{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T18:25:38Z","timestamp":1747247138288},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["No. 2018YFB1700902"],"award-info":[{"award-number":["No. 2018YFB1700902"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Real-Time Image Proc"],"published-print":{"date-parts":[[2023,2]]},"DOI":"10.1007\/s11554-023-01267-x","type":"journal-article","created":{"date-parts":[[2023,2,9]],"date-time":"2023-02-09T21:53:56Z","timestamp":1675979636000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A real-time and effective text detection method for multi-scale and fuzzy text"],"prefix":"10.1007","volume":"20","author":[{"given":"Guoxiang","family":"Tong","sequence":"first","affiliation":[]},{"given":"Ming","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Song","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"1267_CR1","doi-asserted-by":"publisher","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, New Orleans, vol. 32, No. 1, pp. 6773\u20136780 (2018). https:\/\/doi.org\/10.1609\/aaai.v32i1.12269","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"1267_CR2","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1016\/j.neucom.2020.10.099","volume":"453","author":"G Deng","year":"2021","unstructured":"Deng, G., Ming, Y., Xue, J.H.: Rfrn: a recurrent feature refinement network for accurate and efficient scene text detection. Neurocomputing 453, 465\u2013481 (2021)","journal-title":"Neurocomputing"},{"key":"1267_CR3","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\u20132970. IEEE (2010)","DOI":"10.1109\/CVPR.2010.5540041"},{"key":"1267_CR4","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., Lin, T.Y., Le, Q.V.: Nas-fpn: learning scalable feature pyramid architecture for object detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, pp. 7029\u20137038 (2019)","DOI":"10.1109\/CVPR.2019.00720"},{"key":"1267_CR5","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 (CVPR), Las Vegas, NV, USA, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"1267_CR6","doi-asserted-by":"crossref","unstructured":"He, W., Zhang, X.Y., Yin, F., Liu, C.L.: Deep direct regression for multi-oriented scene text detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 745\u2013753 (2017)","DOI":"10.1109\/ICCV.2017.87"},{"key":"1267_CR7","doi-asserted-by":"crossref","unstructured":"Hu, H., Zhang, C., Luo, Y., Wang, Y., Han, J., Ding, E.: Wordsup: exploiting word annotations for character based text detection. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy, pp. 4950\u20134959 (2017)","DOI":"10.1109\/ICCV.2017.529"},{"key":"1267_CR8","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 2011\u20132023 (2020)","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"1267_CR9","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et al.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28, 2017\u20132025 (2015)"},{"issue":"5","key":"1267_CR10","doi-asserted-by":"publisher","first-page":"1039","DOI":"10.1007\/s10796-016-9699-x","volume":"19","author":"S Joan","year":"2017","unstructured":"Joan, S., Valli, S.: An enhanced text detection technique for the visually impaired to read text. Inf. Syst. Front. 19(5), 1039\u20131056 (2017)","journal-title":"Inf. Syst. Front."},{"key":"1267_CR11","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\u00a0al.: Icdar 2015 competition on robust reading. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1156\u20131160. IEEE (2015)","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"1267_CR12","doi-asserted-by":"crossref","unstructured":"Karatzas, D., Shafait, F., Uchida, S., Iwamura, M., i\u00a0Bigorda, L.G., Mestre, S.R., Mas, J., Mota, D.F., Almazan, J.A., De\u00a0Las\u00a0Heras, L.P.: Icdar 2013 robust reading competition. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 1484\u20131493. IEEE (2013)","DOI":"10.1109\/ICDAR.2013.221"},{"key":"1267_CR13","doi-asserted-by":"crossref","unstructured":"Kim, Y., Kang, B.N., Kim, D.: San: learning relationship between convolutional features for multi-scale object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, pp. 316\u2013331 (2018)","DOI":"10.1007\/978-3-030-01228-1_20"},{"key":"1267_CR14","doi-asserted-by":"crossref","unstructured":"Kong, T., Sun, F., Tan, C., Liu, H., Huang, W.: Deep feature pyramid reconfiguration for object detection. In: Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany, pp. 169\u2013185 (2018)","DOI":"10.1007\/978-3-030-01228-1_11"},{"key":"1267_CR15","doi-asserted-by":"crossref","unstructured":"Li, D., Hu, J., Wang, C., Li, X., She, Q., Zhu, L., Zhang, T., Chen, Q.: Involution: inverting the inherence of convolution for visual recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Kuala Lumpur, Malaysia, pp. 12321\u201312330 (2021)","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"1267_CR16","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1016\/j.neucom.2021.04.035","volume":"449","author":"X Li","year":"2021","unstructured":"Li, X., Liu, J., Zhang, G., Huang, Y., Zheng, Y., Zhang, S.: Learning to predict more accurate text instances for scene text detection. Neurocomputing 449, 455\u2013463 (2021)","journal-title":"Neurocomputing"},{"key":"1267_CR17","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, pp. 510\u2013519 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"1267_CR18","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: Thirty-first AAAI Conference on Artificial Intelligence, San Francisco, USA, pp. 4161\u20134167 (2017)","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"1267_CR19","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Doll\u00e1r, P., Girshick, R., He, K., Hariharan, B., Belongie, S.: Feature pyramid networks for object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, pp. 2117\u20132125 (2017)","DOI":"10.1109\/CVPR.2017.106"},{"key":"1267_CR20","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"},{"key":"1267_CR21","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/j.neucom.2020.05.059","volume":"407","author":"J Liu","year":"2020","unstructured":"Liu, J., Zhong, Q., Yuan, Y., Su, H., Du, B.: Semitext: scene text detection with semi-supervised learning. Neurocomputing 407, 343\u2013353 (2020)","journal-title":"Neurocomputing"},{"key":"1267_CR22","doi-asserted-by":"crossref","unstructured":"Liu, S., Qi, L., Qin, H., Shi, J., Jia, J.: Path aggregation network for instance segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, pp. 8759\u20138768 (2018)","DOI":"10.1109\/CVPR.2018.00913"},{"issue":"6","key":"1267_CR23","doi-asserted-by":"publisher","first-page":"1965","DOI":"10.1007\/s11554-021-01074-2","volume":"18","author":"J Ma","year":"2021","unstructured":"Ma, J., Wan, H., Wang, J., Xia, H., Bai, C.: An improved one-stage pedestrian detection method based on multi-scale attention feature extraction. J. Real Time Image Process. 18(6), 1965\u20131978 (2021)","journal-title":"J. Real Time Image Process."},{"issue":"10","key":"1267_CR24","doi-asserted-by":"publisher","first-page":"761","DOI":"10.1016\/j.imavis.2004.02.006","volume":"22","author":"J Matas","year":"2004","unstructured":"Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide-baseline stereo from maximally stable extremal regions. Image Vis. Comput. 22(10), 761\u2013767 (2004)","journal-title":"Image Vis. Comput."},{"issue":"9","key":"1267_CR25","doi-asserted-by":"publisher","first-page":"1872","DOI":"10.1109\/TPAMI.2015.2496234","volume":"38","author":"L Neumann","year":"2015","unstructured":"Neumann, L., Matas, J.: Real-time lexicon-free scene text localization and recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(9), 1872\u20131885 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"1","key":"1267_CR26","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1007\/s11554-020-00942-7","volume":"18","author":"C Nguyen Dinh","year":"2021","unstructured":"Nguyen Dinh, C., Delalandre, M., Conte, D., et al.: Fast rt-log operator for scene text detection. J. Real Time Image Process. 18(1), 19\u201336 (2021)","journal-title":"J. Real Time Image Process."},{"key":"1267_CR27","doi-asserted-by":"crossref","unstructured":"Qiao, S., Chen, L.C., Yuille, A.: Detectors: detecting objects with recursive feature pyramid and switchable atrous convolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Kuala Lumpur, Malaysia, pp. 10213\u201310224 (2021)","DOI":"10.1109\/CVPR46437.2021.01008"},{"key":"1267_CR28","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. Adv. Neural Inf. Process. Syst. 32, 68\u201380 (2019)"},{"issue":"6","key":"1267_CR29","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1007\/s11554-021-01102-1","volume":"18","author":"K Ren","year":"2021","unstructured":"Ren, K., Huang, L., Fan, C., Han, H., Deng, H.: Real-time traffic sign detection network using ds-detnet and lite fusion fpn. J. Real Time Image Process. 18(6), 2181\u20132191 (2021)","journal-title":"J. Real Time Image Process."},{"key":"1267_CR30","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 (CVPR), Hawaii, USA, pp. 2550\u20132558 (2017)","DOI":"10.1109\/CVPR.2017.371"},{"key":"1267_CR31","doi-asserted-by":"crossref","unstructured":"Singh, J.P., Kumar, A., Rana, N.P., Dwivedi, Y.K.: Attention-based lstm network for rumor veracity estimation of tweets. Inf. Syst. Front. 24, 459\u2013474 (2020)","DOI":"10.1007\/s10796-020-10040-5"},{"key":"1267_CR32","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30, 6000\u20136010 (2017)"},{"key":"1267_CR33","doi-asserted-by":"crossref","unstructured":"Wang, F., Jiang, M., Qian, C., Yang, S., Li, C., Zhang, H., Wang, X., Tang, X.: Residual attention network for image classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, pp. 3156\u20133164 (2017)","DOI":"10.1109\/CVPR.2017.683"},{"key":"1267_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., Xie, E., Li, X., Hou, W., Lu, T., Yu, G., Shao, S.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, California, USA, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"1267_CR35","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1267_CR36","doi-asserted-by":"crossref","unstructured":"Woo, S., Hwang, S., Kweon, I.S.: Stairnet: Top-down semantic aggregation for accurate one shot detection. In: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1093\u20131102. IEEE (2018)","DOI":"10.1109\/WACV.2018.00125"},{"key":"1267_CR37","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"1267_CR38","doi-asserted-by":"crossref","unstructured":"Xing, L., Tian, Z., Huang, W., Scott, M.R.: Convolutional character networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9126\u20139136 (2019)","DOI":"10.1109\/ICCV.2019.00922"},{"issue":"4","key":"1267_CR39","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1007\/s11554-021-01121-y","volume":"18","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Song, H., Sun, S., Zhang, W., Chen, Y., Rakal, L., Fang, Y.: A fast and effective video vehicle detection method leveraging feature fusion and proposal temporal link. J. Real Time Image Process. 18(4), 1261\u20131274 (2021)","journal-title":"J. Real Time Image Process."},{"key":"1267_CR40","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\u20131090. IEEE (2012)"},{"key":"1267_CR41","unstructured":"Yao, C., Bai, X., Sang, N., Zhou, X., Zhou, S., Cao, Z.: Scene text detection via holistic, multi-channel prediction. arXiv preprint arXiv:1606.09002 (2016)"},{"key":"1267_CR42","doi-asserted-by":"crossref","unstructured":"Ye, J., Chen, Z., Liu, J., Du, B.: Textfusenet: scene text detection with richer fused features. In: IJCAI, vol.\u00a020, pp. 516\u2013522 (2020)","DOI":"10.24963\/ijcai.2020\/72"},{"key":"1267_CR43","doi-asserted-by":"crossref","unstructured":"Yu, H., Wang, X., Shao, Y., Qin, F., Chen, B., Gong, S.: Research on license plate location and recognition in complex environment. J. Real Time Image Process. 19, 823\u2013837 (2022)","DOI":"10.1007\/s11554-022-01225-z"},{"key":"1267_CR44","doi-asserted-by":"crossref","unstructured":"Yu, J., Jiang, Y., Wang, Z., Cao, Z., Huang, T.: Unitbox: an advanced object detection network. In: Proceedings of the 24th ACM International Conference on Multimedia, pp. 516\u2013520 (2016)","DOI":"10.1145\/2964284.2967274"},{"key":"1267_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Zhang, C., Shen, W., Yao, C., Liu, W., Bai, X.: Multi-oriented text detection with fully convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, USA, pp. 4159\u20134167 (2016)","DOI":"10.1109\/CVPR.2016.451"},{"key":"1267_CR46","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Peng, Q., Zhuang, Y.: Lane line detection based on the codec structure of the attention mechanism. J. Real Time Image Process. 19, 715\u2013726 (2022)","DOI":"10.1007\/s11554-022-01217-z"},{"key":"1267_CR47","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Wang, P., Ren, D., Liu, W., Ye, R., Hu, Q., Zuo, W.: Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Trans. Cybern. 52(8), 8574\u20138586 (2021)","DOI":"10.1109\/TCYB.2021.3095305"},{"key":"1267_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, P., Ni, B., Geng, C., Hu, J., Xu, Y.: Scale-transferrable object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Salt Lake City, USA, pp. 528\u2013537 (2018)","DOI":"10.1109\/CVPR.2018.00062"},{"key":"1267_CR49","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Hawaii, USA, pp. 5551\u20135560 (2017)","DOI":"10.1109\/CVPR.2017.283"},{"key":"1267_CR50","unstructured":"Zhu, M., Han, K., Yu, C., Wang, Y.: Dynamic feature pyramid networks for object detection. arXiv preprint arXiv:2012.00779 (2020)"},{"key":"1267_CR51","doi-asserted-by":"crossref","unstructured":"Zhu, X., Cheng, D., Zhang, Z., Lin, S., Dai, J.: An empirical study of spatial attention mechanisms in deep networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), Seoul, Korea (South), pp. 6688\u20136697 (2019)","DOI":"10.1109\/ICCV.2019.00679"}],"container-title":["Journal of Real-Time Image Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01267-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11554-023-01267-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11554-023-01267-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,27]],"date-time":"2023-02-27T18:33:53Z","timestamp":1677522833000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11554-023-01267-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2]]},"references-count":51,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2023,2]]}},"alternative-id":["1267"],"URL":"https:\/\/doi.org\/10.1007\/s11554-023-01267-x","relation":{},"ISSN":["1861-8200","1861-8219"],"issn-type":[{"value":"1861-8200","type":"print"},{"value":"1861-8219","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2]]},"assertion":[{"value":"21 July 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 December 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All the authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"13"}}