{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T19:26:25Z","timestamp":1762543585871,"version":"3.37.3"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T00:00:00Z","timestamp":1646611200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100013076","name":"National Major Science and Technology Projects of China","doi-asserted-by":"publisher","award":["2017ZX01030102"],"award-info":[{"award-number":["2017ZX01030102"]}],"id":[{"id":"10.13039\/501100013076","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2021YFB2206200"],"award-info":[{"award-number":["2021YFB2206200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1007\/s10489-021-03065-z","type":"journal-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T20:54:42Z","timestamp":1646686482000},"page":"14374-14386","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Arbitrary-shaped scene text detection by predicting distance map"],"prefix":"10.1007","volume":"52","author":[{"given":"Xinyu","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2456-6845","authenticated-orcid":false,"given":"Yaohua","family":"Yi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jibing","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaili","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,7]]},"reference":[{"key":"3065_CR1","doi-asserted-by":"crossref","unstructured":"Liao M, Shi B, Bai X, Wang X, Liu W (2017) Textboxes: A fast text detector with a single deep neural network. In: Singh SP, Markovitch S (eds) Proceedings of the Thirty-First AAAI conference on artificial intelligence, pp 4161\u20134167","DOI":"10.1609\/aaai.v31i1.11196"},{"key":"3065_CR2","doi-asserted-by":"crossref","unstructured":"Zhou X, Yao C, Wen H, Wang Y, Zhou S, He W, Liang J (2017) EAST: an efficient and accurate scene text detector. In: 2017 IEEE Conference on computer vision and pattern recognition(CVPR), pp 2642\u20132651","DOI":"10.1109\/CVPR.2017.283"},{"issue":"8","key":"3065_CR3","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 Trans Image Process 27(8):3676\u20133690","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"3065_CR4","doi-asserted-by":"publisher","first-page":"3623","DOI":"10.1007\/s10489-020-01742-z","volume":"50","author":"L Lu","year":"2020","unstructured":"Lu L, Wu D, Wu T, Huang F, Yi Y (2020) Anchor-free multi-orientation text detection in natural scene images. Appl Intell 50(11):3623\u20133637","journal-title":"Appl Intell"},{"key":"3065_CR5","doi-asserted-by":"crossref","unstructured":"Long S, Ruan J, Zhang W, He X, Wu W, Yao C (2018) Textsnake: A flexible representation for detecting text of arbitrary shapes. In: Ferrari V, Hebert M, Sminchisescu C, Weiss Y (eds) Computer vision - ECCV 2018 - 15th european conference, lecture notes in computer science, vol 11206, pp 19\u201335","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"3065_CR6","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Li X, Hou W, Lu T, Yu G, Shao S (2019) Shape robust text detection with progressive scale expansion network. In: IEEE Conference on computer vision and pattern recognition(CVPR), pp 9336\u20139345","DOI":"10.1109\/CVPR.2019.00956"},{"key":"3065_CR7","doi-asserted-by":"crossref","unstructured":"Tian Z, Shu M, Lyu P, Li R, Zhou C, Shen X, Jia J (2019) Learning shape-aware embedding for scene text detection. In: IEEE Conference on computer vision and pattern recognition(CVPR), pp 4234\u20134243","DOI":"10.1109\/CVPR.2019.00436"},{"key":"3065_CR8","doi-asserted-by":"crossref","unstructured":"Wang W, Xie E, Song X, Zang Y, Wang W, Lu T, Yu G, Shen C (2019) Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: 2019 IEEE\/CVF International conference on computer vision(ICCV), pp 8439\u20138448","DOI":"10.1109\/ICCV.2019.00853"},{"key":"3065_CR9","doi-asserted-by":"crossref","unstructured":"Karatzas D, Gomez-Bigorda L, Nicolaou A, Ghosh SK, Bagdanov AD, Iwamura M, Matas J, Neumann L, Chandrasekhar VR, Lu S, Shafait F, Uchida S, Valveny E (2015) ICDAR 2015 competition on robust reading. In: 13th International conference on document analysis and recognition(ICDAR), pp 1156\u20131160","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"3065_CR10","unstructured":"Liu Y, Jin L, Zhang S, Zhang S (2017) Detecting curve text in the wild: New dataset and new solution. arxiv:1712.02170"},{"key":"3065_CR11","doi-asserted-by":"crossref","unstructured":"Chng CK, Chan CS (2017) Total-text: A comprehensive dataset for scene text detection and recognition. In: 14th IAPR International conference on document analysis and recognition(ICDAR), pp 935\u2013942","DOI":"10.1109\/ICDAR.2017.157"},{"key":"3065_CR12","doi-asserted-by":"crossref","unstructured":"Zhu Y, Du J (2018) Sliding line point regression for shape robust scene text detection. In: 24th International conference on pattern recognition(ICPR), pp 3735\u20133740","DOI":"10.1109\/ICPR.2018.8545067"},{"key":"3065_CR13","doi-asserted-by":"crossref","unstructured":"Wang X, Jiang Y, Luo Z, Liu C, Choi H, Kim S (2019) Arbitrary shape scene text detection with adaptive text region representation. In: IEEE Conference on computer vision and pattern recognition(CVPR), pp 6449\u20136458","DOI":"10.1109\/CVPR.2019.00661"},{"issue":"8","key":"3065_CR14","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"3065_CR15","doi-asserted-by":"crossref","unstructured":"Wang H, Lu P, Zhang H, Yang M, Bai X, Xu Y, He M, Wang Y, Liu W (2020) All you need is boundary: Toward arbitrary-shaped text spotting. In: The thirty-fourth AAAI conference on artificial intelligence(AAAI), pp 12160\u201312167","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"3065_CR16","doi-asserted-by":"crossref","unstructured":"Liu Y, Chen H, Shen C, He T, Jin L, Wang L (2020) Abcnet: Real-time scene text spotting with adaptive bezier-curve network. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition(CVPR), pp 9806\u20139815","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"3065_CR17","doi-asserted-by":"crossref","unstructured":"Tang J, Yang Z, Wang Y, Zheng Q, Xu Y, Bai X (2019) Seglink++: Detecting dense and arbitrary-shaped scene text by instance-aware component grouping. Pattern Recognit 96:106954","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"3065_CR18","doi-asserted-by":"crossref","unstructured":"Zhang S, Zhu X, Hou J, Liu C, Yang C, Wang H, Yin X (2020) Deep relational reasoning graph network for arbitrary shape text detection. In: 2020 IEEE\/CVF Conference on computer vision and pattern recognition(CVPR), pp 9696\u20139705","DOI":"10.1109\/CVPR42600.2020.00972"},{"key":"3065_CR19","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: 5th International conference on learning representations(ICLR)"},{"key":"3065_CR20","doi-asserted-by":"crossref","unstructured":"Feng W, He W, Yin F, Zhang X, Liu C (2019) Textdragon: An end-to-end framework for arbitrary shaped text spotting. In: 2019 IEEE\/CVF International conference on computer vision(ICCV), pp 9075\u20139084","DOI":"10.1109\/ICCV.2019.00917"},{"issue":"4","key":"3065_CR21","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1109\/TPAMI.2016.2572683","volume":"39","author":"E Shelhamer","year":"2017","unstructured":"Shelhamer E, Long J, Darrell T (2017) Fully convolutional networks for semantic segmentation. IEEE Trans Pattern Anal Mach Intell 39(4):640\u2013651","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3065_CR22","doi-asserted-by":"crossref","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-net: Convolutional networks for biomedical image segmentation. In: Navab N, Hornegger J, III WMW, Frangi AF (eds) Medical Image computing and computer-assisted intervention(MICCAI), Lecture Notes in Computer Science, vol 9351, pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"3065_CR23","unstructured":"Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: Bengio Y, LeCun Y (eds) 3rd International Conference on Learning Representations(ICLR)"},{"key":"3065_CR24","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: Bach FR, Blei DM (eds) Proceedings of the 32nd international conference on machine learning(ICML), JMLR workshop and conference proceedings, vol 37, pp 448\u2013456"},{"issue":"1","key":"3065_CR25","doi-asserted-by":"publisher","first-page":"415","DOI":"10.4086\/toc.2012.v008a019","volume":"8","author":"PF Felzenszwalb","year":"2012","unstructured":"Felzenszwalb PF, Huttenlocher DP (2012) Distance transforms of sampled functions. Theory Comput 8(1):415\u2013428","journal-title":"Theory Comput"},{"issue":"4","key":"3065_CR26","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1145\/321356.321357","volume":"13","author":"A Rosenfeld","year":"1966","unstructured":"Rosenfeld A, Pfaltz JL (1966) Sequential operations in digital picture processing. J ACM 13(4):471\u2013494","journal-title":"J ACM"},{"key":"3065_CR27","doi-asserted-by":"crossref","unstructured":"Heckbert PS (1990) A seed fill algorithm. San Diego, pp 275\u2013277","DOI":"10.1016\/B978-0-08-050753-8.50058-9"},{"key":"3065_CR28","doi-asserted-by":"crossref","unstructured":"Sudre CH, Li W, Vercauteren T, Ourselin S, Cardoso MJ (2017) Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations. In: Cardoso MJ, Arbel T, Carneiro G, Syeda-Mahmood TF, Tavares JMRS, Moradi M, Bradley AP, Greenspan H, Papa JP, Madabhushi A, Nascimento JC, Cardoso JS, Belagiannis V, Lu Z (eds) Deep learning in medical image analysis and multimodal learning for clinical decision support - third international workshop(DLMIA), lecture notes in computer science, vol 10553, pp 240\u2013248","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"3065_CR29","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A, Girshick RB (2016) Training region-based object detectors with online hard example mining. In: 2016 IEEE Conference on computer vision and pattern recognition(CVPR), pp 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"3065_CR30","doi-asserted-by":"crossref","unstructured":"Nayef N, Yin F, Bizid I, Choi H, Feng Y, Karatzas D, Luo Z, Pal U, Rigaud C, Chazalon J, Khlif W, Luqman MM, Burie J, Liu C, Ogier J (2017) ICDAR2017 robust reading challenge on multi-lingual scene text detection and script identification - RRC-MLT. In: 14th IAPR International Conference on document analysis and recognition(ICDAR), pp 1454\u20131459","DOI":"10.1109\/ICDAR.2017.237"},{"key":"3065_CR31","unstructured":"Liu L, Jiang H, He P, Chen W, Liu X, Gao J, Han J (2020) On the variance of the adaptive learning rate and beyond. In: 8th International conference on learning representations(ICLR)"},{"key":"3065_CR32","unstructured":"Kingma DP, Ba J (2015) Adam: A method for stochastic optimization. In: Bengio Y, LeCun Y (eds) 3rd International conference on learning representations(ICLR)"},{"key":"3065_CR33","doi-asserted-by":"crossref","unstructured":"Gupta A, Vedaldi A, Zisserman A (2016) Synthetic data for text localisation in natural images. In: 2016 IEEE Conference on computer vision and pattern recognition(CVPR), pp 2315\u20132324","DOI":"10.1109\/CVPR.2016.254"},{"key":"3065_CR34","unstructured":"Zhang MR, Lucas J, Ba J, Hinton GE (2019) Lookahead optimizer: k steps forward, 1 step back. In: Wallach HM, Larochelle H, Beygelzimer A, d\u2019Alch\u00e9-Buc F, Fox EB, Garnett R (eds) Advances in neural information processing systems 32: annual conference on neural information processing systems, pp 9593\u20139604"},{"key":"3065_CR35","doi-asserted-by":"crossref","unstructured":"Lyu P, Yao C, Wu W, Yan S, Bai X (2018) Multi-oriented scene text detection via corner localization and region segmentation. In: 2018 IEEE Conference on computer vision and pattern recognition(CVPR), pp 7553\u20137563","DOI":"10.1109\/CVPR.2018.00788"},{"key":"3065_CR36","doi-asserted-by":"crossref","unstructured":"Liu X, Liang D, Yan S, Chen D, Qiao Y, Yan J (2018) FOTS: Fast oriented text spotting with a unified network. In: 2018 IEEE Conference on computer vision and pattern recognition(CVPR), pp 5676\u20135685","DOI":"10.1109\/CVPR.2018.00595"},{"key":"3065_CR37","doi-asserted-by":"crossref","unstructured":"Zhang C, Liang B, Huang Z, En M, Han J, Ding E, Ding X (2019) Look more than once: An accurate detector for text of arbitrary shapes. In: IEEE Conference on computer vision and pattern recognition(CVPR), pp 10552\u201310561","DOI":"10.1109\/CVPR.2019.01080"},{"key":"3065_CR38","doi-asserted-by":"crossref","unstructured":"Tian Z, Huang W, He T, He P, Qiao Y (2016) Detecting text in natural image with connectionist text proposal network. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer Vision - ECCV 2016 - 14th European conference, lecture notes in computer science, vol 9912, pp 56\u201372","DOI":"10.1007\/978-3-319-46484-8_4"},{"issue":"11","key":"3065_CR39","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 Trans Multim 20(11):3111\u20133122","journal-title":"IEEE Trans Multim"},{"key":"3065_CR40","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. arxiv:1706.09579","DOI":"10.1109\/ICPR.2018.8545598"},{"key":"3065_CR41","doi-asserted-by":"crossref","unstructured":"Shi B, Bai X, Belongie SJ (2017) Detecting oriented text in natural images by linking segments. In: 2017 IEEE Conference on computer vision and pattern recognition(CVPR), pp 3482\u20133490","DOI":"10.1109\/CVPR.2017.371"},{"key":"3065_CR42","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: IEEE International conference on computer vision(ICCV), pp 3066\u20133074","DOI":"10.1109\/ICCV.2017.331"},{"key":"3065_CR43","doi-asserted-by":"crossref","unstructured":"Hu H, Zhang C, Luo Y, Wang Y, Han J, Ding E (2017) Wordsup: Exploiting word annotations for character based text detection. In: IEEE International conference on computer vision(ICCV), pp 4950\u20134959","DOI":"10.1109\/ICCV.2017.529"},{"key":"3065_CR44","doi-asserted-by":"crossref","unstructured":"Liao M, Zhu Z, Shi B, Xia G, Bai X (2018) Rotation-sensitive regression for oriented scene text detection. In: 2018 IEEE Conference on computer vision and pattern recognition(CVPR), pp 5909\u20135918","DOI":"10.1109\/CVPR.2018.00619"},{"issue":"11","key":"3065_CR45","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. IEEE Trans Image Process 28(11):5566\u20135579","journal-title":"IEEE Trans Image Process"},{"key":"3065_CR46","doi-asserted-by":"crossref","unstructured":"Xue C, Lu S, Zhang W (2019) MSR: multi-scale shape regression for scene text detection. In: Kraus S (ed) Proceedings of the twenty-eighth international joint conference on artificial intelligence(IJCAI), pp 989\u2013995","DOI":"10.24963\/ijcai.2019\/139"},{"key":"3065_CR47","doi-asserted-by":"crossref","unstructured":"He T, Tian Z, Huang W, Shen C, Qiao Y, Sun C (2018) An end-to-end textspotter with explicit alignment and attention. In: 2018 IEEE Conference on computer vision and pattern recognition, CVPR 2018, pp 5020\u20135029","DOI":"10.1109\/CVPR.2018.00527"},{"key":"3065_CR48","doi-asserted-by":"crossref","unstructured":"Dai Y, Huang Z, Gao Y, Xu Y, Chen K, Guo J, Qiu W (2018) Fused text segmentation networks for multi-oriented scene text detection. In: 24th International conference on pattern recognition(ICPR), pp 3604\u20133609","DOI":"10.1109\/ICPR.2018.8546066"},{"key":"3065_CR49","doi-asserted-by":"crossref","unstructured":"Liu Z, Lin G, Yang S, Liu F, Lin W, Goh WL (2019) Towards robust curve text detection with conditional spatial expansion. In: IEEE Conference on computer vision and pattern recognition(CVPR), pp 7269\u20137278","DOI":"10.1109\/CVPR.2019.00744"},{"key":"3065_CR50","doi-asserted-by":"crossref","unstructured":"Zhu Y, Du J (2021) Textmountain: Accurate scene text detection via instance segmentation. Pattern Recognition 110:107336","DOI":"10.1016\/j.patcog.2020.107336"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-03065-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-021-03065-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-021-03065-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,1]],"date-time":"2022-10-01T09:36:58Z","timestamp":1664617018000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-021-03065-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,7]]},"references-count":50,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2022,9]]}},"alternative-id":["3065"],"URL":"https:\/\/doi.org\/10.1007\/s10489-021-03065-z","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2022,3,7]]},"assertion":[{"value":"30 November 2021","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 March 2022","order":2,"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 they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}}]}}