{"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/scan-sequence-character-aware-network-for","title":"SCAN: Sequence-character Aware Network for Text Recognition","arxiv_id":null,"date":"2021-01-08","proceeding":"International Conference of Computer Vision Theory and Application 2021 1","authors":["Heba Hassan","Marwan Torki","Mohamed E. Hussein"],"abstract":"Text recognition continues to be a challenging problem in the context of text reading in natural scenes. Bearing\r\nin mind the sequential nature of text, the problem is usually posed as a sequence prediction problem from a\r\nwhole-word image. Alternatively, it can also be posed as a character prediction problem. The latter approach\r\nis typically more robust to challenging word shapes. Attempting to find the sweet spot that attains the best\r\nof the two approaches, we propose Sequence-Character Aware Network (SCAN). SCAN starts by locating\r\nand recognizing the characters and then generates the word using a sequence-based approach. It comprises\r\ntwo modules: a semantic-segmentation-based character prediction, and an encoder-decoder network for word\r\ngeneration. The training is done over two stages. In the first stage, we adopt a multi-task training technique\r\nwith both character-level and word-level losses and trainable loss weighting. In the second stage, the character level\r\nloss is removed, enabling the use of data with only word-level annotations. Experiments are conducted\r\non several datasets for both regular and irregular text, showing state of the art performance of the proposed\r\napproach. It also shows that the proposed approach is robust against noisy word detection.","url_abs":"https://www.scitepress.org/Papers/2021/103211/","url_pdf":"https://www.scitepress.org/Papers/2021/103211/103211.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":"scan-sequence-character-aware-network-for","repo_url":"https://github.com/HGamal11/SCAN","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"decoder","task_name":"Decoder"},{"task_slug":"semantic-segmentation","task_name":"Semantic Segmentation"}],"methods":[{"method_slug":"aware","method_name":"AWARE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}