{"adoption": {"forks": 351, "observed_at": "2026-08-28T04:05:24.583740+00:00", "stars": 1703}, "canonical_url": "https://ross.abutalabs.com/products/wanghaisheng-awesome-ocr", "card": {"archived": false, "artifact_type": "learning-resource", "description": " A curated list of promising OCR resources", "domain": ["computer-vision", "awesome-lists", "tutorials"], "enriched": true, "function": ["ocr", "nlp", "image-processing", "developer-tools"], "health_score": 20, "homepage": "http://wanghaisheng.github.io/ocr-arxiv-daily/", "language": null, "license": "MIT", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["wanghaisheng/awesome-ocr"], "name": "wanghaisheng/awesome-ocr", "platform": ["cross-platform"], "pushed_at": "2022-06-24T04:50:59+00:00", "repo": "wanghaisheng/awesome-ocr", "stars": 1703, "tags": ["awesome-list", "ocr-resources", "curated-list", "research-papers", "text-recognition", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["find OCR libraries and tools for a project", "compare cloud OCR APIs like Baidu, Tencent, and Aliyun", "track the latest OCR research papers on arXiv", "find open-source text recognition SDKs like Tesseract or PaddleOCR", "discover resources for recognizing Chinese text from images", "learn about OCR engines for historical document processing"], "what_it_is": "A curated list of OCR (optical character recognition) resources, including libraries, cloud APIs, tools, and research paper trackers. It also links to companion projects like an arXiv daily paper tracker and tweet monitoring for OCR research.", "when_to_avoid": ["you need a production-ready OCR engine itself rather than a resource list", "you need actively maintained code - this is a curated list, not software", "you need up-to-date API pricing details, which may be stale"], "when_to_choose": ["you want a starting point to survey the OCR ecosystem", "you need to discover libraries, APIs, and research in one place", "you want to follow new OCR papers automatically"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/wanghaisheng-awesome-ocr", "repo": "wanghaisheng/awesome-ocr", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:24.583740+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:37:38.872491+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "0a74416f16be001e8444e57aebbd4859621e9728c75457c88c340be36e5d650b", "fetched_at": "2026-08-28T04:05:24.583740+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wanghaisheng/awesome-ocr"}, {"content_hash": "46bcaabbc1eeba6ac02d5a8b4dbf1795763307d2d963b8f082dd4fe717b22557", "fetched_at": "2026-08-29T11:12:30.216285+00:00", "kind": "homepage", "missing": false, "url": "http://wanghaisheng.github.io/ocr-arxiv-daily/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 3793, "days_push": 1531, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}