{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T01:41:25Z","timestamp":1772934085957,"version":"3.50.1"},"reference-count":25,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T00:00:00Z","timestamp":1765152000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100002347","name":"Federal Ministry of Education and Research of Germany","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002347","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,12,8]]},"DOI":"10.1109\/bigdata66926.2025.11402448","type":"proceedings-article","created":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T20:57:57Z","timestamp":1772830677000},"page":"5437-5442","source":"Crossref","is-referenced-by-count":0,"title":["Arabic OCR in the Age of Multimodal Models: A Comprehensive Comparative Evaluation"],"prefix":"10.1109","author":[{"given":"Hossam","family":"Elsafty","sequence":"first","affiliation":[{"name":"Fraunhofer IAIS,Germany"}]},{"given":"Farizeh","family":"Aldabbas","sequence":"additional","affiliation":[{"name":"Fraunhofer IAIS,Germany"}]},{"given":"Rafet","family":"Sifa","sequence":"additional","affiliation":[{"name":"Fraunhofer IAIS,Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3768150"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.32604\/cmes.2022.024555"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-013-0201-8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.54"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3087647"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11760-023-02970-9"},{"key":"ref7","article-title":"Ain: The arabic inclusive large multimodal model","author":"Heakl","year":"2025","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"A complete survey on generative ai (aigc): Is chatgpt from gpt-4 to gpt-5 all you need?","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Qari-ocr: High-fidelity arabic text recognition through multimodal large language model adaptation","author":"Wasfy","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.1135"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52866\/2788-7421.1246"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/s23239475"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-12045-z"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MIUCC58832.2023.10278370"},{"key":"ref15","article-title":"A review of arabic optical character recognition","author":"Saleh","year":"2022","journal-title":"Journal of King Saud University - Computer and Information Sciences"},{"issue":"2","key":"ref16","first-page":"123","article-title":"Advances in arabic ocr: Challenges and solutions","volume":"49","author":"Nasr","year":"2023","journal-title":"Journal of Computational Linguistics"},{"key":"ref17","volume-title":"Chatgpt (gpt-5)","year":"2025"},{"key":"ref18","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","volume-title":"Dimi-arabic-ocr: Fine-tuned qwen2.5-vl for arabic text recognition","author":"Zaky","year":"2025"},{"key":"ref21","article-title":"Florence-2: Advancing a unified representation for a variety of vision tasks","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Qalam: A multimodal 11 m for arabic optical character and handwriting recognition","author":"Bhatia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","volume-title":"Surya: A lightweight document ocr and analysis toolkit","author":"Paruchuri","year":"2025"},{"key":"ref24","article-title":"Arabic-nougat: Fine-tuning vision transformers for arabic ocr and markdown extraction","author":"Rashad","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","volume-title":"Easyocr: Ready-to-use ocr with 80+ supported languages","year":"2020"}],"event":{"name":"2025 IEEE International Conference on Big Data (BigData)","location":"Macau, China","start":{"date-parts":[[2025,12,8]]},"end":{"date-parts":[[2025,12,11]]}},"container-title":["2025 IEEE International Conference on Big Data (BigData)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11400704\/11400712\/11402448.pdf?arnumber=11402448","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T06:59:22Z","timestamp":1772866762000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11402448\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":25,"URL":"https:\/\/doi.org\/10.1109\/bigdata66926.2025.11402448","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]}}}