{"id":46843916,"url":"https://github.com/fairdataihub/poster2json","last_synced_at":"2026-03-10T14:13:07.534Z","repository":{"id":336940468,"uuid":"1150038500","full_name":"fairdataihub/poster2json","owner":"fairdataihub","description":null,"archived":false,"fork":false,"pushed_at":"2026-02-24T04:52:53.000Z","size":3029,"stargazers_count":7,"open_issues_count":2,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-02-24T10:46:26.909Z","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/fairdataihub.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","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,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2026-02-04T20:10:05.000Z","updated_at":"2026-02-24T04:52:44.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/fairdataihub/poster2json","commit_stats":null,"previous_names":["fairdataihub/poster2json"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/fairdataihub/poster2json","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairdataihub%2Fposter2json","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairdataihub%2Fposter2json/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairdataihub%2Fposter2json/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairdataihub%2Fposter2json/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/fairdataihub","download_url":"https://codeload.github.com/fairdataihub/poster2json/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/fairdataihub%2Fposter2json/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":30336300,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-03-10T12:41:07.687Z","status":"ssl_error","status_checked_at":"2026-03-10T12:41:06.728Z","response_time":106,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"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":"2026-03-10T14:13:05.283Z","updated_at":"2026-03-10T14:13:07.518Z","avatar_url":"https://github.com/fairdataihub.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"\u003cdiv align=\"center\"\u003e\n\n\u003cimg src=\"https://cdn.posters.science/logos/poster-fairy.png\" alt=\"logo\" width=\"200\" height=\"auto\" /\u003e\n\n\u003cbr /\u003e\n\n\u003ch1\u003eposter2json\u003c/h1\u003e\n\n\u003cp\u003e\nConvert scientific posters (PDF/images) to structured JSON metadata using Large Language Models.\n\u003c/p\u003e\n\n\u003cbr /\u003e\n\n\u003cp\u003e\n  \u003ca href=\"https://github.com/fairdataihub/poster2json/graphs/contributors\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/contributors/fairdataihub/poster2json.svg?style=flat-square\" alt=\"contributors\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/fairdataihub/poster2json/stargazers\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/stars/fairdataihub/poster2json.svg?style=flat-square\" alt=\"stars\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/fairdataihub/poster2json/issues/\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/issues/fairdataihub/poster2json.svg?style=flat-square\" alt=\"open issues\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://github.com/fairdataihub/poster2json/blob/main/LICENSE\"\u003e\n    \u003cimg src=\"https://img.shields.io/github/license/fairdataihub/poster2json.svg?style=flat-square\" alt=\"license\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\u003cp\u003e\n  \u003ca href=\"https://pypi.org/project/poster2json\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/v/poster2json.svg\" alt=\"PyPI Version\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://pypistats.org/packages/poster2json\"\u003e\n    \u003cimg src=\"https://img.shields.io/pypi/dm/poster2json.svg?color=orange\" alt=\"PyPI Downloads\" /\u003e\n  \u003c/a\u003e\n  \u003ca href=\"https://zenodo.org/badge/latestdoi/1105067405\"\u003e\n    \u003cimg src=\"https://zenodo.org/badge/1105067405.svg\" alt=\"DOI\" /\u003e\n  \u003c/a\u003e\n\u003c/p\u003e\n\n\u003ch4\u003e\n    \u003ca href=\"https://fairdataihub.github.io/poster2json/\"\u003eDocumentation\u003c/a\u003e\n  \u003cspan\u003e · \u003c/span\u003e\n    \u003ca href=\"https://fairdataihub.github.io/poster2json/about/changelog/\"\u003eChangelog\u003c/a\u003e\n  \u003cspan\u003e · \u003c/span\u003e\n    \u003ca href=\"https://github.com/fairdataihub/poster2json/issues/\"\u003eReport Bug\u003c/a\u003e\n  \u003cspan\u003e · \u003c/span\u003e\n    \u003ca href=\"https://github.com/fairdataihub/poster2json/issues/\"\u003eRequest Feature\u003c/a\u003e\n\u003c/h4\u003e\n\u003c/div\u003e\n\n\u003cbr /\u003e\n\n---\n\n## Description\n\n**poster2json** extracts structured metadata from scientific conference posters (PDF or image format) into machine-actionable JSON conforming to the [poster-json-schema](https://github.com/fairdataihub/poster-json-schema).\n\nThe pipeline uses:\n\n- [**Llama-3.1-8B-Poster-Extraction**](https://huggingface.co/fairdataihub/Llama-3.1-8B-Poster-Extraction) for JSON structuring\n- **Qwen2-VL-7B** for vision-based OCR of image posters\n- **pdfalto** for layout-aware PDF text extraction\n\n## Quick Start\n\n### Installation\n\n```bash\npip install poster2json\n```\n\n### CLI Usage\n\n```bash\n# Extract metadata from a poster\nposter2json extract poster.pdf -o result.json\n\n# Validate extracted JSON\nposter2json validate result.json\n\n# Process multiple posters\nposter2json batch ./posters/ -o ./output/\n```\n\n### Python API\n\n```python\nfrom poster2json import extract_poster, validate_poster\n\n# Extract metadata\nresult = extract_poster(\"poster.pdf\")\nprint(result[\"titles\"][0][\"title\"])\n\n# Validate the result\nis_valid = validate_poster(result)\n```\n\n## Output Format\n\nOutput conforms to the [poster-json-schema](https://github.com/fairdataihub/poster-json-schema) (DataCite-based):\n\n```json\n{\n  \"$schema\": \"https://posters.science/schema/v0.1/poster_schema.json\",\n  \"creators\": [\n    {\n      \"name\": \"Garcia, Sofia\",\n      \"givenName\": \"Sofia\",\n      \"familyName\": \"Garcia\",\n      \"affiliation\": [\"University\"]\n    }\n  ],\n  \"titles\": [\n    { \"title\": \"Machine Learning Approaches to Diabetic Retinopathy Detection\" }\n  ],\n  \"posterContent\": {\n    \"sections\": [\n      { \"sectionTitle\": \"Abstract\", \"sectionContent\": \"...\" },\n      { \"sectionTitle\": \"Methods\", \"sectionContent\": \"...\" },\n      { \"sectionTitle\": \"Results\", \"sectionContent\": \"...\" }\n    ]\n  },\n  \"imageCaptions\": [{ \"captions\": [\"Figure 1.\", \"ROC curves showing...\"] }],\n  \"tableCaptions\": [{ \"captions\": [\"Table 1.\", \"Performance metrics\"] }]\n}\n```\n\n## System Requirements\n\n| Requirement | Specification                    |\n| ----------- | -------------------------------- |\n| GPU         | NVIDIA CUDA-capable, ≥16GB VRAM  |\n| RAM         | ≥32GB recommended                |\n| Python      | 3.10+                            |\n| OS          | Linux, macOS, Windows (via WSL2) |\n\n## Performance\n\nValidated on 10 manually annotated scientific posters:\n\n| Metric           | Score | Threshold |\n| ---------------- | ----- | --------- |\n| Word Capture     | 0.96  | ≥0.75     |\n| ROUGE-L          | 0.89  | ≥0.75     |\n| Number Capture   | 0.93  | ≥0.75     |\n| Field Proportion | 0.99  | 0.50–2.00 |\n\n**Pass Rate**: 10/10 (100%)\n\n## Documentation\n\n| Document                             | Description                     |\n| ------------------------------------ | ------------------------------- |\n| [Architecture](docs/architecture.md) | Technical details \u0026 methodology |\n| [Evaluation](docs/evaluation.md)     | Validation metrics \u0026 results    |\n\n## Development Setup\n\n```bash\n# Clone the repository\ngit clone https://github.com/fairdataihub/poster2json.git\ncd poster2json\n\n# Create a virtual environment\npython -m venv .venv\n\n# Activate the virtual environment\nsource venv/bin/activate\n.venv\\Scripts\\activate # On Windows\n\n# Install poetry\npip install poetry\n\n# Install dependencies\npoetry install\n\n# Run tests\npoe test\n\n# Format code\npoe format\n```\n\nIf you are on windows and have multiple python versions, you can use the following commands:\n\n```bash\npy -0p # list all python versions\n\npy -3.12 -m venv .venv\n```\n\n## License\n\nMIT License - see [LICENSE](LICENSE.md) for details.\n\n## Citation\n\n```bibtex\n@software{poster2json2026,\n  title = {poster2json: Scientific Poster to JSON Metadata Extraction},\n  author = {O'Neill, James and Soundarajan, Sanjay and Portillo, Dorian and Patel, Bhavesh},\n  year = {2026},\n  url = {https://github.com/fairdataihub/poster2json},\n  doi = {10.5281/zenodo.18320010}\n}\n```\n\n## Acknowledgements\n\n- [FAIR Data Innovations Hub](https://fairdataihub.org/)\n- Meta AI for Llama 3.1\n- Alibaba Cloud for Qwen2-VL\n- Part of the [posters.science](https://posters.science) platform\n\n## Contributing\n\nContributions welcome! Please see [CONTRIBUTING.md](CONTRIBUTING.md) for guidelines.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffairdataihub%2Fposter2json","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ffairdataihub%2Fposter2json","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ffairdataihub%2Fposter2json/lists"}