FICHA · AUR

tesseract-git

Open Source OCR Engine

  • cli
  • TERMINAL
  • LIBRARY
  • Launchable
  • Runs in terminal
official+codex · reviewed · May 29, 2026 description in en

Description

Text can be extracted from scanned pages, screenshots, and images through an open OCR engine. This is useful for converting image-only documents into searchable text or feeding recognition results into other workflows.

Recognition quality depends on image clarity, language data, layout, and preprocessing. Users should review extracted text before using it for legal, financial, or archival decisions.

How to run

tesseract

Commands: tesseract

Permissions

Permissions not analysed for this source yet.