Using OCR to redact image documents

View as MarkdownMarkdown

Set up your AI agent

Give your coding agent live access to the GroupDocs documentation and API reference through the GroupDocs Docs MCP server — no install, no API key. Learn more

claude mcp add --transport http groupdocs-docs https://docs.groupdocs.com/mcp

Also process documents locally

The GroupDocs.Redaction MCP server lets your agent work with files on your machine; they are never uploaded. It needs the .NET 10 SDK or Docker.

claude mcp add groupdocs-redaction -- dnx GroupDocs.Redaction.Mcp --yes
Folders, licensing and more →

On this page

GroupDocs.Redaction redacts text it can only see in pictures, given an OCR engine:

  • image files, such as scans of printed documents (PNG, JPG and others);
  • images embedded in documents (PDF, DOCX and others).

GroupDocs.Redaction does not ship an OCR engine. You plug one in through an OCR connector, the Python side of the IOcrConnector interface, and pass it to RedactorSettings. Any engine works, local or a web service, as long as it reports each recognized word with its position.

In this section

  • OCR usage basics — what a connector receives and returns, with a connector you can run without an OCR engine.
  • Use Tesseract OCR — a connector built on the open-source Tesseract engine and pytesseract.

On this page