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 →

GroupDocs.Redaction supports both types of image documents for Optical Character Recognition (OCR):

  • image files, such as printed document scans (PNG, JPG, etc.)
  • embedded images within office documents (PDF, DOCX, etc.)

You have to implement IOcrConnector interface and pass the instance to RedactorSettings constructor.

For more details, see OCR Usage Basics article.

OCR usage limitations

There are the following limitations of the OCR with GroupDocs.Redaction for Node.js via Java v21.6:

  • textual replacements are not supported, so you have to use color box replacements to redact text in images.
  • Spreadsheets, HTML and Markdown document types are not supported.

We are working on removing these limitations in future releases of GroupDocs.Redaction.

Learn more

You can find details and examples of using OCR with GroupDocs.Redaction in one of these guides: