Open Source Linux OCR Software - Page 6

OOCR is a open source character recognition program, it is used to convert images to editable text.

Ozyr is a simple and easy to use OCR snipping tool to get text from images so you can copy and edit it. Source Code: https://github.com/PETEROLO291/Ozyr Installer: 117MB Program: 524MB Version: 1.0

Note as of 2013-09-13: I'm moving this project over to github due to this: http://www.gluster.org/2013/08/how-far-the-once-mighty-sourceforge-has-fallen/ Feel free to rejoin the more updated versions on https://github.com/mnott/PDFOCRWrapper Thanks. Matthias -- This is a wrapper written in Java that allows to recursively iterate a directory structure and call an OCR engine on each found PDF on the condition that it hat not yet been called for that PDF. It works well with the ABBYY OCR Engine for Linux.

Convert AI papers to GUI，Make it easy and convenient for everyone to use artificial intelligence technology。让每个人都简单方便的使用前沿人工智能技术 Paper2GUI: An AI desktop APP toolbox for ordinary people. It can be used immediately without installation. It already supports 40+ AI models, covering AI painting, speech synthesis, video frame complementing, video super-resolution, object detection, and image stylization. , OCR recognition and other fields. Support Windows, Mac, Linux systems. Paper2GUI: 一款面向普通人的 AI 桌面 APP 工具箱，免安装即开即用，已支持 40+AI 模型，内容涵盖 AI 绘画、语音合成、视频补帧、视频超分、目标检测、图片风格化、OCR 识别等领域。支持 Windows、Mac、Linux 系统。

An omnifont OCR engine. The long-term goal is recognition of formulas.

Turn your scanner into a free document reader for invoices (e.g. for e-banking) with the help of tesseract-ocr available for many unix (and also windows) platforms.

RadicalSpam Virtual Appliance takes full solution of RadicalSpam Community Edition , pre-installed in a OVF virtual machine ( Open Virtual Format ) compatible with the best virtualization platforms on the market , including VMware ESX Server. More information : http://www.radical-spam.org

Optical Character Recognition (OCR) utility

SALIX is a web application for the OCR and natural language parsing of Herbarium specimen labels

SecureJDMS is the attempt to develop a secure DMS, based on an RCP and (even untrusted) DB for data storage. For now, its all about managing scanned documents and searching them by content (using OCR). All data sent and stored will be strongly encrypted.

We have developed a co-simulator which combines support for power device models and communication models to improve practical investigation of the Smart Grid. Our proposed system uses OpenDSS power system simulator and OMNeT++ communication system simulator which are available under an open source licence. We have resolved a synchronisation problem between already existing communication and power networks simulators. This is done through a software interface between the communication and power networks simulators. We have tested our co-simulation framework with a renewable energy integration application. * This work was partly supported by an Open Collaborative Research (OCR) project from IBM. The authors are thankful to Deva Seetharam, Koushik Das and their team at IBM, for their valuable suggestions and comments.

Socr3 is a plugin-oriented, open source platform upon which I'm building an OCR suite. The name Socr3 stands for "Open Source Optical Character Recognition, Reading, Rendering, and Exporting", and is subject to change in the future.

TNN, a high-performance, lightweight neural network inference framework open sourced by Tencent Youtu Lab. It also has many outstanding advantages such as cross-platform, high performance, model compression, and code tailoring. The TNN framework further strengthens the support and performance optimization of mobile devices on the basis of the original Rapidnet and ncnn frameworks. At the same time, it refers to the high performance and good scalability characteristics of the industry's mainstream open source frameworks, and expands the support for X86 and NV GPUs. On the mobile phone, TNN has been used by many applications such as mobile QQ, weishi, and Pitu. As a basic acceleration framework for Tencent Cloud AI, TNN has provided acceleration support for the implementation of many businesses. Everyone is welcome to participate in the collaborative construction to promote the further improvement of the TNN inference framework.

Toxin Finder is an android app which uses google's tesseract ocr engine in order to capture an image of a product's ingredient list and return a list of harmful ingredients.

Useful when you have to re-type text from a picture that cannot be OCR-ed by FineReader. Just start the app, select transparency with the slide bar on the right, and type the text, looking at the picture with the text through the notepad.

Tx2Px is an open source program for rendering text unreadable with OCR programs. Such text may be used on web pages for verification purposes.

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.

Unlimited-OCR is Baidu’s open-source optical character recognition (OCR) model designed to accurately extract and understand text from complex documents, images, and multilingual content. Unlike traditional OCR systems that focus only on text detection and transcription, Unlimited-OCR combines advanced document parsing with language understanding, enabling it to recognize structured elements such as tables, formulas, charts, and mixed-layout documents while preserving their logical organization. The model is optimized for long documents and high-resolution inputs, making it suitable for digitizing books, research papers, invoices, forms, receipts, and business documents. It supports multilingual recognition, robust handling of noisy or distorted images, and integration into document AI pipelines. Built for practical deployment, Unlimited-OCR can serve as the foundation for document indexing, retrieval-augmented generation, knowledge extraction, and intelligent document processing.

Vedvarsha is an application for 2 purposes: 1. Handwariting script recognition that extracts recognized letters into documents. 2. OCR (Optical Character Recogniton) that works only for non-cursive and isolated characters. It depends upon libsyntactic,

Waygoer is an OCR program. It is based on contour extraction and momentum transformations. This allows for rotation- and scale-invariant recognition. Waygoer is still at an early stage of development.

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.

Handwriting recognition and OCR in Indic languages

ALTO files are XML files that store the output of OCR. Alto_search searches for terms in these ALTO files. A term can be several words and multiple terms can be searched at the same time. The output is in XML format and contains the coordinates of the words that were found as well as textual context around the hits.

The National library of Luxembourg's viewer for METS (http://www.loc.gov/standards/mets/) files with OCR files in the ALTO format. The viewer needs a tomcat application server to run in. It can be deployed so that it reads the METS files from a local folder. Its main use is for digitized newspapers and postcards but can be adapted to other METS profiles as well. The viewer can be seen in action at: http://www.eluxemburgensia.lu Other known users include: National library of Latvia (http://www.periodika.lv) University library of Belgrade (http://arhiva.unilib.rs/unilib/istorijskenovine/index.php?lang=en)