{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:11:36Z","timestamp":1758089496715,"version":"3.44.0"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032046239"},{"type":"electronic","value":"9783032046246"}],"license":[{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T00:00:00Z","timestamp":1758067200000},"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":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-04624-6_18","type":"book-chapter","created":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:34:31Z","timestamp":1758000871000},"page":"305-322","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Towards Understanding the\u00a0Logical Layout of\u00a0Scene Text in\u00a0Signboard Images"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7937-0516","authenticated-orcid":false,"given":"Giang Tran Thi","family":"Cam","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-4600-9715","authenticated-orcid":false,"given":"Cam-Nguyen","family":"Tran-Nhu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7895-8935","authenticated-orcid":false,"given":"Thuyen Tran","family":"Doan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6882-0070","authenticated-orcid":false,"given":"Thanh Duc","family":"Ngo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,17]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Barrow, J., Jain, R., Morariu, V., Manjunatha, V., Oard, D.W., Resnik, P.: A joint model for document segmentation and segment labeling. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 313\u2013322 (2020)","DOI":"10.18653\/v1\/2020.acl-main.29"},{"key":"18_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-4277-0","volume-title":"Document Layout Analysis","author":"S Bhowmik","year":"2023","unstructured":"Bhowmik, S.: Document Layout Analysis. Springer, Singapore (2023). https:\/\/doi.org\/10.1007\/978-981-99-4277-0"},{"issue":"6","key":"18_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355610","volume":"52","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surv. (CSUR) 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"18_CR4","unstructured":"Cai\u00a0Chen, H., Wu, L., Zhang, Y.: EDocNet: efficient datasheet layout analysis based on focus and global knowledge distillation. arXiv e-prints pp. arXiv\u20132502 (2025)"},{"key":"18_CR5","unstructured":"Cattoni, R., Coianiz, T., Messelodi, S., Modena, C.M.: Geometric layout analysis techniques for document image understanding: a review. ITC-irst Technical Report 9703(09) (1998)"},{"key":"18_CR6","unstructured":"Chen, Y., et al.: Graph-based document structure analysis. arXiv preprint arXiv:2502.02501 (2025)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Ch\u2019ng, C.K., Chan, C.S.: Total-text: a comprehensive dataset for scene text detection and recognition. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 935\u2013942. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.157"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 19462\u201319472 (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Do, T., Tran, T., Nguyen, T., Le, D.D., Ngo, T.D.: SignboardText: text detection and recognition in in-the-wild signboard images. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3395374"},{"key":"18_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patcog.2016.10.023","volume":"64","author":"S Eskenazi","year":"2017","unstructured":"Eskenazi, S., Gomez-Kr\u00e4mer, P., Ogier, J.M.: A comprehensive survey of mostly textual document segmentation algorithms since 2008. Pattern Recogn. 64, 1\u201314 (2017)","journal-title":"Pattern Recogn."},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Gomez, R., et al.: ICDAR2017 robust reading challenge on coco-text. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol.\u00a01, pp. 1435\u20131443. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.234"},{"issue":"1","key":"18_CR12","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/asi.4630370102","volume":"37","author":"A Griffiths","year":"1986","unstructured":"Griffiths, A., Luckhurst, H.C., Willett, P.: Using interdocument similarity information in document retrieval systems. J. Am. Soc. Inf. Sci. 37(1), 3\u201311 (1986)","journal-title":"J. Am. Soc. Inf. Sci."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Gupta, A., Vedaldi, A., Zisserman, A.: Synthetic data for text localisation in natural images. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2315\u20132324 (2016)","DOI":"10.1109\/CVPR.2016.254"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Haralick: Document image understanding: geometric and logical layout. In: 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 385\u2013390. IEEE (1994)","DOI":"10.1109\/CVPR.1994.323855"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: LayoutLMv3: pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 4083\u20134091 (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"18_CR16","unstructured":"Jaderberg, M., Simonyan, K., Vedaldi, A., Zisserman, A.: Synthetic data and artificial neural networks for natural scene text recognition. arXiv preprint arXiv:1406.2227 (2014)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Jaume, G., Ekenel, H.K., Thiran, J.P.: FUNSD: a dataset for form understanding in noisy scanned documents. In: 2019 International Conference on Document Analysis and Recognition Workshops (ICDARW), vol.\u00a02, pp.\u00a01\u20136. IEEE (2019)","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Karatzas, D., 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":"18_CR19","doi-asserted-by":"crossref","unstructured":"Kotenko, I., Chechulin, A., Komashinsky, D.: Evaluation of text classification techniques for inappropriate web content blocking. In: 2015 IEEE 8th International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications (IDAACS), vol.\u00a01, pp. 412\u2013417. IEEE (2015)","DOI":"10.1109\/IDAACS.2015.7340769"},{"key":"18_CR20","unstructured":"Li, M., Cui, L., Huang, S., Wei, F., Zhou, M., Li, Z.: TableBank: table benchmark for image-based table detection and recognition. In: Proceedings of the Twelfth Language Resources and Evaluation Conference, pp. 1918\u20131925 (2020)"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: DocBank: a benchmark dataset for document layout analysis. arXiv preprint arXiv:2006.01038 (2020)","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"18_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11432-019-2737-0","volume":"63","author":"M Liao","year":"2020","unstructured":"Liao, M., Song, B., Long, S., He, M., Yao, C., Bai, X.: Synthtext3d: synthesizing scene text images from 3d virtual worlds. SCIENCE CHINA Inf. Sci. 63, 1\u201314 (2020)","journal-title":"SCIENCE CHINA Inf. Sci."},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Liao, M., Wan, Z., Yao, C., Chen, K., Bai, X.: Real-time scene text detection with differentiable binarization. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 11474\u201311481 (2020)","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Liao, M., Zou, Z., Wan, Z., Yao, C., Bai, X.: Real-time scene text detection with differentiable binarization and adaptive scale fusion. IEEE Trans. Pattern Anal. Mach. Intell., 919\u2013931 (2022)","DOI":"10.1109\/TPAMI.2022.3155612"},{"issue":"1","key":"18_CR25","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1007\/s11263-020-01369-0","volume":"129","author":"S Long","year":"2021","unstructured":"Long, S., He, X., Yao, C.: Scene text detection and recognition: the deep learning era. Int. J. Comput. Vision 129(1), 161\u2013184 (2021)","journal-title":"Int. J. Comput. Vision"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Long, S., Qin, S., Panteleev, D., Bissacco, A., Fujii, Y., Raptis, M.: Towards end-to-end unified scene text detection and layout analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1049\u20131059 (2022)","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"18_CR27","first-page":"197","volume":"5010","author":"S Mao","year":"2003","unstructured":"Mao, S., Rosenfeld, A., Kanungo, T.: Document structure analysis algorithms: a literature survey. Doc. Recognit. Retrieval X 5010, 197\u2013207 (2003)","journal-title":"Doc. Recognit. Retrieval X"},{"key":"18_CR28","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1007\/978-1-84628-726-8_2","volume-title":"Digital Document Processing: Major Directions and Recent Advances","author":"AM Namboodiri","year":"2007","unstructured":"Namboodiri, A.M., Jain, A.K.: Document structure and layout analysis. In: Chaudhuri, B.B. (ed.) Digital Document Processing: Major Directions and Recent Advances, pp. 29\u201348. Springer, London (2007). https:\/\/doi.org\/10.1007\/978-1-84628-726-8_2"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen, N., et al.: Dictionary-guided scene text recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7383\u20137392 (2021)","DOI":"10.1109\/CVPR46437.2021.00730"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Oliveira, S.A., Seguin, B., Kaplan, F.: dhSegment: a generic deep-learning approach for document segmentation. In: 2018 16th International Conference on Frontiers in Handwriting Recognition (ICFHR), pp. 7\u201312. IEEE (2018)","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.: DocLayNet: a large human-annotated dataset for document-layout segmentation. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, pp. 3743\u20133751 (2022)","DOI":"10.1145\/3534678.3539043"},{"issue":"3","key":"18_CR32","first-page":"305","volume":"52","author":"F Smith","year":"1975","unstructured":"Smith, F.: The role of prediction in reading. Elem. Engl. 52(3), 305\u2013311 (1975)","journal-title":"Elem. Engl."},{"key":"18_CR33","unstructured":"Veit, A., Matera, T., Neumann, L., Matas, J., Belongie, S.: COCO-Text: dataset and benchmark for text detection and recognition in natural images. arXiv preprint arXiv:1601.07140 (2016)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Shape robust text detection with progressive scale expansion network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9336\u20139345 (2019)","DOI":"10.1109\/CVPR.2019.00956"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Wang, W., et al.: Efficient and accurate arbitrary-shaped text detection with pixel aggregation network. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8440\u20138449 (2019)","DOI":"10.1109\/ICCV.2019.00853"},{"issue":"6","key":"18_CR36","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1016\/j.engappai.2010.03.002","volume":"23","author":"K Zagoris","year":"2010","unstructured":"Zagoris, K., Ergina, K., Papamarkos, N.: A document image retrieval system. Eng. Appl. Artif. Intell. 23(6), 872\u2013879 (2010)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: Reading order matters: information extraction from visually-rich documents by token path prediction. arXiv preprint arXiv:2310.11016 (2023)","DOI":"10.18653\/v1\/2023.emnlp-main.846"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, R., et\u00a0al.: ICDAR 2019 robust reading challenge on reading Chinese text on signboard. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1577\u20131581. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"18_CR39","unstructured":"Zhao, Z., Kang, H., Wang, B., He, C.: DocLayout-YOLO: enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception. arXiv preprint arXiv:2410.12628 (2024)"},{"key":"18_CR40","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Yepes, A.J.: PubLayNet: largest dataset ever for document layout analysis. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 1015\u20131022. IEEE (2019)","DOI":"10.1109\/ICDAR.2019.00166"}],"container-title":["Lecture Notes in Computer Science","Document Analysis and Recognition \u2013 ICDAR 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04624-6_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:34:43Z","timestamp":1758000883000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04624-6_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,17]]},"ISBN":["9783032046239","9783032046246"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04624-6_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,9,17]]},"assertion":[{"value":"17 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICDAR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Document Analysis and Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wuhan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icdar2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/iapr.org\/icdar2025","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}