All work

MLQU 006 · Live

Document transcription

Scanned pages to formatted Word, with stamps and signatures kept in place.

Client
Client project
Year
2026
Status
Live
Our role
Sole engineer
FastAPIClaude VisionOpenCVS3

The problem

Ordinary OCR reads the text on a scanned document and throws away everything else. For certified and legal work the stamp and the signature are the point, and losing them makes the output useless.

How it’s built

  1. Read each page

    One Claude Vision call per page, run concurrently under a configurable ceiling, so a hundred-page file does not crawl through serially.

  2. Find the non-text

    OpenCV and scikit-image locate stamps, seals and signatures and record where on the page they sat.

  3. Two output modes

    Placeholder replaces each element with a text marker. Preserve extracts the image and re-embeds it at the detected position.

  4. Async by default

    Submit a job, poll its status, download through a presigned link. Storage is S3 or MinIO, with Alembic managing the schema.

What changed

  • Stamps and signatures survive the conversion instead of vanishing
  • Long documents process page-parallel rather than one at a time
  • Output is a formatted DOCX, ready to edit

Want one of these?

Two lines is enough. We reply within a day.