{"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/synthetic-data-for-text-localisation-in","title":"Synthetic Data for Text Localisation in Natural Images","arxiv_id":"1604.06646","date":"2016-04-22","proceeding":"CVPR 2016 6","authors":["Ankush Gupta","Andrea Vedaldi","Andrew Zisserman"],"abstract":"In this paper we introduce a new method for text detection in natural images.\nThe method comprises two contributions: First, a fast and scalable engine to\ngenerate synthetic images of text in clutter. This engine overlays synthetic\ntext to existing background images in a natural way, accounting for the local\n3D scene geometry. Second, we use the synthetic images to train a\nFully-Convolutional Regression Network (FCRN) which efficiently performs text\ndetection and bounding-box regression at all locations and multiple scales in\nan image. We discuss the relation of FCRN to the recently-introduced YOLO\ndetector, as well as other end-to-end object detection systems based on deep\nlearning. The resulting detection network significantly out performs current\nmethods for text detection in natural images, achieving an F-measure of 84.2%\non the standard ICDAR 2013 benchmark. Furthermore, it can process 15 images per\nsecond on a GPU.","url_abs":"http://arxiv.org/abs/1604.06646v1","url_pdf":"http://arxiv.org/pdf/1604.06646v1.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":"synthetic-data-for-text-localisation-in","repo_url":"https://github.com/youdao-ai/SRNet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"synthetic-data-for-text-localisation-in","repo_url":"https://github.com/PaddlePaddle/PaddleOCR","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"paddle","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"synthetic-data-for-text-localisation-in","repo_url":"https://github.com/ankush-me/SynthText","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":null,"task_name":"GPU"},{"task_slug":"object-detection","task_name":"Object Detection"},{"task_slug":"text-detection","task_name":"Text Detection"},{"task_slug":"object-detection-1","task_name":"object-detection"},{"task_slug":"regression-1","task_name":"regression"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/scene-text-detection-on-icdar-2013","task":"Scene Text Detection","dataset":"ICDAR 2013","model":"Gupta et al.","rank_in_archive_order":12,"of":16,"metrics":{"F-Measure":"83.0%","Precision":"92.0","Recall":"75.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1604.06646","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1604.06646"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/PaddlePaddle/PaddleOCR","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ankush-me/SynthText","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/youdao-ai/SRNet","reach":{"status":"ok","spdx":"GPL-3.0"}}],"summary":{"unverified":6},"by_repo_kind":{"listed":{"samples":6,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"ffced6d3ac2f6923","entry":"DST","repo":"ankush-me/SynthText","repo_kind":"listed","path":"poisson_reconstruct.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/poisson_reconstruct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffced6d3ac2f6923"}},{"code_sha256_prefix":"428c5ce64546ee0a","entry":"IDST","repo":"ankush-me/SynthText","repo_kind":"listed","path":"poisson_reconstruct.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/poisson_reconstruct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"428c5ce64546ee0a"}},{"code_sha256_prefix":"b47cddfb74004df7","entry":"crop_safe","repo":"ankush-me/SynthText","repo_kind":"listed","path":"text_utils.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b47cddfb74004df7"}},{"code_sha256_prefix":"15c813055f58cb66","entry":"get_grads","repo":"ankush-me/SynthText","repo_kind":"listed","path":"poisson_reconstruct.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/poisson_reconstruct.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"15c813055f58cb66"}},{"code_sha256_prefix":"d6195a48a890dfc2","entry":"move_bb","repo":"ankush-me/SynthText","repo_kind":"listed","path":"text_utils.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d6195a48a890dfc2"}},{"code_sha256_prefix":"fd4d5b853c711eb8","entry":"sample_weighted","repo":"ankush-me/SynthText","repo_kind":"listed","path":"text_utils.py","file_url":"https://github.com/ankush-me/SynthText/blob/HEAD/text_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fd4d5b853c711eb8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}