Skip to the content
Know your tech before you buy it. Makers: get listed from $49/mo

OCRFeeder

wiki.gnome.org

  • Free plan
  • Linux
7.4 Club score Visit wiki.gnome.org

What OCRFeeder is

OCRFeeder is a Linux application for analyzing document layouts and recognizing text in images. It outlines image contents, separates graphics from text, and runs OCR on text regions. In its GTK graphical interface, users can correct recognition errors and bounding boxes, set paragraph styles, and clean input images. It can import PDFs and save or reopen projects.

The application exports to multiple formats, with ODT as its main output, and includes both graphical and command-line interfaces. The graphical interface provides documentation through its Help menu or with F1. OCRFeeder uses system-wide OCR engines, including command-line engines. It is free software under the GNU General Public License, version 3 or any later version chosen by the user. The GNOME project page links to source code and release packages, and the project page links to a GitLab issue tracker. The listed roadmap includes plain-text export and undo and redo as proposed additions.

Who it suits

OCRFeeder suits Linux users who need to turn image-based documents or PDFs into editable, formatted output and review OCR results. It offers both a graphical interface and a command-line interface.

Good to know, and what to watch

  • Automatically separates graphics from text
  • Supports PDF imports and saved projects
  • Exports multiple formats, with ODT as its main format
  • Includes graphical and command-line interfaces
  • Users can correct recognition and layout
  • Available for Linux only
  • Plain-text export is listed as a roadmap addition
  • Undo and redo are listed as roadmap additions

OCRFeeder

Free

Free plan

Getting started

  1. Open the GNOME OCRFeeder website
  2. Download a source package or release package for Linux
  3. Install and launch the application
  4. Import an image or PDF
  5. Use the graphical interface or command-line interface
  6. Open Help or press F1 for documentation

Limits to check

OCRFeeder is free under GPL version 3 or later, with no paid tier listed. The roadmap lists plain-text export and undo/redo as additions rather than current capabilities.

The Club's review

OCRFeeder is a Linux document-layout analysis and optical character recognition application with both graphical and command-line interfaces. It is aimed at people who need to inspect, correct and format scanned pages, not just extract text. The free, GPL-licensed workflow is strongest for Linux users building editable documents around ODT and saved projects.

Overview

OCRFeeder automatically maps the contents of an image, separates graphics from text and applies OCR to text regions. That layout-first approach is useful on pages that mix illustrations, columns or other non-text elements, because it gives you a structure to review before exporting. The GTK application is a document workbench rather than a minimal recognition utility: you can correct characters, revise regions and shape the resulting document.

It accepts PDF imports and lets you save and reload projects. Those capabilities suit batches or documents that need several correction passes. The project is free software under the GNU General Public License version 3 or any later version, with source code and release packages linked by the GNOME project. A GitLab issue tracker provides a route for reporting problems and requests.

Key features

Layout analysis and editing

Automatic outlining and graphic-versus-text separation provide a useful first pass on mixed pages, but recognition still benefits from review. OCRFeeder lets you redefine bounding boxes and fix unrecognized characters, so users can repair both what was read and where it was placed. Paragraph styles help turn corrected regions into a more coherent document, while image-cleaning tools can improve the source before recognition. This combination favors a deliberate correction workflow over unattended conversion.

Import, projects and export

PDF import makes existing document scans workable, and project save/load preserves an editable job instead of forcing a restart. ODT is the principal output, while the interface can export to multiple formats. That is a practical route into an office-document workflow, especially when formatting matters. Plain-text export is listed as a roadmap addition rather than a current strength, and undo and redo are also proposed additions; users who rely on either should account for that gap.

Interfaces, engines and help

The GTK interface supports page-by-page correction and exposes documentation from the Help menu or with F1. A command-line interface offers a route for scripted or terminal-oriented work. OCRFeeder uses system-wide OCR engines and can work with command-line engines, so its results and setup depend partly on the engines installed on the Linux system. That integration is valuable for users who already manage local OCR tooling, but it is less self-contained than an all-in-one service.

Pricing

OCRFeeder costs nothing. There is one free plan, no trial period and no recurring subscription or seat quota described. The GPL license permits use of the software, and the project publishes source code as well as release packages. The README also states that it is supplied without warranty, including implied warranties of merchantability or fitness for a particular purpose, so organizations should set their own support and maintenance expectations.

Platforms

OCRFeeder is available on Linux as a desktop application. No Android, iOS, macOS or Windows edition is provided in its supported-platform scope, making operating-system choice the first qualification for adoption.

Who it's for

Choose OCRFeeder if you work on Linux and need to turn scanned PDFs or images into structured, editable documents while correcting layout and recognition errors yourself. It fits archivists, technical users and teams comfortable installing and selecting system OCR engines, particularly when ODT output and resumable projects matter.

It is a poorer match for users seeking a cross-platform desktop product, a hosted API, or a hands-off pipeline that delivers plain text with robust undo and redo. Its controls reward review time; they do not remove the need to check OCR accuracy.

Pros and cons

  • Pro: Automatic layout analysis separates graphics and text before OCR, giving mixed-page documents a more useful starting structure.
  • Pro: Editable bounding boxes, character corrections, paragraph styles and image cleanup support targeted repair instead of all-or-nothing recognition.
  • Pro: PDF import plus saved projects supports iterative work and revisions.
  • Pro: Graphical and command-line interfaces accommodate both visual editing and terminal workflows.
  • Con: Linux is the only supported platform, excluding users who need macOS, Windows or mobile access.
  • Con: Plain-text export and undo/redo are roadmap items, limiting workflows built around those functions.
  • Con: Reliance on system-wide OCR engines can make setup and output quality depend on local engine configuration.

Alternatives

Tesseract OCR is the better choice when you need an open-source OCR engine across Linux, macOS, Windows, Android, APIs or self-hosted deployments rather than OCRFeeder's layout-editing desktop workflow.

OCRmyPDF suits users who want free, self-hosted PDF processing across several platforms and are comfortable depending on external OCR and PDF tools.

docTR is preferable for developers wanting a free open-source Python library installable with pip, Git or Docker on API, desktop and self-hosted environments.

PaddleOCR fits Android and iOS users or projects that can work within its official API tier's daily 20,000-page parsing limit.

FreeOCR.AI is an option for web and API access, with a freemium model and paid monthly or annual credit plans.

Tungsten OmniPage is the alternative for buyers seeking a paid product with a free trial across desktop, API and self-hosted platforms.

Open-Capture is a free, GPLv3, self-hosted and web-capable option with no user limit.

Surya provides a free API and self-hosted option with pay-as-you-go allowances and request/concurrency limits.

Verdict

Choose it for controlled, revisable document production; look elsewhere if you need broad platform coverage, a self-contained hosted service, plain-text output or dependable undo and redo today.

The verdict

OCRFeeder combines layout analysis and OCR with tools for correcting recognition and formatting output. Linux users should account for the roadmap's listed gaps in plain-text export and undo and redo.

Questions people ask

What does OCRFeeder cost?

OCRFeeder is free software under GPL version 3 or any later version chosen by the user.

Which platforms does it support?

The listed platform is Linux, with desktop as the primary platform.

Can it process PDFs?

Yes. PDFs can be imported, and projects can be saved or loaded.

What output formats does it provide?

It generates multiple formats, with ODT as its main format.

Does it have a command-line interface?

Yes. OCRFeeder includes graphical and command-line interfaces.

Where is its source available?

The GNOME Wiki links to the source repository and release packages.

What the maker publishes

Author
The README names Joaquim Rocha as the author. source
Automatic analysis
It automatically outlines image contents, distinguishes graphics from text, and performs OCR on the text. source
Code availability
The GNOME Wiki links to the source repository and release packages. source
Command line
The project README says OCRFeeder includes both graphical and command line interfaces. source
Documentation
The README says graphical interface documentation is available from the Help menu or by pressing F1. source
Downloads
The GNOME project page links to source code and release packages. source
Editing
Its GTK graphical interface lets users correct unrecognized characters, define or correct bounding boxes, set paragraph styles, and clean input images. source
Editing tools
Its GTK graphical interface lets users correct recognized characters and bounding boxes, set paragraph styles, and clean input images. source
Export
The interface can export documents to multiple formats. source
Free plan
Yes source
Help
The graphical interface includes documentation accessible from its Help menu or by pressing F1. source
Supported inputs
both source
Interfaces
OCRFeeder provides graphical and command-line interfaces. source
Layout analysis
It automatically outlines image contents, distinguishes graphics from text, and performs OCR on text. source
License
The README says OCRFeeder is free software under the GNU General Public License, version 3 or, at the user's option, any later version. source
Limitations
The project roadmap lists plain-text export and Undo/Redo support as items to add. source
OCR engine integration
OCRFeeder uses system-wide OCR engines; its project documentation says command-line OCR engines can be used with it. source
Output
It generates multiple formats, with ODT as its main format. source
PDF and projects
Users can import PDFs and save or load projects. source
Primary platform
desktop source
Purpose
OCRFeeder is a document layout analysis and optical character recognition system. source
Roadmap limits
The listed roadmap includes proposed additions such as plain-text export, undo/redo, and an option to choose all OCR engines and automatically select the best results. source
Support
The project page links to a GitLab issue tracker. source
Warranty
The README states that OCRFeeder is distributed without any warranty, including implied warranties of merchantability or fitness for a particular purpose. source

Checked against the maker's pages on 9 Oct 2026.