{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T19:10:06Z","timestamp":1758913806796,"version":"3.44.0"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032061355","type":"print"},{"value":"9783032061362","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T00:00:00Z","timestamp":1758931200000},"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\/978-3-032-06136-2_12","type":"book-chapter","created":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T18:38:06Z","timestamp":1758911886000},"page":"124-134","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DM-LP: A Large Arabic Script Languages Dataset for\u00a0OCR and\u00a0Cataloguing Research"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4833-8882","authenticated-orcid":false,"given":"Luca","family":"Sala","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9914-3295","authenticated-orcid":false,"given":"Riccardo Amerigo","family":"Vigliermo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5556-1827","authenticated-orcid":false,"given":"Giovanni","family":"Sullutrone","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8087-6587","authenticated-orcid":false,"given":"Sonia","family":"Bergamaschi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"12_CR1","doi-asserted-by":"publisher","unstructured":"Adams, R.M.: Defining digital pedagogy in theological libraries. In: Anderson, C. (ed.) Digital Humanities and Libraries and Archives in Religious Studies: An Introduction, pp. 111\u2013122. De Gruyter (2022). https:\/\/doi.org\/10.1515\/9783110536539-008","DOI":"10.1515\/9783110536539-008"},{"key":"12_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1177\/1847979019890771","volume":"11","author":"K Adnan","year":"2019","unstructured":"Adnan, K., Akbar, R.: Limitations of information extraction methods and techniques for heterogeneous unstructured big data. Int. J. Eng. Bus. Manag. 11, 1\u201323 (2019). https:\/\/doi.org\/10.1177\/1847979019890771","journal-title":"Int. J. Eng. Bus. Manag."},{"key":"12_CR3","unstructured":"Aga Khan\u00a0University, C.: KITAB Project. https:\/\/kitab-project.org\/blogs"},{"issue":"6","key":"12_CR4","first-page":"3666","volume":"6","author":"M Ahmed","year":"2019","unstructured":"Ahmed, M., Abidi, A.: Review on optical character recognition. Int. Res. J. Eng. Technol. (IRJET) 6(6), 3666\u20133669 (2019)","journal-title":"Int. Res. J. Eng. Technol. (IRJET)"},{"key":"12_CR5","unstructured":"Al-Hashim, A.G., Mahmoud, S.A.: Printed Arabic text database (PATDB) for research and benchmarking. In: Proceedings of the 9th WSEAS international conference on Applications of computer engineering, ACE\u201910, pp. 62\u201368. World Scientific and Engineering Academy and Society (WSEAS), Stevens Point, Wisconsin (2010)"},{"key":"12_CR6","doi-asserted-by":"publisher","unstructured":"Alsheikh, I., Mohd, M.: A quranic dataset for text recognition. In: Proceedings of the 1st International Conference on Informatics, Engineering, Science and Technology, Bandung, Indonesia (2019). https:\/\/doi.org\/10.4108\/eai.18-7-2019.2287842","DOI":"10.4108\/eai.18-7-2019.2287842"},{"key":"12_CR7","first-page":"259","volume":"2","author":"NEB Amara","year":"2005","unstructured":"Amara, N.E.B., Mazhoud, O., Bouzrara, N., Ellouze, N.: Arabase: a relational database for arabic ocr systems. Int. Arab J. Inf. Technol. 2, 259\u2013266 (2005)","journal-title":"Int. Arab J. Inf. Technol."},{"key":"12_CR8","doi-asserted-by":"publisher","unstructured":"Anderson, C.: Introduction. In: Anderson, C. (ed.) Digital Humanities and Libraries and Archives in Religious Studies: An Introduction, pp. 1\u201310. De Gruyter (2022). https:\/\/doi.org\/10.1515\/9783110536539. https:\/\/www.degruyter.com\/document\/doi\/10.1515\/9783110536539\/html","DOI":"10.1515\/9783110536539"},{"key":"12_CR9","doi-asserted-by":"publisher","unstructured":"Badry, M., Hassan, H., Bayomi, H., Oakasha, H.: QTID: quran text image dataset. Int. J. Adv. Comput. Sci. Appl. (IJACSA) 9(3), 385\u2013391 (2018). https:\/\/doi.org\/10.14569\/IJACSA.2018.090351. https:\/\/thesai.org\/Publications\/ViewPaper?Volume=9&Issue=3 &Code=IJACSA &SerialNo=51","DOI":"10.14569\/IJACSA.2018.090351"},{"key":"12_CR10","doi-asserted-by":"publisher","unstructured":"Bai, J., et al.: Qwen-VL: a versatile vision-language model for understanding, localization, text reading, and beyond (2023). https:\/\/doi.org\/10.48550\/arXiv.2308.12966. http:\/\/arxiv.org\/abs\/2308.12966","DOI":"10.48550\/arXiv.2308.12966"},{"key":"12_CR11","doi-asserted-by":"publisher","first-page":"199","DOI":"10.5614\/itbj.ict.res.appl.2017.11.2.6","volume":"11","author":"B Bataineh","year":"2017","unstructured":"Bataineh, B.: A printed paw image database of Arabic language for document analysis and recognition. J. ICT Res. Appl. 11, 199\u2013211 (2017). https:\/\/doi.org\/10.5614\/itbj.ict.res.appl.2017.11.2.6","journal-title":"J. ICT Res. Appl."},{"key":"12_CR12","doi-asserted-by":"publisher","unstructured":"Bergamaschi, S., et al.: Preserving and conserving culture: first steps towards a knowledge extractor and cataloguer for multilingual and multi-alphabetic heritages. In: Proceedings of the Conference on Information Technology for Social Good, GoodIT \u201921, pp. 301\u2013304. Association for Computing Machinery, New York (2021). https:\/\/doi.org\/10.1145\/3462203.3475927","DOI":"10.1145\/3462203.3475927"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Chen, Z., et al.: Intern vl: scaling up vision foundation models and aligning for generic visual-linguistic tasks. 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 24185\u201324198 (2023). https:\/\/api.semanticscholar.org\/CorpusID:266521410","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"12_CR14","doi-asserted-by":"publisher","unstructured":"Chiron, G., Doucet, A., Coustaty, M., Visani, M., Moreux, J.P.: Impact of OCR errors on the use of digital libraries: towards a better access to information. In: 2017 ACM\/IEEE Joint Conference on Digital Libraries (JCDL), pp.\u00a01\u20134 (2017). https:\/\/doi.org\/10.1109\/JCDL.2017.7991582","DOI":"10.1109\/JCDL.2017.7991582"},{"key":"12_CR15","doi-asserted-by":"publisher","unstructured":"Chtourou, I., Rouhou, A.C., Jaiem, F.K., Kanoun, S.: ALTID: Arabic\/Latin text images database for recognition research. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 836\u2013840. IEEE Computer Society (2015). https:\/\/doi.org\/10.1109\/ICDAR.2015.7333879. https:\/\/www.computer.org\/csdl\/proceedings-article\/icdar\/2015\/07333879\/12OmNwB2dXI","DOI":"10.1109\/ICDAR.2015.7333879"},{"key":"12_CR16","volume-title":"Corso di arabo contemporaneo","author":"O Durand","year":"2010","unstructured":"Durand, O., Langone, A.D., Mion, G.: Corso di arabo contemporaneo. Hoepli, Milano (2010)"},{"key":"12_CR17","unstructured":"Escolano\u00a0Rodr\u00edguez, E., et al.: ISBD International Standard Bibliographic Description: 2021 Update to the 2011 Consolidated Edition (2022). https:\/\/repository.ifla.org\/handle\/123456789\/1939"},{"key":"12_CR18","volume-title":"Introduzione alle lingue semitiche","author":"G Garbini","year":"1994","unstructured":"Garbini, G., Durand, O.: Introduzione alle lingue semitiche. Studi sul Vicino Oriente antico, Paideia (1994)"},{"key":"12_CR19","unstructured":"Guerrini, M.: Verso nuovi principi e nuovi codici di catalogazione. Studi Bibliografici, Edizioni Sylvestre Bonnard, Milano (2005). http:\/\/archive.org\/details\/versonuoviprinci0000guer"},{"key":"12_CR20","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-642-41181-6_26","volume-title":"Image Analysis and Processing \u2013 ICIAP 2013","author":"FK Jaiem","year":"2013","unstructured":"Jaiem, F.K., Kanoun, S., Khemakhem, M., Abed, H., Kardoun, J.: Database for Arabic printed text recognition research. In: Petrosino, A. (ed.) ICIAP 2013. LNCS, vol. 8156, pp. 251\u2013259. Springer, Heidelberg (2013). https:\/\/doi.org\/10.1007\/978-3-642-41181-6_26"},{"key":"12_CR21","unstructured":"Kew, J.: Notes on some Unicode Arabic characters: recommendations for usage. Draft 2, SIL (2005). https:\/\/static-scripts.sil.org\/cms\/sites\/nrsi\/download\/arabicletterusagenotes\/ArabicLetterUsageNotes.pdf"},{"key":"12_CR22","doi-asserted-by":"publisher","unstructured":"Kiessling, B., Kurin, G., Miller, M.T., Smail, K.: Advances and limitations in open source Arabic-script OCR: a case study. Dig. Stud.\/Le champ num\u00e9rique 11(1) (2021). https:\/\/doi.org\/10.16995\/dscn.8094. http:\/\/arxiv.org\/abs\/2402.10943","DOI":"10.16995\/dscn.8094"},{"key":"12_CR23","doi-asserted-by":"publisher","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved Baselines with Visual Instruction Tuning (2024). https:\/\/doi.org\/10.48550\/arXiv.2310.03744. http:\/\/arxiv.org\/abs\/2310.03744","DOI":"10.48550\/arXiv.2310.03744"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Li, Y., Lee, Y.J.: Improved baselines with visual instruction tuning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 26296\u201326306 (2024)","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"12_CR25","doi-asserted-by":"publisher","unstructured":"Liu, X., Gao, F., Zhang, Q., Zhao, H.: Graph Convolution for Multimodal Information Extraction from Visually Rich Documents. In: Loukina, A., Morales, M., Kumar, R. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, vol. 2 (Industry Papers), pp. 32\u201339. Association for Computational Linguistics, Minneapolis (2019). https:\/\/doi.org\/10.18653\/v1\/N19-2005. https:\/\/aclanthology.org\/N19-2005","DOI":"10.18653\/v1\/N19-2005"},{"issue":"6","key":"12_CR26","doi-asserted-by":"publisher","first-page":"2231","DOI":"10.1016\/j.patcog.2013.12.012","volume":"47","author":"H Luqman","year":"2014","unstructured":"Luqman, H., Mahmoud, S.A., Awaida, S.: KAFD Arabic font database. Pattern Recogn. 47(6), 2231\u20132240 (2014). https:\/\/doi.org\/10.1016\/j.patcog.2013.12.012","journal-title":"Pattern Recogn."},{"key":"12_CR27","unstructured":"Martoglia, R., Bergamaschi, S., Ruozzi, F., Vanzini, M., Sala, L., Vigliermo, R.A.: Knowledge extraction, management and long-term preservation of non-Latin cultural heritages - Digital Maktaba project presentation. In: Alessia, B., Alex, F., Stefano, F., Stefano, M., Domenico, R. (eds.) Proceedings of the 19th Conference on Information and Research Science Connecting to Digital and Library Science. CEUR Workshop Proceedings, vol.\u00a03365, pp. 153\u2013161. CEUR, Bari (2023). https:\/\/ceur-ws.org\/Vol-3365\/#short11, iSSN: 1613-0073"},{"key":"12_CR28","first-page":"43","volume-title":"I costi sociali dell\u2019analfabetismo religioso","author":"P Naso","year":"2014","unstructured":"Naso, P.: Rapporto sull\u2019analfabetismo religioso in italia. In: Melloni, A. (ed.) I costi sociali dell\u2019analfabetismo religioso, pp. 43\u201357. Il Mulino, Bologna (2014)"},{"key":"12_CR29","doi-asserted-by":"publisher","unstructured":"Nguyen, L., Piwowarski, B., Laborde, J., Moyse, G.: Learning reading order via document layout with Layout2Pos. In: Antonacopoulos, A., et al. (eds.) Linking Theory and Practice of Digital Libraries, pp. 3\u201319. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72437-4_1","DOI":"10.1007\/978-3-031-72437-4_1"},{"key":"12_CR30","doi-asserted-by":"publisher","unstructured":"Nigst, L., Romanov, M., Savant, S.B., Seydi, M., Verkinderen, P.: OpenITI: a Machine-Readable Corpus of Islamicate Texts (2023). https:\/\/doi.org\/10.5281\/zenodo.7687795. https:\/\/zenodo.org\/record\/7687795","DOI":"10.5281\/zenodo.7687795"},{"key":"12_CR31","unstructured":"for Persian\u00a0Studies, R.I.: Persian Digital Library. https:\/\/launch.umd.edu\/project\/907"},{"key":"12_CR32","doi-asserted-by":"publisher","unstructured":"Slimane, F., Ingold, R., Kanoun, S., Alimi, A., Hennebert, J.: A new Arabic printed text image database and evaluation protocols. In: 10th International Conference on Document Analysis and Recognition, Barcelona, Spain, pp. 946\u2013950 (2009). https:\/\/doi.org\/10.1109\/ICDAR.2009.155","DOI":"10.1109\/ICDAR.2009.155"},{"key":"12_CR33","unstructured":"Stokes, P., Kiessling, B., St\u00f6kl Ben\u00a0Ezra, D., Tissot, R., Gargem, E.: The EScriptorium VRE for manuscript cultures. Classics@ J. Ancient Manus. Virt. Res. Environ. 18 (2021)"},{"key":"12_CR34","doi-asserted-by":"publisher","unstructured":"Sturgeon, D.: Chinese text project: a dynamic digital library of premodern Chinese. Dig. Scholarship Human. 36(Supplement_1), 101\u2013112 (2021). https:\/\/doi.org\/10.1093\/llc\/fqz046. https:\/\/doi.org\/10.1093\/llc\/fqz046","DOI":"10.1093\/llc\/fqz046"},{"key":"12_CR35","doi-asserted-by":"publisher","unstructured":"Sullutrone, G., Vigliermo, R.A., Sala, L., Bergamaschi, S.: Sensitive topics retrieval in digital libraries: a case study of \u1e25ad\u012b collections. In: Antonacopoulos, A., Hinze, A., Piwowarski, B., Coustaty, M., Di\u00a0Nunzio, G.M., Gelati, F., Vanderschantz, N. (eds.) Linking Theory and Practice of Digital Libraries, pp. 51\u201362. Springer, Cham (2024). https:\/\/doi.org\/10.1007\/978-3-031-72440-4_5","DOI":"10.1007\/978-3-031-72440-4_5"},{"key":"12_CR36","unstructured":"Team, Q.: Qwen-2vl: Open multimodal large model (2024). https:\/\/qwen2.org\/vl\/. Accessed 12 June 2025"},{"key":"12_CR37","doi-asserted-by":"publisher","unstructured":"TheIliffSchoolof Theology, E.H.: Library as interface for digital humanities. In: Anderson, C.B. (ed.) Digital Humanities and Libraries and Archives in Religious Studies: An Introduction, pp. 147\u2013164. De Gruyter (2022). https:\/\/doi.org\/10.1515\/9783110536539-010. https:\/\/www.degruyter.com\/document\/doi\/10.1515\/9783110536539-010\/html","DOI":"10.1515\/9783110536539-010"},{"key":"12_CR38","doi-asserted-by":"publisher","unstructured":"Wang, H., Wang, Q., Li, Y., Wang, C., Chu, C., Wang, R.: DocTrack: a visually-rich document dataset really aligned with human eye movement for machine reading (2023). https:\/\/doi.org\/10.48550\/arXiv.2310.14802. http:\/\/arxiv.org\/abs\/2310.14802","DOI":"10.48550\/arXiv.2310.14802"},{"key":"12_CR39","doi-asserted-by":"publisher","unstructured":"Wang, P., et al.: Qwen2-VL: enhancing vision-language model\u2019s perception of the world at any resolution (2024). https:\/\/doi.org\/10.48550\/arXiv.2409.12191. http:\/\/arxiv.org\/abs\/2409.12191","DOI":"10.48550\/arXiv.2409.12191"},{"key":"12_CR40","doi-asserted-by":"crossref","unstructured":"Yahia, M.H., Al-Muhtaseb, H.: Bpti: bilingual (Arabic\/English) printed text images dataset for recognition research (2022). https:\/\/papers.ssrn.com\/sol3\/papers.cfm?abstract_id=4007916","DOI":"10.34028\/iajit\/20\/4\/12"},{"key":"12_CR41","unstructured":"Yang, A., et al.: Qwen2 Technical Report (2024). https:\/\/arxiv.org\/abs\/2407.10671v4"}],"container-title":["Communications in Computer and Information Science","New Trends in Theory and Practice of Digital Libraries"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-06136-2_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,26]],"date-time":"2025-09-26T18:38:15Z","timestamp":1758911895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-06136-2_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"ISBN":["9783032061355","9783032061362"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-06136-2_12","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"27 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TPDL","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Theory and Practice of Digital Libraries","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tampere","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Finland","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":"23 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tpdl2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/tpdl2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}