{"adoption": {"forks": 588, "observed_at": "2026-08-28T04:08:05.765142+00:00", "stars": 3465}, "canonical_url": "https://ross.abutalabs.com/products/dup-ocropy", "card": {"archived": true, "artifact_type": "library", "description": "Python-based tools for document analysis and OCR", "domain": ["computer-vision", "image-processing", "developer-tools"], "enriched": true, "function": ["ocr", "image-processing", "machine-learning", "nlp"], "health_score": 10, "homepage": null, "language": "Jupyter Notebook", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["ocropus-archive/DUP-ocropy"], "name": "ocropus-archive/DUP-ocropy", "platform": ["python", "cli"], "pushed_at": "2021-05-22T21:57:32+00:00", "repo": "ocropus-archive/DUP-ocropy", "stars": 3465, "tags": ["ocr", "document-analysis", "text-recognition", "binarization", "layout-analysis", "historical-documents", "rnn", "natural-language-processing", "linux", "docker"], "topics": [], "urls": [], "use_cases": ["run OCR on scanned document images", "binarize scanned pages for text recognition", "perform page layout analysis on documents", "recognize text lines from historical documents", "train custom OCR models for specific fonts or languages", "measure OCR error rates and confusion matrices", "edit and correct OCR ground truth"], "what_it_is": "OCRopy is a collection of Python-based tools for document analysis and OCR, covering binarization, page layout analysis, and text line recognition. It is not a turn-key OCR system and requires image preprocessing and possibly model training for specific documents.", "when_to_avoid": ["you want a turn-key OCR solution that works out of the box", "you need actively maintained software with modern Python support", "you only need modern-language OCR with minimal setup"], "when_to_choose": ["you need fine-grained control over the OCR pipeline stages", "you are processing historical or non-standard documents requiring custom models", "you want an open-source, scriptable document analysis toolkit"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/dup-ocropy", "repo": "ocropus-archive/DUP-ocropy", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:08:05.765142+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-29T18:36:52.762682+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "86f3cf1fd351e02063e404d296b7b052f46a5b348a07917c999c9aa5753a4ade", "fetched_at": "2026-08-28T04:08:05.765142+00:00", "kind": "readme", "missing": false, "url": "https://github.com/ocropus-archive/DUP-ocropy"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 8}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 4327, "days_push": 1929, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}