399"},{"key":"4538_CR25","doi-asserted-by":"crossref","unstructured":"Saudagar AKJ, Mohammed HV, Iqbal K, Gyani YJ (2015) Efficient arabic text extraction and recognition using thinning and dataset comparison technique. In: 2015 international conference on communication, information & computing technology (ICCICT). IEEE, pp 1\u20135","DOI":"10.1109\/ICCICT.2015.7045725"},{"key":"4538_CR26","unstructured":"Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y (2013) Overfeat: integrated recognition, localization and detection using convolutional networks. CoRR, arXiv: 1312.6229"},{"key":"4538_CR27","doi-asserted-by":"crossref","unstructured":"Shahab A, Shafait F, Dengel A (2011) ICDAR 2011 robust reading competition challenge 2: teading text in scene images. In: ICDAR. IEEE Computer Society, pp 1491\u20131496","DOI":"10.1109\/ICDAR.2011.296"},{"issue":"1","key":"4538_CR28","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1007\/s11042-013-1385-0","volume":"72","author":"P Shivakumara","year":"2014","unstructured":"Shivakumara P, Dutta A, Tan CL, Pal U (2014) Multi-oriented scene text detection in video based on wavelet and angle projection boundary growing. Multimed Tools Appl 72(1):515\u2013539","journal-title":"Multimed Tools Appl"},{"key":"4538_CR29","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. CoRR, arXiv: 1409.1556"},{"key":"4538_CR30","doi-asserted-by":"crossref","unstructured":"Szegedy C, Liu W, Jia Y, Sermanet P, Reed SE, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A (2015) Going deeper with convolutions. In: CVPR. IEEE Computer Society, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4538_CR31","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2015) Rethinking the inception architecture for computer vision. CoRR, arXiv: 1512.00567"},{"key":"4538_CR32","doi-asserted-by":"crossref","unstructured":"Tian S, Pan Y, Huang C, Lu S, Yu K, Tan CL (2015) Text flow: a unified text detection system in natural scene images. In: ICCV. IEEE Computer Society, pp 4651\u20134659","DOI":"10.1109\/ICCV.2015.528"},{"key":"4538_CR33","unstructured":"Wang K, Babenko B, Belongie SJ (2011) End-to-end scene text recognition. In: ICCV. IEEE Computer Society, pp 1457\u20131464"},{"key":"4538_CR34","unstructured":"Wang T, Wu DJ, Coates A, Ng AY (2012) End-to-end text recognition with convolutional neural networks. In: ICPR. IEEE Computer Society, pp 3304\u20133308"},{"issue":"4","key":"4538_CR35","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 (2006) Object count\/area graphs for the evaluation of object detection and segmentation algorithms. IJDAR 8(4):280\u2013296","journal-title":"IJDAR"},{"key":"4538_CR36","doi-asserted-by":"crossref","unstructured":"Xie H, Gao K, Zhang Y, Li J, Ren H (2011) Common visual pattern discovery via graph matching. In: ACM multimedia. ACM, pp 1385\u20131388","DOI":"10.1145\/2072298.2072021"},{"key":"4538_CR37","doi-asserted-by":"crossref","unstructured":"Xie H, Gao K, Zhang Y, Li J, Liu Y (2011) Pairwise weak geometric consistency for large scale image search. In: ICMR. ACM, p 42","DOI":"10.1145\/1991996.1992038"},{"issue":"5","key":"4538_CR38","doi-asserted-by":"crossref","first-page":"635","DOI":"10.1016\/j.jvcir.2013.04.012","volume":"24","author":"H Xie","year":"2013","unstructured":"Xie H, Zhang Y, Ke G, Tang S, Kefu X, Li G, Li J (2013) Robust common visual pattern discovery using graph matching. J Vis Commun Image Represent 24(5):635\u2013646","journal-title":"J Vis Commun Image Represent"},{"issue":"19","key":"4538_CR39","doi-asserted-by":"crossref","first-page":"12155","DOI":"10.1007\/s11042-015-3112-5","volume":"75","author":"Z Xu","year":"2016","unstructured":"Xu Z, Hu C, Lin M (2016) Video structured description technology based intelligence analysis of surveillance videos for public security applications. Multimedia Tools Appl 75(19):12155\u201312172","journal-title":"Multimedia Tools Appl"},{"issue":"3","key":"4538_CR40","doi-asserted-by":"crossref","first-page":"1283","DOI":"10.1007\/s10586-016-0581-x","volume":"19","author":"Z Xu","year":"2016","unstructured":"Xu Z, Lin M, Hu C, Liu Y (2016) The big data analytics and applications of the surveillance system using video structured description technology. Clust Comput 19(3):1283\u20131292","journal-title":"Clust Comput"},{"issue":"1\u20132","key":"4538_CR41","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1007\/s00607-014-0408-7","volume":"98","author":"Z Xu","year":"2016","unstructured":"Xu Z, Mei L, Liu Y, Hu C, Chen L (2016) Semantic enhanced cloud environment for surveillance data management using video structural description. Computing 98(1\u20132):35\u201354","journal-title":"Computing"},{"issue":"8","key":"4538_CR42","doi-asserted-by":"crossref","first-page":"739","DOI":"10.1109\/LSP.2010.2053200","volume":"17","author":"J Yan","year":"2010","unstructured":"Yan J, Zhu M, Liu H, Liu Y (2010) Visual saliency detection via sparsity pursuit. IEEE Signal Process Lett 17(8):739\u2013742","journal-title":"IEEE Signal Process Lett"},{"key":"4538_CR43","unstructured":"Yao C, Bai X, Liu W, Ma Y, Tu Z (2012) Detecting texts of arbitrary orientations in natural images. In: CVPR. IEEE Computer Society, pp 1083\u20131090"},{"issue":"7","key":"4538_CR44","doi-asserted-by":"crossref","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2015","unstructured":"Ye Q, Doermann DS (2015) Text detection and recognition in imagery: a survey. IEEE Trans Pattern Anal Mach Intell 37(7):1480\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"9","key":"4538_CR45","doi-asserted-by":"crossref","first-page":"1930","DOI":"10.1109\/TPAMI.2014.2388210","volume":"37","author":"X-C Yin","year":"2015","unstructured":"Yin X-C, Pei W-Y, Zhang J, Hao H-W (2015) Multi-orientation scene text detection with adaptive clustering. IEEE Trans Pattern Anal Mach Intell 37 (9):1930\u20131937","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"5","key":"4538_CR46","doi-asserted-by":"crossref","first-page":"970","DOI":"10.1109\/TPAMI.2013.182","volume":"36","author":"X-C Yin","year":"2014","unstructured":"Yin X-C, Yin X, Huang K, Hao H-W (2014) Robust text detection in natural scene images. IEEE Trans Pattern Anal Mach Intell 36(5):970\u2013983","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"4538_CR47","doi-asserted-by":"crossref","unstructured":"Yousfi S, Berrani S-A, Garcia C (2015) ALIF: a dataset for arabic embedded text recognition in TV broadcast. In: ICDAR. IEEE Computer Society, pp 1221\u20131225","DOI":"10.1109\/ICDAR.2015.7333958"},{"issue":"3","key":"4538_CR48","doi-asserted-by":"crossref","first-page":"859","DOI":"10.1007\/s11042-013-1702-7","volume":"74","author":"J Yuan","year":"2015","unstructured":"Yuan J, Wei B, Liu Y, Zhang Y, Wang L (2015) A method for text line detection in natural images. Multimed Tools Appl 74(3):859\u2013884","journal-title":"Multimed Tools Appl"},{"key":"4538_CR49","doi-asserted-by":"crossref","unstructured":"Zayene O, Hennebert J, Touj SM, Ingold R, Amara NEB (2015) A dataset for arabic text detection, tracking and recognition in news videos- activ. In: ICDAR. IEEE Computer Society, pp 996\u20131000","DOI":"10.1109\/ICDAR.2015.7333911"},{"key":"4538_CR50","doi-asserted-by":"crossref","unstructured":"Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. In: ECCV, volume 8689 of lecture notes in computer science. Springer, pp 818\u2013833","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"4538_CR51","doi-asserted-by":"crossref","unstructured":"Zhang Z, Shen W, Yao C, Bai X (2015) Symmetry-based text line detection in natural scenes. In: CVPR. IEEE Computer Society, pp 2558\u20132567","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"4538_CR52","doi-asserted-by":"crossref","unstructured":"Zhang C, Yan J, Li C, Rui X, Liu L, Bie R (2016) On estimating air pollution from photos using convolutional neural network. In: ACM Multimedia. ACM, pp 297\u2013301","DOI":"10.1145\/2964284.2967230"},{"key":"4538_CR53","doi-asserted-by":"crossref","unstructured":"Zhang Z, Zhang C, Shen W, Yao C, Liu W, Bai X (2016) Multi-oriented text detection with fully convolutional networks. CoRR, arXiv: 1604.04018","DOI":"10.1109\/CVPR.2016.451"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-017-4538-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4538-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-017-4538-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2019,9,19]],"date-time":"2019-09-19T10:05:28Z","timestamp":1568887528000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-017-4538-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,3,9]]},"references-count":53,"journal-issue":{"issue":"13","published-print":{"date-parts":[[2017,7]]}},"alternative-id":["4538"],"URL":"https:\/\/doi.org\/10.1007\/s11042-017-4538-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2017,3,9]]}}}