tesseract-ocr/tesseract

Tesseract Open Source OCR Engine (main repository)

What it solves

It provides a way to convert images of text into machine-readable text, a process known as Optical Character Recognition (OCR). This allows users to extract text from various image formats and output it into formats like plain text, PDF, or HTML.

How it works

Tesseract uses two different OCR engines: a modern neural network based on Long Short-Term Memory (LSTM) that focuses on line recognition, and a legacy engine that recognizes individual character patterns. It processes input images (such as PNG, JPEG, and TIFF) and uses trained data files to recognize text in over 100 different languages.

Who it’s for

It is designed for both end-users who need a command-line tool for text extraction and developers who want to integrate OCR capabilities into their own applications via the libtesseract C/C++ API.

Highlights

  • Supports over 100 languages out of the box.
  • Offers multiple output formats including plain text, hOCR, PDF, TSV, ALTO, and PAGE.
  • Supports Unicode (UTF-8).
  • Can be trained to recognize new languages.

Related

  • Project
    SubhamTyagi/android-ocr

    A privacy-focused Android application that uses Tesseract 5 to perform offline optical character recognition (OCR) in over 120 languages.

  • Project
    robertknight/ocrs

    A Rust-based OCR library and CLI tool that uses neural network models to extract text from images with minimal preprocessing.

  • Project
    bhimrazy/receipt-ocr

    An OCR engine that extracts either raw text or structured JSON data from receipt images using Tesseract and LLMs.

  • Project
    dynobo/normcap

    An OCR-powered screen-capture tool for Linux, macOS, and Windows that extracts text and barcodes from the screen instead of saving images.

  • Project
    ocrmypdf/OCRmyPDF

    A command-line tool that adds an OCR text layer to scanned PDFs, making them searchable and copy-pasteable while maintaining image quality.