{"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/crossing-language-borders-a-pipeline-for","title":"Crossing Language Borders: A Pipeline for Indonesian Manhwa Translation","arxiv_id":"2501.01629","date":"2025-01-03","proceeding":null,"authors":["Nithyasri Narasimhan","Sagarika Singh"],"abstract":"In this project, we develop a practical and efficient solution for automating the Manhwa translation from Indonesian to English. Our approach combines computer vision, text recognition, and natural language processing techniques to streamline the traditionally manual process of Manhwa(Korean comics) translation. The pipeline includes fine-tuned YOLOv5xu for speech bubble detection, Tesseract for OCR and fine-tuned MarianMT for machine translation. By automating these steps, we aim to make Manhwa more accessible to a global audience while saving time and effort compared to manual translation methods. While most Manhwa translation efforts focus on Japanese-to-English, we focus on Indonesian-to-English translation to address the challenges of working with low-resource languages. Our model shows good results at each step and was able to translate from Indonesian to English efficiently.","url_abs":"https://arxiv.org/abs/2501.01629v1","url_pdf":"https://arxiv.org/pdf/2501.01629v1.pdf","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":"crossing-language-borders-a-pipeline-for","repo_url":"https://github.com/Sagarika-Singh-99/indonesian_manhwa_translation","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"optical-character-recognition","task_name":"Optical Character Recognition (OCR)"},{"task_slug":"translation","task_name":"Translation"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/machine-translation-on-opensubtitles","task":"Machine Translation","dataset":"OpenSubtitles","model":"Fine tuned MarianMT","rank_in_archive_order":1,"of":1,"metrics":{"BLEU score":"27","METEOR":"61"},"uses_additional_data":false},{"leaderboard":"/sota/object-detection-on-4","task":"Object Detection","dataset":"","model":"Fine tuned Yolov5xu","rank_in_archive_order":1,"of":2,"metrics":{"F1 Score":"90.7","Mean Recall":"96.3","Mean mAP":"88.9","mAP@0.5":"0.963","mean precision":"89.4"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}