{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:11:03Z","timestamp":1780333863979,"version":"3.54.1"},"reference-count":32,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T00:00:00Z","timestamp":1623801600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T00:00:00Z","timestamp":1623801600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"name":"the grants from the Department of Industrial and Systems Engineering, Hong Kong Polytechnic University","award":["H-ZG3K"],"award-info":[{"award-number":["H-ZG3K"]}]},{"name":"the Graduate Education Reform Project of Shenzhen University","award":["SZUGS2020JG11"],"award-info":[{"award-number":["SZUGS2020JG11"]}]},{"name":"the Science and Technology Plan Projects of Shenzhen","award":["No. JSGG20200807171601010, JSGG20191127151401743"],"award-info":[{"award-number":["No. JSGG20200807171601010, JSGG20191127151401743"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,8]]},"DOI":"10.1007\/s11042-021-11101-w","type":"journal-article","created":{"date-parts":[[2021,6,16]],"date-time":"2021-06-16T02:02:41Z","timestamp":1623808961000},"page":"29005-29016","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["A scene text detector based on deep feature merging"],"prefix":"10.1007","volume":"80","author":[{"given":"Yong","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yubei","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-1438","authenticated-orcid":false,"given":"Donning","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chun Ho","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wai Hung","family":"Ip","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kai Leung","family":"Yung","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,6,16]]},"reference":[{"key":"11101_CR1","doi-asserted-by":"crossref","unstructured":"Ali A, Zhu Y, Zakarya M (2021) A data aggregation based approach to exploit dynamic spatio-temporal correlations for citywide crowd flows prediction in fog computing[J]. Multimed Tools Appl:1\u201333","DOI":"10.1007\/s11042-020-10486-4"},{"key":"11101_CR2","doi-asserted-by":"publisher","unstructured":"Ch'ng CK, Chan CS (2017) Total-Text: A Comprehensive Dataset for Scene Text Detection and Recognition, pp 935\u2013942. https:\/\/doi.org\/10.1109\/ICDAR.2017.157","DOI":"10.1109\/ICDAR.2017.157"},{"key":"11101_CR3","doi-asserted-by":"publisher","first-page":"153400","DOI":"10.1109\/ACCESS.2019.2948405","volume":"7","author":"L Deng","year":"2019","unstructured":"Deng L, Gong Y, Lu X, Lin Y, Ma Z, Xie M (2019) STELA: a real-time scene text detector with learned anchor[J]. IEEE Access 7:153400\u2013153407","journal-title":"IEEE Access"},{"key":"11101_CR4","doi-asserted-by":"crossref","unstructured":"Epshtein B, Ofek E, Wexler Y (2010) Detecting text in natural scenes with stroke width transform[C]. 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE, pp 2963\u20132970","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"11101_CR5","doi-asserted-by":"crossref","unstructured":"He P, Huang W, He T, Zhu Q, Qiao Y, Li X (2017) Single Shot Text Detector with Regional Attention. In Proc. of ICCV","DOI":"10.1109\/ICCV.2017.331"},{"key":"11101_CR6","doi-asserted-by":"crossref","unstructured":"Huang W, Qiao Y, Tang X (2014) Robust scene text detection with convolution neural network induced mser trees. In Proc. of ECCV","DOI":"10.1007\/978-3-319-10593-2_33"},{"key":"11101_CR7","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L et al (2017) Densely connected convolutional networks[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA. IEEE, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"11101_CR8","doi-asserted-by":"crossref","unstructured":"Jaderberg M, Vedaldi A, Zisserman A (2014) Deep features for text spotting[C]\/\/European conference on computer vision. Springer, Cham, pp 512\u2013528","DOI":"10.1007\/978-3-319-10593-2_34"},{"key":"11101_CR9","doi-asserted-by":"crossref","unstructured":"Jiang Y, Zhu X , Wang X, Yang S, Li W, Wang H, Fu P, Luo Z (2017) R2CNN: Rotational region CNN for orientation robust scene text detection. CoRR, vol. abs\/1706.09579","DOI":"10.1109\/ICPR.2018.8545598"},{"key":"11101_CR10","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A et al (2015) ICDAR 2015 Competition on robust reading[C]\/\/ 2015 13th international conference on document analysis and recognition, IEEE, pp 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"11101_CR11","unstructured":"Kim KH et al (2016) PVANET: Deep but lightweight neural networks for real-time object detection. arXiv preprint arXiv:1608.08021"},{"key":"11101_CR12","unstructured":"Kingma DP, Ba J (2015) Adam: A Method for Stochastic Optimization[C]. International Conference for Learning Representations, San Diego, USA. 2015: CoRR abs\/1412.6980"},{"key":"11101_CR13","doi-asserted-by":"crossref","unstructured":"Liu W, Anguelov D, Erhan D et al (2016) Ssd: single shot multibox detector[C]\/\/ proceedings of European conference on computer vision, Springer, Cham, pp 21\u201337","DOI":"10.1007\/978-3-319-46448-0_2"},{"issue":"11","key":"11101_CR14","doi-asserted-by":"publisher","first-page":"3111","DOI":"10.1109\/TMM.2018.2818020","volume":"20","author":"J Ma","year":"2018","unstructured":"Ma J, Shao W, Ye H, Wang L, Wang H, Zheng Y, Xue X (2018) Arbitrary-oriented scene text detection via rotation proposals[J]. IEEE Trans Multimed 20(11):3111\u20133122","journal-title":"IEEE Trans Multimed"},{"key":"11101_CR15","doi-asserted-by":"crossref","unstructured":"Milletari F, Navab N, Ahmadi S A (2016) V-net: fully convolutional neural networks for volumetric medical image segmentation[C]. Proceedings of 2016 fourth international conference on 3D vision, Los Alamitos, CA, USA. IEEE Computer Society, pp 565\u2013571","DOI":"10.1109\/3DV.2016.79"},{"key":"11101_CR16","doi-asserted-by":"publisher","unstructured":"Nahari R, Putro S, Setiawan N, Alflta R (2020) Detecting Text in the Scene Text Image Using Fast Fourier Transform. Journal of Physics: Conference Series. 1569. 032070. https:\/\/doi.org\/10.1088\/1742-6596\/1569\/3\/032070","DOI":"10.1088\/1742-6596\/1569\/3\/032070"},{"key":"11101_CR17","doi-asserted-by":"crossref","unstructured":"Neumann L, Matas J (2010) A method for text localization and recognition in real-world images[C]. Asian conference on computer vision. Springer, Berlin, Heidelberg, pp 770\u2013783","DOI":"10.1007\/978-3-642-19318-7_60"},{"key":"11101_CR18","doi-asserted-by":"publisher","unstructured":"Ranjitha P, Rajashekar K, Shamjith (2020) A Review on Text Detection from Multi-Oriented Text Images in Different Approaches, pp 240\u2013245. https:\/\/doi.org\/10.1109\/ICESC48915.2020.9156002","DOI":"10.1109\/ICESC48915.2020.9156002"},{"key":"11101_CR19","unstructured":"Ren S, He K, Girshick R et al (2015) Faster r-cnn: towards real-time object detection with region proposal networks[C]. Proceedings of the international conference on neural information processing systems, Istanbul, Turkey. pp 91\u201399"},{"key":"11101_CR20","doi-asserted-by":"crossref","unstructured":"Rezatofighi H, Tsoi N, Gwak J Y et al (2019) Generalized intersection over union: a metric and a loss for bounding box regression[C]. Proceedings of conference on computer vision and pattern recognition, Long Beach, CA, USA. IEEE, pp 658\u2013666","DOI":"10.1109\/CVPR.2019.00075"},{"key":"11101_CR21","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Belongie S (2017) Detecting oriented text in natural images by linking segments[C]. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. Hawaii, USA. IEEE, 2550\u20132558","DOI":"10.1109\/CVPR.2017.371"},{"key":"11101_CR22","doi-asserted-by":"crossref","unstructured":"Tian Z, Huang W, He T et al (2016) Detecting text in natural image with connectionist text proposal network[C]\/\/European conference on computer vision. Springer, Cham, pp 56\u201372","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"11101_CR23","unstructured":"Xing D, Li Z, Chen X et al (2017) Arbitext: Arbitrary-oriented text detection in unconstrained scene[J]. arXiv preprint arXiv:1711.11249"},{"issue":"11","key":"11101_CR24","doi-asserted-by":"publisher","first-page":"5566","DOI":"10.1109\/TIP.2019.2900589","volume":"28","author":"Y Xu","year":"2019","unstructured":"Xu Y, Wang Y, Zhou W, Wang Y, Yang Z, Bai X (2019) TextField: learning a deep direction field for irregular scene text detection[J]. IEEE Trans Image Process 28(11):5566\u20135579","journal-title":"IEEE Trans Image Process"},{"key":"11101_CR25","unstructured":"Yao C, Bai X, Liu W et al (2012) Detecting texts of arbitrary orientations in natural images[C]. Proceedings of the 2012 IEEE conference on computer vision and pattern recognition, Providence, RI, USA. IEEE, pp 1083\u20131090"},{"key":"11101_CR26","unstructured":"Yao C, Bai X, Sang Net al (2016) Scene text detection via holistic, multi-channel prediction[J]. arXiv preprint arXiv:1606.09002"},{"issue":"7","key":"11101_CR27","doi-asserted-by":"publisher","first-page":"1480","DOI":"10.1109\/TPAMI.2014.2366765","volume":"37","author":"Q Ye","year":"2014","unstructured":"Ye Q, Doermann D (2014) Text detection and recognition in imagery: a survey[J]. IEEE Trans Pattern Anal Mach Intell 37(7):1480\u20131500","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11101_CR28","doi-asserted-by":"crossref","unstructured":"Yu J, Jiang Y, Wang Z et al (2016) Unitbox: an advanced object detection network[C]. Proceedings of the 24th ACM international conference on multimedia, New York, NY, USA. Association for Computing Machinery, pp 516\u2013520","DOI":"10.1145\/2964284.2967274"},{"key":"11101_CR29","doi-asserted-by":"crossref","unstructured":"Zhang Z, Zhang C, Shen W et al (2016) Multi-oriented text detection with fully convolutional networks[C]. Proceedings of the 2016 IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA. IEEE, pp 4159\u20134167","DOI":"10.1109\/CVPR.2016.451"},{"key":"11101_CR30","doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H et al (2017) EAST: an efficient and accurate scene text detector[C]. Proceedings of the 2017 IEEE conference on computer vision and pattern recognition, Honolulu, HI, USA. IEEE, pp 2642\u20132651","DOI":"10.1109\/CVPR.2017.283"},{"key":"11101_CR31","doi-asserted-by":"crossref","unstructured":"Zhu S, Zanibbi R (2016) A text detection system for natural scenes with convolutional feature learning and cascaded classification[C]. Proceedings of the IEEE conference on computer vision and pattern recognition, Las Vegas, NV, USA. IEEE, pp 625\u2013632","DOI":"10.1109\/CVPR.2016.74"},{"issue":"1","key":"11101_CR32","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11704-015-4488-0","volume":"10","author":"Y Zhu","year":"2016","unstructured":"Zhu Y, Yao C, Bai X (2016) Scene text detection and recognition: recent advances and future trends[J]. Front Comput Sci 10(1):19\u201336","journal-title":"Front Comput Sci"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11101-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11101-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11101-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,19]],"date-time":"2021-08-19T17:57:56Z","timestamp":1629395876000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11101-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,16]]},"references-count":32,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2021,8]]}},"alternative-id":["11101"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11101-w","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,16]]},"assertion":[{"value":"5 August 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 April 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 June 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}