Loading document OCR tools… (requires login and the OCR review service).
Site-wide inbox for document OCR. Upload a scan, confirm who it is and which soldier page would change, then Apply.
How it works
- Log in (same as photo uploads).
- Upload a document. OCR runs on the server; nothing is written yet.
- Confirm — a roster becomes a table: person on the scan, matched wiki page, and the one change that would be written on that profile (usually Team). Rank, role, and ASN from the scan are matching cues, not automatic edits. This is the same review for SO 103, 125, 135, and other multi-person scans — not a separate layout per form.
- Read Soldier pages that will be edited at the top. Use Preview Apply to see planned page changes without writing. Then Apply selected (requires
ocr-revieweror admin). Discard drops the job. - Expert options (raw OCR text, document type, gallery, overwrite) are under Advanced.
Profile shortcut: soldier page → Gallery → OCR a document (pre-selects that soldier).
Facebook gallery OCR candidates in the 70–79% band can be seeded into this queue (review only — nothing is auto-applied). See Facebook OCR review and python scripts/seed_fb_ocr_review_jobs.py.
Privacy
- Do not upload Social Security numbers or private contact details for living people.
- Staging files are not published until Apply (Gallery attach is optional; off by default for multi-person uploads).
- See About the data and Contribute.
For reviewers
Administrators can grant the ocr-reviewer group. Other logged-in uploads stay in the queue until a reviewer applies or discards them.