{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T07:28:42Z","timestamp":1740122922939,"version":"3.37.3"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T00:00:00Z","timestamp":1691366400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16389-4","type":"journal-article","created":{"date-parts":[[2023,8,7]],"date-time":"2023-08-07T06:02:16Z","timestamp":1691388136000},"page":"22433-22454","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["TextFuse: Fusing Deep Scene Text Detection Models for Enhanced Performance"],"prefix":"10.1007","volume":"83","author":[{"given":"Xianjin","family":"Shi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0961-4370","authenticated-orcid":false,"given":"Guowen","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Xiajiong","family":"Shen","sequence":"additional","affiliation":[]},{"given":"Chongsheng","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,8,7]]},"reference":[{"key":"16389_CR1","doi-asserted-by":"crossref","unstructured":"Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image and vision computing 22(10), pp. 761-767(2004)","DOI":"10.1016\/j.imavis.2004.02.006"},{"key":"16389_CR2","doi-asserted-by":"crossref","unstructured":"Epshtein, B., Ofek, E., Wexler, Y.: Detecting text in natural scenes with stroke width transform. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2963-2970 (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"16389_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Shen, W., Yao, C., Bai, X.: Symmetry-based text line detection in natural scenes. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2558-2567 (2015) https:\/\/doi.org\/10.1109\/CVPR.2015.7298871","DOI":"10.1109\/CVPR.2015.7298871"},{"key":"16389_CR4","unstructured":"Wang, K., Babenko, B., Belongie, S.: End-to-end scene text recognition. In: 2011 International Conference on Computer Vision, pp. 1457-1464 (2011)"},{"key":"16389_CR5","unstructured":"Y, X.: Research on Text Detection and Recognition Algorithm of Natural Scenes based on Deep Learning. PhD thesis, Xidian university (2017)"},{"key":"16389_CR6","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint http:\/\/arxiv.org\/abs\/1409.1556arXiv:1409.1556 (2014)"},{"key":"16389_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770-778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"16389_CR8","doi-asserted-by":"crossref","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.:SSD: Single shot multibox detector. In: European Conference on Computer Vision, pp. 21-37 (2016)","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"16389_CR9","doi-asserted-by":"crossref","unstructured":"Shi, B., Bai, X., Belongie, S.: Detecting oriented text in natural images by linking segments. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2550-2558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"issue":"8","key":"16389_CR10","doi-asserted-by":"publisher","first-page":"3676","DOI":"10.1109\/TIP.2018.2825107","volume":"27","author":"M Liao","year":"2018","unstructured":"Liao M, Shi B, Bai X (2018) Textboxes++: A single-shot oriented scene text detector. IEEE transactions on image processing 27(8):3676\u20133690","journal-title":"IEEE transactions on image processing"},{"key":"16389_CR11","doi-asserted-by":"crossref","unstructured":"Liao, M., Shi, B., Bai, X., Wang, X., Liu, W.: Textboxes: A fast text detector with a single deep neural network. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 4161-4167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"16389_CR12","unstructured":"C, L.: Research on text detection and location of natural scenes based on deep learning. PhD thesis, South China university of technology (2018)"},{"key":"16389_CR13","doi-asserted-by":"crossref","unstructured":"Tian, Z., Huang, W., He, T., He, P., Qiao, Y.: Detecting text in natural image with connectionist text proposal network. In: European Conference on Computer Vision (ECCV 2016), pp. 56-72 (2016)","DOI":"10.1007\/978-3-319-46484-8_4"},{"key":"16389_CR14","doi-asserted-by":"crossref","unstructured":"Zhou, X., Yao, C., Wen, H., Wang, Y., Zhou, S., He, W., Liang, J.: EAST: An Efficient and Accurate Scene Text Detector. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2642-2651 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.283","DOI":"10.1109\/CVPR.2017.283"},{"key":"16389_CR15","doi-asserted-by":"crossref","unstructured":"Deng, D., Liu, H., Li, X., Cai, D.: Pixellink: Detecting scene text via instance segmentation. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6773-6780 (2018)","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"16389_CR16","doi-asserted-by":"crossref","unstructured":"Graves, A., Schmidhuber, J.: Framewise phoneme classification with bidirectional LSTM and other neural network architectures. Neural networks 18(5-6), pp. 602-610(2005)","DOI":"10.1016\/j.neunet.2005.06.042"},{"issue":"1","key":"16389_CR17","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/TPAMI.2015.2437384","volume":"38","author":"R Girshick","year":"2015","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2015) Region-based convolutional networks for accurate object detection and segmentation. IEEE transactions on pattern analysis and machine intelligence 38(1):142\u2013158","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"issue":"11","key":"16389_CR18","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. IEEE Transactions on Multimedia 20(11):3111\u20133122","journal-title":"IEEE Transactions on Multimedia"},{"key":"16389_CR19","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1016\/j.neucom.2019.01.013","volume":"334","author":"L Deng","year":"2019","unstructured":"Deng L, Gong Y, Lin Y, Shuai J, Tu X, Zhang Y, Ma Z, Xie M (2019) Detecting multi-oriented text with corner-based region proposals. Neurocomputing 334:134\u2013142","journal-title":"Neurocomputing"},{"key":"16389_CR20","unstructured":"S, W.: Research on text detection algorithm of natural scenes based on deep learning. PhD thesis, Hangzhou University of Electronic Science and Technology (2018)"},{"key":"16389_CR21","doi-asserted-by":"crossref","unstructured":"Cai, C., Lv, P., Su, B.: Feature Fusion Network for Scene Text Detection. In: 2018 25th IEEE International Conference on Image Processing (ICIP), pp. 2755-2759(2018)","DOI":"10.1109\/ICIP.2018.8451402"},{"key":"16389_CR22","doi-asserted-by":"crossref","unstructured":"On the Fusion of Text Detection Results (2020) Campana, J.L.F., Pinto, A., Neira, M.A.C., Decker, L.G.L., Santos, A., Concei\u00e7ao, J. S. Torres, R.D.S. A Genetic Programming Approach. IEEE Access 8:81257\u201381270","DOI":"10.1109\/ACCESS.2020.2987869"},{"key":"16389_CR23","doi-asserted-by":"crossref","unstructured":"Bhunia, A.K., Sain, A., Chowdhury, P.N., Song, Y.-Z.: Text is text, no matter what: Unifying text recognition using knowledge distillation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 983-992(2021)","DOI":"10.1109\/ICCV48922.2021.00102"},{"key":"16389_CR24","doi-asserted-by":"crossref","unstructured":"Yu, D., Li, X., Zhang, C., Liu, T., Han, J., Liu, J., Ding, E.: Towards accurate scene text recognition with semantic reasoning networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12113-12122 (2020)","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"16389_CR25","doi-asserted-by":"crossref","unstructured":"Tychsen-Smith, L., Petersson, L.: Denet: Scalable real-time object detection with directed sparse sampling. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 428-436 (2017)","DOI":"10.1109\/ICCV.2017.54"},{"key":"16389_CR26","unstructured":"Wang, X., Chen, K., Huang, Z., Yao, C., Liu, W.: Point linking network for object detection. arXiv preprint http:\/\/arxiv.org\/abs\/1706.03646arXiv:1706.03646 (2017)"},{"key":"16389_CR27","unstructured":"Van Rijsbergen, C.: Information retrieval: theory and practice. In: Proceedings of the Joint IBM\/University of Newcastle upon Tyne Seminar on Data Base Systems, vol. 79 (1979)"},{"key":"16389_CR28","unstructured":"Sasaki, Y., et al.: The truth of the f-measure. 2007. URL: https:\/\/www.cs.odu.edu\/mukka\/cs795sum09dm\/Lecturenotes\/Day3\/F-measure-YS-26Oct07.pdf [accessed 2021-05-26] 49 (2007)"},{"key":"16389_CR29","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception Architecture for Computer Vision. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2818-2826 (2016). https:\/\/doi.org\/10.1109\/CVPR.2016.308","DOI":"10.1109\/CVPR.2016.308"},{"key":"16389_CR30","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De Las Heras, L.P.: Icdar 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484-1493 (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"16389_CR31","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Gomez-Bigorda, L., Nicolaou, A., Ghosh, S., Bagdanov, A., Iwamura, M., Matas, J., Neumann, L., Chandrasekhar, V.R., Lu, S., et al.: ICDAR 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156-1160 (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"16389_CR32","unstructured":"Yao, C., Bai, X., Liu, W., Ma, Y., Tu, Z.: Detecting texts of arbitrary orientations in natural images. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1083-1090 (2012)"},{"key":"16389_CR33","doi-asserted-by":"crossref","unstructured":"Shi, B., Yao, C., Liao, M., Yang, M., Xu, P., Cui, L., Belongie, S., Lu, S., Bai, X.: ICDAR2017 competition on reading chinese text in the wild (RCTW-17). In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 1, pp. 1429-1434 (2017)","DOI":"10.1109\/ICDAR.2017.233"},{"key":"16389_CR34","doi-asserted-by":"crossref","unstructured":"Zhang, C., Ding, W., Peng, G., Fu, F., Wang, W.: Street View Text Recognition With Deep Learning for Urban Scene Understanding in Intelligent Transportation Systems. IEEE Transactions on Intelligent Transportation Systems 22(7), 4727-4743 (2021). https:\/\/doi.org\/10.1109\/TITS.2020.3017632","DOI":"10.1109\/TITS.2020.3017632"},{"key":"16389_CR35","doi-asserted-by":"crossref","unstructured":"Yu, W., Liu, Y., Hua, W., Jiang, D., Ren, B., Bai, X.: Turning a clip model into a scene text detector. arXiv preprint http:\/\/arxiv.org\/abs\/2302.14338arXiv:2302.14338 (2023)","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"16389_CR36","doi-asserted-by":"crossref","unstructured":"Pourhatami, A., Kaviyani-Charati, M., Kargar, B., Baziyad, H., Kargar, M., Olmeda-G\u00f3mez, C.: Mapping the intellectual structure of the coronavirus field (2000-2020): a co-word analysis. Scientometrics 126(8), pp. 6625-6657 (2021)","DOI":"10.1007\/s11192-021-04038-2"},{"key":"16389_CR37","doi-asserted-by":"crossref","unstructured":"Hosseini, S., Baziyad, H., Norouzi, R., Jabbedari Khiabani, S., Gid\u00f3falvi, G., Albadvi, A., Alimohammadi, A., Seyedabrishami, S.: Mapping the intellectual structure of gis-t field (2008-2019): A dynamic co-word analysis. Scientometrics 126, pp. 2667-2688 (2021)","DOI":"10.1007\/s11192-020-03840-8"},{"key":"16389_CR38","doi-asserted-by":"crossref","unstructured":"Baziyad, H., Shirazi, S., Hosseini, S., Norouzi, R.: Mapping the intellectual structure of epidemiology with use of co-word analysis. Journal of Biostatistics and Epidemiology (2019)","DOI":"10.18502\/jbe.v5i3.3618"},{"key":"16389_CR39","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1007\/s11192-015-1740-1","volume":"105","author":"B-N Yan","year":"2015","unstructured":"Yan B-N, Lee T-S, Lee T-P (2015) Mapping the intellectual structure of the internet of things (iot) field (2000\u20132014): A co-word analysis. Scientometrics 105:1285\u20131300","journal-title":"Scientometrics"},{"key":"16389_CR40","doi-asserted-by":"crossref","unstructured":"Norouzi, R., Baziyad, H., Aknondzadeh Noghabi, E., Albadvi, A.: Developing tourism users\u2019 profiles with data-driven explicit information. Mathematical Problems in Engineering 2022 (2022)","DOI":"10.1155\/2022\/6536908"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16389-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16389-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16389-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,22]],"date-time":"2024-02-22T13:18:46Z","timestamp":1708607926000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16389-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,7]]},"references-count":40,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2024,3]]}},"alternative-id":["16389"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16389-4","relation":{},"ISSN":["1573-7721"],"issn-type":[{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2023,8,7]]},"assertion":[{"value":"22 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 July 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 July 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 August 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}