{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/arabic-scene-text-recognition-in-the-deep","title":"Arabic Scene Text Recognition in the Deep Learning Era: Analysis on A Novel Dataset","arxiv_id":null,"date":"2021-07-27","proceeding":"IEEE Access 2021 7","authors":["HEBA HASSAN1","Ahmed El-Mahdy","Mohamed E. Hussein"],"abstract":"The problem of scene text recognition has recently gained extra attention, being an essential part of scene\r\nunderstanding systems. The broad scope of applications and the unresolved challenges has given this\r\nproblem its popularity. However, the research focus has long been on languages with Latin characters\r\nwhile leaving behind other languages with different characteristics, such as the Arabic language. In this\r\npaper, we focus on Arabic scene text recognition and attempt to fill two main gaps regarding this research\r\ntask. First, the Arabic language is lacking a publicly available benchmark dataset to compare different\r\nproposed methods on the same grounds. Therefore, we introduce a novel Arabic/English dataset: Everyday\r\nArabic-English Scene Text dataset (EvArEST), to fill that need. Second, while deep learning methods have\r\ncontinuously evolved and pushed the sate of the art in languages with Latin characters, their use for the\r\nArabic language has been very limited. Therefore, we use our new dataset to evaluate the problem of\r\nArabic scene text recognition from three perspectives: (1) using deep learning techniques and studying\r\ntheir suitability for Arabic scene text recognition, where we identify essential components required for\r\nthe model to obtain good performance; (2) identifying Arabic text challenges that differ from Latin text\r\nand require special attention; (3) investigating a bilingual model that concurrently deals with Arabic and\r\nEnglish words, since Arabic text is usually found along with other languages. We determine the best model\r\nto handle bidirectional text, its challenges, and possible ways to overcome them. We offer both Arabic and\r\nBilingual text recognition results using EvArEST dataset for upcoming research to build upon and improve.\r\nWe also point to directions for future research based on the analysis performed on the dataset. The dataset\r\nis publicly available at https://github.com/HGamal11/EvArEST-dataset.","url_abs":"https://ieeexplore.ieee.org/abstract/document/9499028","url_pdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9499028","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"arabic-scene-text-recognition-in-the-deep","repo_url":"https://github.com/hgamal11/evarest-dataset","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":null},{"paper_slug":"arabic-scene-text-recognition-in-the-deep","repo_url":"https://github.com/HGamal11/EvArEST-dataset-for-Arabic-scene-text","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":null}],"tasks":[{"task_slug":"scene-text-recognition","task_name":"Scene Text Recognition"},{"task_slug":"scene-understanding","task_name":"Scene Understanding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}