tesseract ☆

« Back to VersTracker

Description:
OCR (Optical Character Recognition) engine

Type: Formula | Latest Version: 5.5.1@1 | Tracked Since: Dec 26, 2025

Links: Homepage | formulae.brew.sh

Category: Ai ml

Tags: ocr text-recognition image-processing ai document

Install: brew install tesseract

About:
Tesseract is a highly accurate OCR engine capable of recognizing text in over 100 languages. It serves as a robust backend for many document conversion and text extraction tools. The engine supports various image formats and can be trained to recognize custom fonts and layouts.

Key Features:

Supports over 100 languages
LSTM neural network based OCR engine
Extensive format support (TIFF, PNG, JPEG, etc.)
Highly trainable for custom fonts and layouts

Use Cases:

Digitizing scanned documents and PDFs
Automated text extraction from images
Data entry automation and document indexing

Alternatives:

ocrmypdf – Wraps Tesseract to add OCR layers to existing PDFs without altering visuals
gImageReader – A graphical frontend for Tesseract on Linux and Windows

Version History

Detected	Version	Rev	Change	Commit
Dec 26, 2025 8:14pm	5.5.1	1	VERSION_BUMP	a7293399
Sep 14, 2025 9:40pm		0	VERSION_BUMP	255e0946
Nov 11, 2024 9:56am		0	VERSION_BUMP	8df0257b
Oct 31, 2024 3:09am		2	VERSION_BUMP	f0bf07ab