An open source OCR engine that converts images of text into machine-readable text using neural net (LSTM) and legacy character pattern recognition across more than 100 languages. It is operated via a command-line interface or integrated directly as a C/C++ library.
Project overview
It offers dual OCR engines and extensive language coverage while running locally without requiring paid external services.
Project type
Document Processing
Use cases
Documents & Office
Deployment
Refer to project documentation
License
Apache-2.0
Best for
Developers and general users who need local, command-line, or library-based OCR processing.
Key capabilities
Provides a neural net (LSTM) based OCR engine focused on line recognition.
Includes a legacy character pattern recognition engine compatible with Tesseract 3.
Recognizes more than 100 languages out of the box with Unicode (UTF-8) support.
Supports various output formats including plain text, hOCR (HTML), PDF, invisible-text-only PDF, TSV, ALTO, and PAGE.
Allows users to train the engine to recognize other languages.
Provides libtesseract C and C++ APIs for developers to build their own applications.
Limitations and risks
The project does not include a GUI application.
OCR results may be poor without improving the quality of the input image.
Getting started
Install the engine via a pre-built binary package, download the required traineddata language files, and run 'tesseract imagename outputbase' to perform OCR.
Alternatives and comparisons
Provides advanced PDF understanding, unified document representation, and integrations with the generative AI ecosystem.
Converts PDF, image, DOCX, PPTX, and XLSX inputs into machine-readable formats such as Markdown and JSON.
Converts PDF documents and images into structured, LLM-ready data (JSON/Markdown) to support RAG and Agentic applications.
README: Tesseract 4 adds a new neural net (LSTM) based [OCR engine](https://en.wikipedia.org/wiki/Optical_character_recognition) which is focused on line recognition, but also still suppo…
README: Tesseract has **unicode (UTF-8) support**, and can **recognize [more than 100 languages](https://tesseract-ocr.github.io/tessdoc/Data-Files-in-different-versions.html)** "out of t…
README: Major version 5 is the current stable version and started with release [5.0.0](https://github.com/tesseract-ocr/tesseract/releases/tag/5.0.0) on November 30, 2021.