- Home
- OCR software
- GNU Ocrad
GNU Ocrad
What it is
GNU Ocrad is an OCR program and library that converts text in PNG or PNM images into 8-bit byte or UTF-8 output. Its layout analysis can distinguish columns and text blocks on printed pages, and it can run as a console application or as a backend for other programs. The manual documents optional image transformations, layout detection, character recognition, and text filters. Users can also create an OCR results file with structured recognition details. Ocrad uses ISO 10646 internally and offers character-set selection through the --charset option. The manual recommends characters at least 20 pixels high, noting that scanning at 300 dpi usually produces a suitable size. It also describes the program as sensitive to character defects and says adding recognition for new characters is difficult. The project characterizes Ocrad mainly as a research project, with algorithms that may change in later releases. GNU Ocrad is free for Linux and self-hosted use; its listed plan is free.
For and against
For
- Reads PNG and PNM images
- Outputs 8-bit byte or UTF-8 text
- Can separate columns and printed-page text blocks
- Runs standalone or as a backend
- Free plan listed as free
Against
- Sensitive to character defects
- Adding recognition for new characters is difficult
- Algorithms may change in later releases
The verdict
GNU Ocrad offers image-to-text recognition with layout analysis and multiple output options at no cost. Its stated sensitivity to character defects and research-project status are important considerations for readers who need predictable recognition behavior.
Who it suits
Ocrad may suit Linux users and developers who want a free OCR program for PNG or PNM images, either at the console or as a software backend. Its layout analysis is relevant to printed pages with columns or text blocks.
Plans and prices
GNU Ocrad
No price stated on the pages opened
Read 11 Oct 2026 · gnu.org
On the record
- Algorithm limitation
- The manual says Ocrad is sensitive to character defects and that adding recognition for new characters is difficult.gnu.org · read 11 Oct 2026
- Character sets
- The manual says Ocrad uses ISO 10646 internally and lets users select character sets with the --charset option.gnu.org · read 11 Oct 2026
- Download
- The project page directs users to GNU mirrors for the latest release and Savannah for older and testing versions.gnu.org · read 11 Oct 2026
- Image quality
- The manual recommends characters at least 20 pixels high and says scanning at 300 dpi usually produces a suitable character size.gnu.org · read 11 Oct 2026
- Input and output
- It reads PNG or PNM images and produces text in 8-bit byte or UTF-8 format.gnu.org · read 11 Oct 2026
- Supported inputs
- imagegnu.org · read 23 Sep 2026
- Layout analysis
- Its layout analyser can separate columns and text blocks on printed pages.gnu.org · read 11 Oct 2026
- Output formats
- The manual documents byte and UTF-8 text output, plus an OCR results file option containing structured recognition details.gnu.org · read 11 Oct 2026
- Processing options
- The manual documents optional image transformations, layout detection, character recognition, and text filters.gnu.org · read 11 Oct 2026
- Purpose
- GNU Ocrad is an OCR program and library based on feature extraction.gnu.org · read 11 Oct 2026
- Research project
- The manual describes Ocrad as mainly a research project and says many algorithms are ad hoc and may change in later releases.gnu.org · read 11 Oct 2026
- Support
- The project page identifies the bug-ocrad mailing list as the appropriate forum for discussing errors.gnu.org · read 11 Oct 2026
- Usage
- Ocrad can run as a standalone console application or as a backend to other programs.gnu.org · read 11 Oct 2026
