{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:18:34Z","timestamp":1740107914447,"version":"3.37.3"},"reference-count":97,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T00:00:00Z","timestamp":1679443200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100000104","name":"NASA","doi-asserted-by":"crossref","award":["20-ADAP20-0225"],"award-info":[{"award-number":["20-ADAP20-0225"]}],"id":[{"id":"10.13039\/100000104","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Digit Libr"],"published-print":{"date-parts":[[2024,9]]},"DOI":"10.1007\/s00799-023-00350-9","type":"journal-article","created":{"date-parts":[[2023,3,27]],"date-time":"2023-03-27T03:35:22Z","timestamp":1679888122000},"page":"471-491","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["The digitization of historical astrophysical literature with highly localized figures and figure captions"],"prefix":"10.1007","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9397-6189","authenticated-orcid":false,"given":"Jill P.","family":"Naiman","sequence":"first","affiliation":[]},{"given":"Peter K. G.","family":"Williams","sequence":"additional","affiliation":[]},{"given":"Alyssa","family":"Goodman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,22]]},"reference":[{"issue":"1","key":"350_CR1","doi-asserted-by":"publisher","first-page":"583","DOI":"10.1002\/pra2.2017.14505401079","volume":"54","author":"HM Sandy","year":"2017","unstructured":"Sandy, H.M., Mitchell, E., Corrado, E.M., Budd, J., West, J.D., Bossaller, J., VanScoy, A.: Making a case for open research: implications for reproducibility and transparency. Proc. Assoc. Inf. Sci. Technol. 54(1), 583\u2013586 (2017). https:\/\/doi.org\/10.1002\/pra2.2017.14505401079","journal-title":"Proc. Assoc. Inf. Sci. Technol."},{"key":"350_CR2","doi-asserted-by":"crossref","unstructured":"Sohmen, L., Charbonnier, J., Bl\u00fcmel, I., Wartena, C., Heller, L.: Figures in scientific open access publications. In: International Conference on Theory and Practice of Digital Libraries, pp. 220\u2013226. Springer (2018)","DOI":"10.1007\/978-3-030-00066-0_19"},{"issue":"6","key":"350_CR3","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1002\/asi.23721","volume":"68","author":"MS Mayernik","year":"2017","unstructured":"Mayernik, M.S., Hart, D.L., Maull, K.E., Weber, N.M.: Assessing and tracing the outcomes and impact of research infrastructures. J. Assoc. Inf. Sci. Technol. 68(6), 1341\u20131359 (2017). https:\/\/doi.org\/10.1002\/asi.23721","journal-title":"J. Assoc. Inf. Sci. Technol."},{"key":"350_CR4","doi-asserted-by":"publisher","unstructured":"Gao, L., Yi, X., Jiang, Z., Hao, L., Tang, Z.: Icdar2017 competition on page object detection. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1417\u20131422 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.231","DOI":"10.1109\/ICDAR.2017.231"},{"key":"350_CR5","doi-asserted-by":"crossref","unstructured":"Zhong, X., Tang, J., Jimeno Yepes, A.: PubLayNet: largest dataset ever for document layout analysis. arXiv e-prints (2019) arXiv:1908.07836 [cs.CL]","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"350_CR6","doi-asserted-by":"publisher","DOI":"10.3390\/app11125344","author":"J Bhatt","year":"2021","unstructured":"Bhatt, J., Hashmi, K.A., Afzal, M.Z., Stricker, D.: A survey of graphical page object detection with deep neural networks. Appl. Sci. (2021). https:\/\/doi.org\/10.3390\/app11125344","journal-title":"Appl. Sci."},{"key":"350_CR7","doi-asserted-by":"crossref","unstructured":"Lehenmeier, C., Burghardt, M., Mischka, B.: Layout detection and table recognition\u2013recent challenges in digitizing historical documents and handwritten tabular data. In: International Conference on Theory and Practice of Digital Libraries, pp. 229\u2013242. Springer (2020)","DOI":"10.1007\/978-3-030-54956-5_17"},{"key":"350_CR8","doi-asserted-by":"crossref","unstructured":"Klampfl, S., Kern, R.: An unsupervised machine learning approach to body text and table of contents extraction from digital scientific articles. In: International Conference on Theory and Practice of Digital Libraries, pp. 144\u2013155. Springer (2013)","DOI":"10.1007\/978-3-642-40501-3_15"},{"key":"350_CR9","doi-asserted-by":"crossref","unstructured":"Bai, K., Mitra, P., Giles, C.L., Liu, Y.: Automatic extraction of table metadata from digital documents. In: Proceedings of the 6th ACM\/IEEE-CS Joint Conference on Digital Libraries (JCDL\u201906), pp. 339\u2013340. IEEE (2006)","DOI":"10.1145\/1141753.1141835"},{"key":"350_CR10","doi-asserted-by":"crossref","unstructured":"Choudhury, S.R., Tuarob, S., Mitra, P., Rokach, L., Kirk, A., Szep, S., Pellegrino, D., Jones, S., Giles, C.L.: A figure search engine architecture for a chemistry digital library. In: Proceedings of the 13th ACM\/IEEE-CS Joint Conference on Digital Libraries, pp. 369\u2013370 (2013)","DOI":"10.1145\/2467696.2467757"},{"key":"350_CR11","unstructured":"Lopez, P.: GROBID. GitHub (2008\u20132021). https:\/\/github.com\/kermitt2\/grobid. Accessed 2023-02-03"},{"key":"350_CR12","doi-asserted-by":"publisher","unstructured":"Choudhury, S.R., Mitra, P., Kirk, A., Szep, S., Pellegrino, D., Jones, S., Giles, C.L.: Figure metadata extraction from digital documents. In: 2013 12th International Conference on Document Analysis and Recognition, pp. 135\u2013139 (2013). https:\/\/doi.org\/10.1109\/ICDAR.2013.34","DOI":"10.1109\/ICDAR.2013.34"},{"key":"350_CR13","doi-asserted-by":"crossref","unstructured":"Clark, C., Divvala, S.: Pdffigures 2.0: mining figures from research papers. In: 2016 IEEE\/ACM Joint Conference on Digital Libraries (JCDL), pp. 143\u2013152 (2016)","DOI":"10.1145\/2910896.2910904"},{"key":"350_CR14","doi-asserted-by":"crossref","unstructured":"Siegel, N., Lourie, N., Power, R., Ammar, W.: Extracting scientific figures with distantly supervised neural networks. arXiv e-prints (2018) arXiv:1804.02445 [cs.DL]","DOI":"10.1145\/3197026.3197040"},{"issue":"20","key":"350_CR15","doi-asserted-by":"publisher","first-page":"10578","DOI":"10.3390\/app122010578","volume":"12","author":"S Sinha","year":"2022","unstructured":"Sinha, S., Hashmi, K.A., Pagani, A., Liwicki, M., Stricker, D., Afzal, M.Z.: Rethinking learnable proposals for graphical object detection in scanned document images. Appl. Sci. 12(20), 10578 (2022). https:\/\/doi.org\/10.3390\/app122010578","journal-title":"Appl. Sci."},{"key":"350_CR16","doi-asserted-by":"publisher","unstructured":"Yang, X., Yumer, E., Asente, P., Kraley, M., Kifer, D., Giles, C.L.: Learning to extract semantic structure from documents using multimodal fully convolutional neural networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4342\u20134351 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.462","DOI":"10.1109\/CVPR.2017.462"},{"key":"350_CR17","doi-asserted-by":"publisher","unstructured":"Saha, R., Mondal, A., Jawahar, C.V.: Graphical object detection in document images. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 51\u201358 (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00018","DOI":"10.1109\/ICDAR.2019.00018"},{"key":"350_CR18","doi-asserted-by":"crossref","unstructured":"Yashwant Kahu, S., Ingram, W.A., Fox, E.A., Wu, J.: ScanBank: a benchmark dataset for figure extraction from scanned electronic theses and dissertations. arXiv e-prints (2021) arXiv:2106.15320 [cs.CV]","DOI":"10.1109\/JCDL52503.2021.00030"},{"key":"350_CR19","doi-asserted-by":"publisher","unstructured":"Younas, J., Rizvi, S.T.R., Malik, M.I., Shafait, F., Lukowicz, P., Ahmed, S.: Ffd: figure and formula detection from document images. In: 2019 Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20137 (2019). https:\/\/doi.org\/10.1109\/DICTA47822.2019.8945972","DOI":"10.1109\/DICTA47822.2019.8945972"},{"key":"350_CR20","doi-asserted-by":"crossref","unstructured":"Smith, R.: An overview of the tesseract ocr engine. In: Proceedings of the Ninth International Conference on Document Analysis and Recognition-Volume 02. ICDAR \u201907, pp. 629\u2013633. IEEE Computer Society, USA (2007)","DOI":"10.1109\/ICDAR.2007.4376991"},{"issue":"7","key":"350_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1371\/journal.pbio.1002195","volume":"13","author":"ZD Stephens","year":"2015","unstructured":"Stephens, Z.D., Lee, S.Y., Faghri, F., Campbell, R.H., Zhai, C., Efron, M.J., Iyer, R., Schatz, M.C., Sinha, S., Robinson, G.E.: Big data: astronomical or genomical? PLoS Biol. 13(7), 1\u201311 (2015). https:\/\/doi.org\/10.1371\/journal.pbio.1002195","journal-title":"PLoS Biol."},{"key":"350_CR22","doi-asserted-by":"publisher","first-page":"16050202","DOI":"10.22323\/2.16050202","volume":"16","author":"L Smith","year":"2017","unstructured":"Smith, L., Arcand, K., Smith, R., Bookbinder, J., Smith, J.: Capturing the many faces of an exploded star: communicating complex and evolving astronomical data. JCOM J. Sci. Commun. 16, 16050202 (2017). https:\/\/doi.org\/10.22323\/2.16050202","journal-title":"JCOM J. Sci. Commun."},{"key":"350_CR23","doi-asserted-by":"publisher","unstructured":"Bagga, S., Piper, A.: HATHI 1M: Introducing a Million Page Historical Prose Dataset in English from the Hathi Trust. Harvard Dataverse (2021). https:\/\/doi.org\/10.7910\/DVN\/HAKKUA","DOI":"10.7910\/DVN\/HAKKUA"},{"key":"350_CR24","unstructured":"Pepe, A., Goodman, A., Muench, A.: The ADS all-sky survey. In: Ballester, P., Egret, D., Lorente, N.P.F. (eds.) Astronomical Data Analysis Software and Systems XXI. Astronomical Society of the Pacific Conference Series, vol. 461, p. 275 (2012)"},{"key":"350_CR25","unstructured":"Accomazzi, A., Kurtz, M.J., Henneken, E.A., Grant, C.S., Thompson, D., Chyla, R., Holachek, A., Sudilovsky, V., Murray, S.S.: Improved functionality and curation support in the ADS. In: American Astronomical Society Meeting Abstracts #225. American Astronomical Society Meeting Abstracts, vol. 225, pp. 336\u201355 (2015)"},{"key":"350_CR26","doi-asserted-by":"publisher","unstructured":"Iwatsuki, K., Sagara, T., Hara, T., Aizawa, A.: Detecting in-line mathematical expressions in scientific documents. In: Proceedings of the 2017 ACM Symposium on Document Engineering. DocEng \u201917, pp. 141\u2013144. Association for Computing Machinery, New York, NY, USA (2017). https:\/\/doi.org\/10.1145\/3103010.3121041","DOI":"10.1145\/3103010.3121041"},{"key":"350_CR27","unstructured":"of Freiburg:\u00a0Algorithms, U., Group, D.S.: pdfact. GitHub (2016\u20132023). https:\/\/github.com\/ad-freiburg\/pdfact Accessed 2023-02-03"},{"key":"350_CR28","unstructured":"K, P.: pdfedit. GitHub (2006\u20132012). https:\/\/github.com\/nullishzero\/PDFEdit Accessed 2023-02-03"},{"key":"350_CR29","unstructured":"Shinyama, Y.: pdfminer.six. GitHub (2018\u20132022). https:\/\/github.com\/pdfminer\/pdfminer.six. Accessed 2023-02-03"},{"key":"350_CR30","unstructured":"Developers, T.P.: pdftocairo. The Poppler Developers (2005\u20132011). https:\/\/manpages.ubuntu.com\/manpages\/trusty\/man1\/pdftocairo.1.html. Accessed 2023-02-03"},{"key":"350_CR31","unstructured":"Fenniak, M., Stamy, M., pubpub-zz, Thoma, M., Peveler, M., exiledkingcc, PyPDF2 Contributors: The PyPDF2 library (2022). https:\/\/pypi.org\/project\/PyPDF2\/"},{"key":"350_CR32","unstructured":"Kahu, S.Y.: Figure extraction from scanned electronic theses and dissertations. Master\u2019s thesis, Virginia Tech (2020). https:\/\/vtechworks.lib.vt.edu\/handle\/10919\/100113"},{"key":"350_CR33","doi-asserted-by":"crossref","unstructured":"Lopez, P.: Grobid: combining automatic bibliographic data recognition and term extraction for scholarship publications. In: Research and Advanced Technology for Digital Libraries: 13th European Conference, ECDL 2009, Corfu, Greece, September 27\u2013October 2, 2009. Proceedings 13, pp. 473\u2013474. Springer (2009)","DOI":"10.1007\/978-3-642-04346-8_62"},{"key":"350_CR34","unstructured":"Romary, L., Lopez, P.: Grobid-information extraction from scientific publications. ERCIM News 100 (2015)"},{"key":"350_CR35","doi-asserted-by":"crossref","unstructured":"Li, P., Jiang, X., Shatkay, H.: Extracting figures and captions from scientific publications. In: Proceedings of the 27th ACM International Conference on Information and Knowledge Management, pp. 1595\u20131598 (2018)","DOI":"10.1145\/3269206.3269265"},{"key":"350_CR36","doi-asserted-by":"crossref","unstructured":"Yu, C.-N., Levy, C.C., Saniee, I.: Convolutional neural networks for figure extraction in historical technical documents. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), 1, 789\u2013795. IEEE (2017)","DOI":"10.1109\/ICDAR.2017.134"},{"key":"350_CR37","unstructured":"Subramani, N., Matton, A., Greaves, M., Lam, A.: A survey of deep learning approaches for OCR and document understanding. arXiv:2011.13534 [cs] (2021)"},{"key":"350_CR38","doi-asserted-by":"publisher","unstructured":"Etter, D., Rawls, S., Carpenter, C., Sell, G.: A synthetic recipe for OCR. In: 2019 International Conference on Document Analysis and Recognition (ICDAR), pp. 864\u2013869. IEEE, Sydney, Australia (2019). https:\/\/doi.org\/10.1109\/ICDAR.2019.00143. https:\/\/ieeexplore.ieee.org\/document\/8978033\/","DOI":"10.1109\/ICDAR.2019.00143"},{"issue":"3","key":"350_CR39","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1007\/s00799-022-00325-2","volume":"23","author":"E Boros","year":"2022","unstructured":"Boros, E., Nguyen, N.K., Lejeune, G., Doucet, A.: Assessing the impact of OCR noise on multilingual event detection over digitised documents. Int. J. Digit. Lib. 23(3), 241\u2013266 (2022). https:\/\/doi.org\/10.1007\/s00799-022-00325-2","journal-title":"Int. J. Digit. Lib."},{"key":"350_CR40","doi-asserted-by":"publisher","unstructured":"Ramirez-Orta, J., Xamena, E., Maguitman, A., Milios, E., Soto, A.J.: Post-OCR document correction with large ensembles of character sequence-to-sequence models. Technical Report arXiv:2109.06264, arXiv (January 2022). https:\/\/doi.org\/10.48550\/arXiv.2109.06264","DOI":"10.48550\/arXiv.2109.06264"},{"key":"350_CR41","unstructured":"Zhu, D., Naiman, J.P., G., W.P.K., Goodman, A.: OCR with the Tesseract Engine: a parameter study with synthetic data. Unpublished paper (2023)"},{"key":"350_CR42","unstructured":"Cosillo, M., Naiman, J.P., G., W.P.K., Goodman, A.: OCR post correction for historical scientific texts. Unpublished paper (2023)"},{"issue":"1","key":"350_CR43","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1051\/aas:2000173","volume":"143","author":"CS Grant","year":"2000","unstructured":"Grant, C.S., Accomazzi, A., Eichhorn, G., Kurtz, M.J., Murray, S.S.: The NASA astrophysics data system: data holdings. Astron. Astrophys. Suppl. Ser. 143(1), 111\u2013135 (2000). https:\/\/doi.org\/10.1051\/aas:2000173","journal-title":"Astron. Astrophys. Suppl. Ser."},{"key":"350_CR44","doi-asserted-by":"crossref","unstructured":"Hasan Choudhury, M., Jayanetti, H.R., Wu, J., Ingram, W.A., Fox, E.A.: Automatic metadata extraction incorporating visual features from scanned electronic theses and dissertations. arXiv e-prints, (2021) arXiv:2107.00516 [cs.DL]","DOI":"10.1109\/JCDL52503.2021.00066"},{"key":"350_CR45","unstructured":"Bradski, G.: The OpenCV Library. Dr. Dobb\u2019s Journal of Software Tools (2000)"},{"key":"350_CR46","unstructured":"Skalski, P.: Make Sense. https:\/\/github.com\/SkalskiP\/make-sense\/ (2019)"},{"key":"350_CR47","unstructured":"W., A.: OCR Offset Image. StackOverflow (2019). https:\/\/i.stack.imgur.com\/qDUFT.png Accessed 2023-02-06"},{"key":"350_CR48","unstructured":"Bochkovskiy, A., Wang, C.-Y., Liao, H.-Y.M.: YOLOv4: optimal speed and accuracy of object detection (2020)"},{"key":"350_CR49","doi-asserted-by":"crossref","unstructured":"Wang, C.-Y., Bochkovskiy, A., Liao, H.-Y.M.: Scaled-YOLOv4: Scaling cross stage partial network. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13029\u201313038 (2021)","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"350_CR50","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. arXiv e-prints, (2015) arXiv:1506.02640 [cs.CV]","DOI":"10.1109\/CVPR.2016.91"},{"key":"350_CR51","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv e-prints (2015) arXiv:1506.01497 [cs.CV]"},{"key":"350_CR52","doi-asserted-by":"publisher","unstructured":"Schreiber, S., Agne, S., Wolf, I., Dengel, A., Ahmed, S.: Deepdesrt: deep learning for detection and structure recognition of tables in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 1162\u20131167 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.192","DOI":"10.1109\/ICDAR.2017.192"},{"key":"350_CR53","doi-asserted-by":"publisher","unstructured":"Vo, N.D., Nguyen, K., Nguyen, T.V., Nguyen, K.: Ensemble of deep object detectors for page object detection. In: Proceedings of the 12th International Conference on Ubiquitous Information Management and Communication. IMCOM \u201918. Association for Computing Machinery, New York, NY, USA (2018). https:\/\/doi.org\/10.1145\/3164541.3164644","DOI":"10.1145\/3164541.3164644"},{"key":"350_CR54","doi-asserted-by":"publisher","unstructured":"Gilani, A., Qasim, S.R., Malik, I., Shafait, F.: Table detection using deep learning. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 771\u2013776 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.131","DOI":"10.1109\/ICDAR.2017.131"},{"key":"350_CR55","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. arXiv e-prints (2017) arXiv:1703.06870 [cs.CV]","DOI":"10.1109\/ICCV.2017.322"},{"key":"350_CR56","doi-asserted-by":"crossref","unstructured":"Li, M., Xu, Y., Cui, L., Huang, S., Wei, F., Li, Z., Zhou, M.: DocBank: a benchmark dataset for document layout analysis. arXiv e-prints (2020) arXiv:2006.01038 [cs.CL]","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"350_CR57","unstructured":"Agarwal, M., Mondal, A., Jawahar, C.V.: CDeC-Net: composite deformable cascade network for table detection in document images. arXiv e-prints (2020) arXiv:2008.10831 [cs.CV]"},{"key":"350_CR58","unstructured":"Kr\u00e4henb\u00fchl, P., Koltun, V.: Efficient inference in fully connected CRFs with Gaussian edge potentials. arXiv e-prints (2012) arXiv:1210.5644 [cs.CV]"},{"key":"350_CR59","doi-asserted-by":"crossref","unstructured":"Kavasidis, I., Palazzo, S., Spampinato, C., Pino, C., Giordano, D., Giuffrida, D., Messina, P.: A saliency-based convolutional neural network for table and chart detection in digitized documents. arXiv e-prints (2018) arXiv:1804.06236 [cs.CV]","DOI":"10.1007\/978-3-030-30645-8_27"},{"key":"350_CR60","doi-asserted-by":"crossref","unstructured":"Dai, J., He, K., Li, Y., Ren, S., Sun, J.: Instance-sensitive fully convolutional networks. arXiv e-prints (2016) arXiv:1603.08678 [cs.CV]","DOI":"10.1007\/978-3-319-46466-4_32"},{"key":"350_CR61","unstructured":"Dai, J., Li, Y., He, K., Sun, J.: R-FCN: object detection via region-based fully convolutional networks. arXiv e-prints (2016) arXiv:1605.06409 [cs.CV]"},{"key":"350_CR62","doi-asserted-by":"crossref","unstructured":"Li, Y., Qi, H., Dai, J., Ji, X., Wei, Y.: Fully convolutional instance-aware semantic segmentation. arXiv e-prints (2016) arXiv:1611.07709 [cs.CV]","DOI":"10.1109\/CVPR.2017.472"},{"key":"350_CR63","doi-asserted-by":"publisher","unstructured":"Ha, J., Haralick, R.M., Phillips, I.T.: Recursive x\u2013y cut using bounding boxes of connected components. In: Proceedings of 3rd International Conference on Document Analysis and Recognition, vol. 2, pp. 952\u20139552 (1995). https:\/\/doi.org\/10.1109\/ICDAR.1995.602059","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"350_CR64","doi-asserted-by":"publisher","unstructured":"Chowdhury, S.P., Mandal, S., Das, A.K., Chanda, B.: Automated segmentation of math-zones from document images. In: Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings, pp. 755\u2013759 (2003). https:\/\/doi.org\/10.1109\/ICDAR.2003.1227763","DOI":"10.1109\/ICDAR.2003.1227763"},{"key":"350_CR65","unstructured":"Cronje, J.: Figure detection and part label extraction from patent drawing images. 23rd Annual Symposium of the Pattern Recognition Association of South Africa (2012) http:\/\/researchspace.csir.co.za\/dspace\/handle\/10204\/6464"},{"key":"350_CR66","doi-asserted-by":"publisher","unstructured":"Bukhari, S.S., Al\u00a0Azawi, M.I.A., Shafait, F., Breuel, T.M.: Document image segmentation using discriminative learning over connected components. In: Proceedings of the 9th IAPR International Workshop on Document Analysis Systems. DAS \u201910, pp. 183\u2013190. Association for Computing Machinery, New York, NY, USA (2010). https:\/\/doi.org\/10.1145\/1815330.1815354","DOI":"10.1145\/1815330.1815354"},{"key":"350_CR67","doi-asserted-by":"publisher","DOI":"10.3390\/app10186460","author":"J Younas","year":"2020","unstructured":"Younas, J., Siddiqui, S.A., Munir, M., Malik, M.I., Shafait, F., Lukowicz, P., Ahmed, S.: Fi-fo detector: figure and formula detection using deformable networks. Appl. Sci. (2020). https:\/\/doi.org\/10.3390\/app10186460","journal-title":"Appl. Sci."},{"issue":"4","key":"350_CR68","doi-asserted-by":"publisher","first-page":"567","DOI":"10.18287\/2412-6179-CO-1020","volume":"46","author":"VV Arlazarov","year":"2022","unstructured":"Arlazarov, V.V., Andreeva, E.I., Bulatov, K.B., Nikolaev, D.P., Petrova, O.O., Savelev, B.I., Slavin, O.A.: Document image analysis and recognition: a survey. Comput. Opti. 46(4), 567\u2013589 (2022). https:\/\/doi.org\/10.18287\/2412-6179-CO-1020","journal-title":"Comput. Opti."},{"issue":"6","key":"350_CR69","doi-asserted-by":"publisher","first-page":"109","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. 52(6), 109\u2013110936 (2019). https:\/\/doi.org\/10.1145\/3355610","journal-title":"ACM Comput. Surv."},{"key":"350_CR70","unstructured":"Kosaraju, S.: Document layout analysis and recognition systems. Master of Science in Computer Science Theses (2019) https:\/\/digitalcommons.kennesaw.edu\/cs_etd\/28\/"},{"issue":"2","key":"350_CR71","first-page":"93","volume":"55","author":"H Christenson","year":"2011","unstructured":"Christenson, H.: Hathitrust. Libr. Resour. Tech. Serv. 55(2), 93\u2013102 (2011)","journal-title":"Libr. Resour. Tech. Serv."},{"key":"350_CR72","unstructured":"Ribaric, T.: Automatic preparation of etd material from the internet archive for the dspace repository platform. Code4Lib J. (8) (2009)"},{"key":"350_CR73","unstructured":"Wajer, M.: OCR at the internet archive with tesseract and hOCR. Internet Archive (2020-2022). https:\/\/archive.org\/developers\/ocr.html. Accessed 2023-02-06"},{"key":"350_CR74","doi-asserted-by":"publisher","unstructured":"Jocher, G., Stoken, A., Borovec, J., NanoCode012, ChristopherSTAN, Changyu, L., Laughing, tkianai, Hogan, A., lorenzomammana, yxNONG, AlexWang1900, Diaconu, L., Marc, wanghaoyang0106, ml5ah, Doug, Ingham, F., Frederik, Guilhen, Hatovix, Poznanski, J., Fang, J., Yu, L., changyu98, Wang, M., Gupta, N., Akhtar, O., PetrDvoracek, Rai, P.: ultralytics\/yolov5: v3.1 - Bug Fixes and Performance Improvements. Zenodo (2020). https:\/\/doi.org\/10.5281\/zenodo.4154370","DOI":"10.5281\/zenodo.4154370"},{"key":"350_CR75","doi-asserted-by":"publisher","unstructured":"Honnibal, M., Montani, I., Van\u00a0Landeghem, S., Boyd, A.: spaCy: industrial-strength natural language processing in Python (2020). https:\/\/doi.org\/10.5281\/zenodo.1212303","DOI":"10.5281\/zenodo.1212303"},{"key":"350_CR76","doi-asserted-by":"publisher","unstructured":"Yi, X., Gao, L., Liao, Y., Zhang, X., Liu, R., Jiang, Z.: Cnn based page object detection in document images. In: 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR), vol. 01, pp. 230\u2013235 (2017). https:\/\/doi.org\/10.1109\/ICDAR.2017.46","DOI":"10.1109\/ICDAR.2017.46"},{"key":"350_CR77","unstructured":"Wu, Y., Kirillov, A., Massa, F., Lo, W.-Y., Girshick, R.: Detectron2. https:\/\/github.com\/facebookresearch\/detectron2 (2019)"},{"key":"350_CR78","doi-asserted-by":"publisher","unstructured":"Girshick, R.: Fast R-CNN. arXiv e-prints (2015) arXiv:1504.08083 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.1504.08083","DOI":"10.48550\/arXiv.1504.08083"},{"key":"350_CR79","doi-asserted-by":"publisher","unstructured":"Girshick, R., Donahue, J., Darrell, T., Malik, J.: Rich feature hierarchies for accurate object detection and semantic segmentation. arXiv e-prints (2013) arXiv:1311.2524 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.1311.2524","DOI":"10.48550\/arXiv.1311.2524"},{"key":"350_CR80","doi-asserted-by":"publisher","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv e-prints (2015) arXiv:1506.01497 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.1506.01497","DOI":"10.48550\/arXiv.1506.01497"},{"issue":"9","key":"350_CR81","doi-asserted-by":"publisher","first-page":"1627","DOI":"10.1109\/TPAMI.2009.167","volume":"32","author":"PF Felzenszwalb","year":"2010","unstructured":"Felzenszwalb, P.F., Girshick, R.B., McAllester, D., Ramanan, D.: Object detection with discriminatively trained part-based models. IEEE Trans. Pattern Anal. Mach. Intell. 32(9), 1627\u20131645 (2010). https:\/\/doi.org\/10.1109\/TPAMI.2009.167","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"350_CR82","doi-asserted-by":"publisher","unstructured":"Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C.-Y., Berg, A.C.: SSD: single shot multibox detector. arXiv e-prints (2015) arXiv:1512.02325 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.1512.02325","DOI":"10.48550\/arXiv.1512.02325"},{"key":"350_CR83","doi-asserted-by":"publisher","unstructured":"Yang, H., Hsu, W.: Transformer-based approach for document layout understanding. In: 2022 IEEE International Conference on Image Processing (ICIP), pp. 4043\u20134047 (2022). https:\/\/doi.org\/10.1109\/ICIP46576.2022.9897491","DOI":"10.1109\/ICIP46576.2022.9897491"},{"key":"350_CR84","doi-asserted-by":"publisher","unstructured":"Singhal, T., Liu, J., Blessing, L.T.M., Lim, K.H.: Analyzing scientific publications using domain-specific word embedding and topic modelling. In: 2021 IEEE International Conference on Big Data (Big Data), pp. 4965\u20134973 (2021). https:\/\/doi.org\/10.1109\/BigData52589.2021.9671598","DOI":"10.1109\/BigData52589.2021.9671598"},{"key":"350_CR85","doi-asserted-by":"crossref","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Bourdev, L., Girshick, R., Hays, J., Perona, P., Ramanan, D., Zitnick, C.L., Doll\u00e1r, P.: Microsoft COCO: common objects in context. arXiv e-prints (2014) arXiv:1405.0312 [cs.CV]","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"350_CR86","doi-asserted-by":"publisher","unstructured":"Wick, C., Puppe, F.: Fully convolutional neural networks for page segmentation of historical document images. In: 2018 13th IAPR International Workshop on Document Analysis Systems (DAS), pp. 287\u2013292 (2018). https:\/\/doi.org\/10.1109\/DAS.2018.39","DOI":"10.1109\/DAS.2018.39"},{"key":"350_CR87","doi-asserted-by":"publisher","unstructured":"Pletschacher, S., Antonacopoulos, A.: The PAGE (page analysis and ground-truth elements) format framework. In: 2010 20th International Conference on Pattern Recognition, pp. 257\u2013260. IEEE, Istanbul, Turkey (2010). https:\/\/doi.org\/10.1109\/ICPR.2010.72. http:\/\/ieeexplore.ieee.org\/document\/5597587\/","DOI":"10.1109\/ICPR.2010.72"},{"key":"350_CR88","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-47024-5_14","volume-title":"Eye Tracking and Visualization","author":"Z Bylinskii","year":"2017","unstructured":"Bylinskii, Z., Borkin, M.A., Kim, N.W., Pfister, H., Oliva, A.: Eye fixation metrics for large scale evaluation and comparison of information visualizations. In: Burch, M., Chuang, L., Fisher, B., Schmidt, A., Weiskopf, D. (eds.) Eye Tracking and Visualization, pp. 235\u2013255. Springer, Cham (2017)"},{"key":"350_CR89","doi-asserted-by":"crossref","unstructured":"Giannakopoulos, T., Foufoulas, I., Stamatogiannakis, E., Dimitropoulos, H., Manola, N., Ioannidis, Y.: Visual-based classification of figures from scientific literature. In: Proceedings of the 24th International Conference on World Wide Web, pp. 1059\u20131060 (2015)","DOI":"10.1145\/2740908.2742024"},{"issue":"11","key":"350_CR90","doi-asserted-by":"publisher","first-page":"3799","DOI":"10.1109\/TPAMI.2020.2992028","volume":"43","author":"K Davila","year":"2021","unstructured":"Davila, K., Setlur, S., Doermann, D., Kota, B.U., Govindaraju, V.: Chart mining: a survey of methods for automated chart analysis. IEEE Trans. Pattern Anal. Mach. Intell. 43(11), 3799\u20133819 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2992028","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"350_CR91","doi-asserted-by":"publisher","unstructured":"Nagy, G., Seth, S., Viswanathan, M.: A prototype document image analysis system for technical journals. Computer 25(7), 10\u201322 (1992). https:\/\/doi.org\/10.1109\/2.144436","DOI":"10.1109\/2.144436"},{"key":"350_CR92","doi-asserted-by":"publisher","unstructured":"Jiang, Z., Deng, H., Wu, Z., Guo, J., Sun, S., Mijovic, V., Yang, Z., Lou, J.-G., Zhang, D.: UniLayout: taming unified sequence-to-sequence transformers for graphic layout generation. arXiv e-prints (2022) arXiv:2208.08037 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.2208.08037","DOI":"10.48550\/arXiv.2208.08037"},{"key":"350_CR93","doi-asserted-by":"publisher","unstructured":"Silajev, I., Victor, N., Mortimer, P.: Semantic table detection with LayoutLMv3. arXiv e-prints (2022) arXiv:2211.15504 [cs.CV]. https:\/\/doi.org\/10.48550\/arXiv.2211.15504","DOI":"10.48550\/arXiv.2211.15504"},{"issue":"1","key":"350_CR94","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1080\/09737766.2019.1583836","volume":"13","author":"BM Gupta","year":"2019","unstructured":"Gupta, B.M., Dhawan, S.M.: Global research studies on \u201celectronic resources in libraries\u2019\u2019: a scientometric assessment during 1994\u20132017. COLLNET J. Sci. Inf. Manag. 13(1), 167\u2013181 (2019). https:\/\/doi.org\/10.1080\/09737766.2019.1583836","journal-title":"COLLNET J. Sci. Inf. Manag."},{"key":"350_CR95","doi-asserted-by":"publisher","unstructured":"Naiman, J.P.: Generalizability in document layout analysis for scientific article figure and caption extraction. arXiv e-prints (2023) arXiv:2301.10781 [cs.DL]. https:\/\/doi.org\/10.48550\/arXiv.2301.10781","DOI":"10.48550\/arXiv.2301.10781"},{"key":"350_CR96","doi-asserted-by":"crossref","unstructured":"Pfitzmann, B., Auer, C., Dolfi, M., Nassar, A.S., Staar, P.W.J.: DocLayNet: a large human-annotated dataset for document-layout analysis. arXiv e-prints (2022) arXiv:2206.01062 [cs.CV]","DOI":"10.1145\/3534678.3539043"},{"key":"350_CR97","doi-asserted-by":"publisher","unstructured":"Neubeck, A., Van\u00a0Gool, L.: Efficient non-maximum suppression. In: 18th International Conference on Pattern Recognition (ICPR\u201906), vol. 3, pp. 850\u2013855 (2006). https:\/\/doi.org\/10.1109\/ICPR.2006.479","DOI":"10.1109\/ICPR.2006.479"}],"container-title":["International Journal on Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-023-00350-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00799-023-00350-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00799-023-00350-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T12:05:43Z","timestamp":1726833943000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00799-023-00350-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,22]]},"references-count":97,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2024,9]]}},"alternative-id":["350"],"URL":"https:\/\/doi.org\/10.1007\/s00799-023-00350-9","relation":{},"ISSN":["1432-5012","1432-1300"],"issn-type":[{"type":"print","value":"1432-5012"},{"type":"electronic","value":"1432-1300"}],"subject":[],"published":{"date-parts":[[2023,3,22]]},"assertion":[{"value":"3 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 February 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 February 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}