本文へスキップ

OCRFeeder

公開元: Joaquim Rocha

The complete OCR suite

オープンソースGPL-3.0-or-later

翻訳が未完了のため、このページの一部は書かれた言語のまま表示されています。

主な特徴

  • Analyzes document layouts to separate text blocks from images.
  • Integrates with external OCR engines to perform character recognition.
  • Provides manual editing tools to correct recognition and layout errors.

このアプリケーションについて

OCRFeeder is an optical character recognition suite designed for Linux desktops, created to help users convert physical paper documents and raster images into editable digital text. The program analyzes document layouts, segments regions into graphics or text, and coordinates with external OCR engines such as Tesseract or Ocrad to perform the actual character recognition. It provides a graphical workspace where users can inspect recognized text, correct layout mistakes, and export the final output to various document formats.

The application includes features for automatic and manual page segmentation, image cropping, and deskewing to improve recognition accuracy on scanned pages. Users can review the recognized content side-by-side with the original image source for verification. OCRFeeder integrates into existing desktop workflows by supporting multiple document formats for import and export, making it a modular tool for digitization tasks.

Linux

当サイトはこのファイルをホストしておらず、スキャンも内容の確認も行いません。出典の記載を読み、ご自身で判断してください。