{"id":13617390,"url":"https://github.com/duaibeom/chemOCR","last_synced_at":"2025-04-14T06:33:40.032Z","repository":{"id":217541785,"uuid":"530647340","full_name":"duaibeom/chemOCR","owner":"duaibeom","description":"DB-based Optical Chemical Structure Recognition","archived":false,"fork":false,"pushed_at":"2022-09-12T08:46:48.000Z","size":49899,"stargazers_count":7,"open_issues_count":1,"forks_count":2,"subscribers_count":1,"default_branch":"main","last_synced_at":"2024-11-08T02:32:39.825Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/duaibeom.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-08-30T12:29:26.000Z","updated_at":"2024-08-06T07:22:31.000Z","dependencies_parsed_at":null,"dependency_job_id":"237a7515-78cc-4f6a-be42-dd3e0db4cc43","html_url":"https://github.com/duaibeom/chemOCR","commit_stats":null,"previous_names":["duaibeom/chemocr"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duaibeom%2FchemOCR","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duaibeom%2FchemOCR/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duaibeom%2FchemOCR/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/duaibeom%2FchemOCR/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/duaibeom","download_url":"https://codeload.github.com/duaibeom/chemOCR/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":248834925,"owners_count":21169118,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T20:01:41.013Z","updated_at":"2025-04-14T06:33:39.072Z","avatar_url":"https://github.com/duaibeom.png","language":"Python","funding_links":[],"categories":["Python"],"sub_categories":[],"readme":"\u003ch1 align=\"center\"\u003e\nChemOCR(OCSR)\n\u003c/h1\u003e\n\n\u003ch3 align=\"center\"\u003e\nDB(Differentiable Binarization)-based Optical Chemical Structure Recognition  \n\u003c/h3\u003e \n\n\u003cimg src=\"data/demo_image.png\" align=\"center\"\u003e\n\n---\n\n```sh\nstreamlit run demo.py\n```\n\n### Backbone\n\n- Swin\n- ResNet\n- MobileNetV3\n\n## Parser\n**Rule-based method**\n\n## DATA\n\n- ChEMBL: https://www.ebi.ac.uk/chembl/\n\n### Training data sample\n\u003cimg src=\"data/sample_data.png\"\u003e\n\n### Limitation\n- Non-charged atom\n- (Inner bridged) Complex ring is not possible.\n- Specific resolution of image\n- Small text atoms (like Iodin) are not recognized.\n\n### TODO\n- [x] Character recognition (pretrained model from MMOCR RCNN)\n- [x] Web front-end (streamlit)\n- [ ] Bond direction analysis\n\n## References\n\n1. https://github.com/MhLiao/DB\n2. https://github.com/open-mmlab/mmocr\n3. https://github.com/rdkit/rdkit\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fduaibeom%2FchemOCR","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fduaibeom%2FchemOCR","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fduaibeom%2FchemOCR/lists"}