Open Source Linux OCR Software

Tesseract.js is a pure Javascript port of the popular Tesseract OCR engine. Tesseract.js' library supports more than 100 languages, automatic text orientation and script detection, a simple interface for reading paragraph, word, and character bounding boxes. Tesseract.js can run either in a browser and on a server with NodeJS. Tesseract.js is a javascript library that gets words in almost any spoken language out of images. The main Tesseract.js functions (ex. recognize, detect) take an image parameter, which should be something that is like an image. What's considered "image-like" differs depending on whether it is being run from the browser or through NodeJS.

DocWire SDK, a standout C++20AI driven data processing tool, has received award from SourceForge and strong backing from Microsoft. It handles nearly 100 file types, empowering efficient text extraction, web data extraction, and document analysis. For businesses, the shift to DocWire SDK signifies a leap forward. It promises comprehensive document format support and the ability to extract valuable insights from email boxes, databases, and websites using cutting-edge AI. DocWire SDK aims to expand its capabilities, focusing on versatile data extraction, platform support, and seamless integration with various systems. DocWire SDK is dedicated to streamlining data processing, reducing development time and costs, and harnessing the potential of AI. Its advancements promise a superior experience compared to its predecessor, DocToText.

When translating becomes a game ! Text to translate can be graphically selected. Several dictionnaries can be sorted according to the context. A large choice of matching strategies is available. The OCR engine is tunable.

Akshara Malayalam OCR is a project for the development of an OCR for printed and handwritten documents in Malayalam language. The inspiration is from similar OCR softwares in other languages etc.

Terese is a tool for proofreading OCR text. Terese tries to map the text back to the scanned image, and visually shows the differences. See the homepage for further details.

UCR is a project name for the development of an handwritten characters in Korean language. The goal is to create a UCR Library for handwriting as well as OCR from off-line, on-line data. And we have a plan to build a UCR library for mobile.

WebDjVuTextEd allows to edit the text layer of OCR'ed DjVu documents in a web browser. You can modify the structure (paragraphs, lines, words...) create, delete, edit text nodes, modify their container box by mouse, and run a spellchecker. The program does not directly read the DjVu files, it requires exported XML text data and images. When using without a webserver, you can open and save local files, but cannot take advantages of auto-save and spell checking. Note that current SVN version has much more features than V1.0!

OCR c++ library. Include: contour recognition; vectorisation; matrix letter feature recognition; auto page segmentation and detect rotation; SS3 ASM core; XML base; web-based GUI; 99,6% printed Unicode text recognition; letter base up to 1200 letters.

Got any emails with obnoxious inline text? Long text stories with bad formatting? Files that an OCR didn't quite translate right? RTF format files and no easy way to read or modify them? Then eBookFormatter is for you!

hocr - Hebrew OCR c/c++ library