{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:18:31Z","timestamp":1750220311482,"version":"3.41.0"},"reference-count":50,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T00:00:00Z","timestamp":1663286400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/100000208","name":"Institute of Museum and Library Services","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000208","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100000103","name":"National Endowment for the Humanities","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100000103","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Holland Computing Center of the University of Nebraska"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["J. Comput. Cult. Herit."],"published-print":{"date-parts":[[2022,9,30]]},"abstract":"<jats:p>The successful use of deep learning solutions for document image segmentation typically relies on a large number of manually labeled ground truth examples, which is expensive to obtain for historical document images that have significant noise effects and variation. At the same time, successful applications of deep learning solutions for document image segmentation have rich potential to facilitate greater levels of description in archival collections (e.g., at and below the item-level). These greater levels of description are critical to increasing access and use of archival collections across an array of research domains. In response, this article investigates whether an augmentation-based approach to generating pseudo-ground truth can be effective with a limited number of labeled images in a document segmentation application. The rationale is that if we can decrease the cost of generating ground truth through augmentation-based approaches, we can use these approaches as part of the description and access pipelines for historical library and archival collections. In this initial exploration, we first generate synthetic images and corresponding pseudo-ground truth using a set of existing degradation-based augmentation models from a small number of labeled actual images. When generating synthetic images, we control the visual quality distortion based on OCR word-level confidence to avoid generating images unlikely to be present in the dataset. Then, we perform several investigations to examine the impact of incorporating pseudo-ground truth data in the training of the deep learning network dhSegment and further evaluate the use of multiple combinations of degradation models. We also assess the generalizability of the approach by applying the trained network on a larger dataset. Our investigations primarily use real-world datasets known to have significant noise effects. Results show that augmentation-based pseudo-ground truth generation is capable of improving segmentation performance with the use of the full original dataset and requires only 30% of the original dataset. Results also show that using more than three degradation models is likely to cause overfitting during training. Furthermore, we show that a segmentation network trained on pseudo-ground truth data has generalization capability.<\/jats:p>","DOI":"10.1145\/3485845","type":"journal-article","created":{"date-parts":[[2022,3,7]],"date-time":"2022-03-07T13:42:44Z","timestamp":1646660564000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Augmentation-based Pseudo-Ground truth Generation for Deep Learning in Historical Document Segmentation for Greater Levels of Archival Description and Access"],"prefix":"10.1145","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9876-4388","authenticated-orcid":false,"given":"Chulwoo","family":"Pack","sequence":"first","affiliation":[{"name":"Computer Science &amp; Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yi","family":"Liu","sequence":"additional","affiliation":[{"name":"Computer Science &amp; Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leen-Kiat","family":"Soh","sequence":"additional","affiliation":[{"name":"Computer Science &amp; Engineering, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Elizabeth","family":"Lorang","sequence":"additional","affiliation":[{"name":"University Libraries, University of Nebraska-Lincoln, Lincoln, Nebraska, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,9,16]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.293"},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"issue":"2","key":"e_1_3_2_4_2","article-title":"Novel approach for baseline detection and text line segmentation","volume":"51","author":"Bahaghighat Mahdi Keshavarz","year":"2012","unstructured":"Mahdi Keshavarz Bahaghighat and Javad Mohammadi. 2012. Novel approach for baseline detection and text line segmentation. International Journal of Computer Applications 51, 2 (2012).","journal-title":"International Journal of Computer Applications"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2015.7364064"},{"key":"e_1_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1145\/2094114.2094129"},{"key":"e_1_3_2_7_2","unstructured":"Bulletin of the Technical Committee on Data Engineering"},{"key":"e_1_3_2_8_2","unstructured":"Xavier Bouthillier Kishore Konda Pascal Vincent and Roland Memisevic. 2015. Dropout as data augmentation. arXiv:1506.08700. Retrieved from https:\/\/arxiv.org\/abs\/1506.08700."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging6050032"},{"key":"e_1_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Kai Chen and Mathias Seuret. 2017. Convolutional neural networks for page segmentation of historical document images. arXiv:1704.01474. Retrieved from https:\/\/arxiv.org\/abs\/1704.01474 [cs.CV].","DOI":"10.1109\/ICDAR.2017.161"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"e_1_3_2_12_2","doi-asserted-by":"crossref","unstructured":"David Doermann and Karl Tombre. 2014. Handbook of Document Image Processing and Recognition. Springer.","DOI":"10.1007\/978-0-85729-859-1"},{"key":"e_1_3_2_13_2","first-page":"145","volume-title":"Proceedings of the ICPRAM","author":"Dumpala Veeru","year":"2019","unstructured":"Veeru Dumpala, Sheela Raju Kurupathi, Syed Saqib Bukhari, and Andreas Dengel. 2019. Removal of historical document degradations using conditional GANs. In Proceedings of the ICPRAM. 145\u2013154."},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.10.023"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00143"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/2501115.2501123"},{"key":"e_1_3_2_18_2","unstructured":"The National Digital Newspaper Program (NDNP) 2020. Chronicling America: Library of Congress. Retrieved October 2020 from https:\/\/chroniclingamerica.loc.gov."},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-011-0168-2"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.17723\/aarc.68.2.c741823776k65863"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/159335.159340"},{"key":"e_1_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging3040062"},{"key":"e_1_3_2_23_2","first-page":"730","article-title":"Global and local document degradation models","author":"Kanungo Tapas","year":"1993","unstructured":"Tapas Kanungo, Robert M. Haralick, and Ihsin Phillips. 1993. Global and local document degradation models. In Proceedings of 2nd International Conference on Document Analysis and Recognition. IEEE, 730\u2013734.","journal-title":"Proceedings of 2nd International Conference on Document Analysis and Recognition"},{"key":"e_1_3_2_24_2","first-page":"2","article-title":"Tesseract: An open-source optical character recognition engine","volume":"159","author":"Kay Anthony","year":"2007","unstructured":"Anthony Kay. 2007. Tesseract: An open-source optical character recognition engine. Linux Journal 2007, 159 (2007), 2.","journal-title":"Linux Journal"},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.104"},{"key":"e_1_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Sosuke Kobayashi. 2018. Contextual augmentation: Data augmentation by words with paradigmatic relations. arXiv:1805.06201. Retrieved from https:\/\/arxiv.org\/abs\/1805.06201.","DOI":"10.18653\/v1\/N18-2072"},{"key":"e_1_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2014.02.002"},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.472"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_31_2","unstructured":"Elizabeth M. Lorang and Leen-Kiat Soh. 2018. Increasing Our Vision for 21st-Century Digital Libraries. (2018)."},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-008-0076-2"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2019.00083"},{"key":"e_1_3_2_34_2","unstructured":"National Library of Luxembourg. [n.d.]. Historical Newspapers - BnL Open Data. Retrieved from https:\/\/data.bnl.lu\/data\/historical-newspapers."},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.14778\/3157794.3157797"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"e_1_3_2_37_2","unstructured":"Mausoom Sarkar Milan Aggarwal Arneh Jain Hiresh Gupta and Balaji Krishnamurthy. 2019. Document structure extraction for forms using very high resolution semantic segmentation. arXiv:1911.12170. Retrieved from https:\/\/arxiv.org\/abs\/1911.12170."},{"key":"e_1_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-019-0197-0"},{"key":"e_1_3_2_39_2","first-page":"2487","article-title":"CollaGAN: Collaborative GAN for missing image data imputation","author":"Lee Dongwook","year":"2019","unstructured":"Dongwook Lee, Junyoung Kim, Won-jin Moon, and Jongchul Ye. 2019. CollaGAN: Collaborative GAN for missing image data imputation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 2487\u20132496.","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"e_1_3_2_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2866692"},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR.2016.0093"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.05.030"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.247"},{"key":"e_1_3_2_45_2","first-page":"287","volume-title":"Proceedings of the 2018 13th IAPR International Workshop on Document Analysis Systems","author":"Wick Christoph","year":"2018","unstructured":"Christoph Wick and Frank Puppe. 2018. Fully convolutional neural networks for page segmentation of historical document images. In Proceedings of the 2018 13th IAPR International Workshop on Document Analysis Systems. IEEE, 287\u2013292."},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.001"},{"key":"e_1_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.462"},{"key":"e_1_3_2_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.148"},{"key":"e_1_3_2_49_2","first-page":"12113","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Yu Deli","year":"2020","unstructured":"Deli Yu, Xuan Li, Chengquan Zhang, Tao Liu, Junyu Han, Jingtuo Liu, and Errui Ding. 2020. Towards accurate scene text recognitionwith semantic reasoning networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 12113\u201312122."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.03.013"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"}],"container-title":["Journal on Computing and Cultural Heritage"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485845","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3485845","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:11:44Z","timestamp":1750191104000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3485845"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,16]]},"references-count":50,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,9,30]]}},"alternative-id":["10.1145\/3485845"],"URL":"https:\/\/doi.org\/10.1145\/3485845","relation":{},"ISSN":["1556-4673","1556-4711"],"issn-type":[{"type":"print","value":"1556-4673"},{"type":"electronic","value":"1556-4711"}],"subject":[],"published":{"date-parts":[[2022,9,16]]},"assertion":[{"value":"2020-11-13","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-12","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-09-16","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}