Open Source OCR Software - Page 5

Our Objective is to create a GPU-based system that can accept scanned inputs of printed Devanagari texts, and produce outputs of the same in Unicode with a very high accuracy (>99.9%).

OCR Software developed by acem students as their minor project

The idea is to enhance and develop the national border crossing process by the integration of automated vehicle recognition while crossing country borders. i'm going to use Automatic number plate recognition (ANPR): a system that recognizes the numbers of the vehicle plates by using OCR (optical character recognition) technology and Infrared cameras. This is going to be achieved by taking the license plate image from the camera and processing it using the software I’m going to develop together with an open source OCR system. The output is going to be a text version of the plate number. Then it is going to retrieve that number from a database and get the information of the vehicle owner. Note: Please note that you need emgucv installed. you also need to move the project files to: C:\Emgu\emgucv-windows-x86XXX\Emgu.CV.Example\ Please note: that the project was created using visual studio 2003, on windows xp. and it might not run fluently on newer versions. please try to update it.

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.

Developing application which will automatically detect vehicle coming at entrance and exit using LDR sensors and detect number of vehicle using OCR implemented in java and should produce bill.

結合拍照功能、圖書館系統及ocr，讓使用者快速查詢到想要的書籍。

The bookshooter can be used in combination with program like Adobe Digital Editions or Kindle for PC. It takes pictures of every Page, which can be read by an OCR-Program.

Takes projective and affine distorted camera captured images and correct them for further use... like OCR, 3d reconstruction etc

Python script to address the problem of manually locating required event timestamps from carved CCTV DVR footages. Full details can be found in the paper published in Eighteenth Annual IFIP WG 11.9 International Conference on Digital Forensics. Link to paper: https://link.springer.com/chapter/10.1007/978-3-031-10078-9_8 The project has been divided into four modules: Framextract.py- Extracts frames from video footages Reconstruct.py- Attempts to repair unplayable video by extracting the frames. framestitch.py- Attempts to construct video using frames extracted from unplayable video. OCR.py- Performs image preprocessing & OCR on the extracted frames.

The Common OCR Service Interface. COSI is an API that allows developpers to easily bring OCR (Optical Character Recognition) capabilities to image processing applications. COSI supports existing OCR tools such as Tesseract, GOCR or GNU Ocrad.

This project is used for testing captcha.It mainly concern OCR.

Classnotes is an OCR intended to translate handwritten scans into text. In order for the program to translate the scans the user must create a handwriting profile by training the OCR with scans.

Conjecture is a modular, extensible, open-source C++ framework for Optical Character Recognition (OCR). It is not a single OCR, but rather an extensible collection of OCRs that can be explored, compared, extended and modified within a unified environment

Optical Character Recognition (OCR) software.

CuneiDjVu is a graphical frontend to a set of the Windows console utilities providing the DjVu OCR capability based on the CuneiForm-Linux OCR Engine

It's a dumb, but lightning fast OCR engine, not using any fancy math to recognize text from screenshots. Aim to recognize 100% of text from screenshot, even if image is affected by jpeg compression or text is affected by antialiasing.

The core idea is to remove the error sources and difficulties of Deep Learning applications by providing a safe haven of commoditized practices, all available as a single core. While the Open Source Deep Learning Server is the core element, with REST API, and multi-platform support that allows training & inference everywhere, the Deep Learning Platform allows higher level management for training neural network models and using them as if they were simple code snippets. Ready for applications of image tagging, object detection, segmentation, OCR, Audio, Video, Text classification, CSV for tabular data and time series. Neural network templates for the most effective architectures for GPU, CPU, and Embedded devices. Training in a few hours and with small data thanks to 25+ pre-trained models. Full Open Source, with an ecosystem of tools (API clients, video, annotation, ...) Fast Server written in pure C++, a single codebase for Cloud, Desktop & Embedded.

DictionaryReader is a research project; the aim of which is to create software that can automatically import data from mixed-script dictionaries. (For example, a Tibetan-English dictionary.)

DigitalEyes is an OCR (Optical Character Recognizer) developed in C/Caml released under GNU GPL by SuM42, as a sophomore project in EPITA.

allows kde user to make a lot of things whit right click on a pdf file.

The tool is an optical recognition tool which runs in following three mode : 1. Drawing Pad : Here the user can draw a character and the tool will recognize which character it is. 2. Image OCR : Image based OCR tool to recognize text and barcodes present in the image. It also supports saving the OCR output. 3. PDF OCR : PDF OCR is the advanced form of OCR, where PDF is parsed into image and OCR is run on that result. At present, PDF OCR comes with low maturity.

Scrapes trade information from screenshots for the game Elite Dangerous.

This tool will search for candidate characters, filter them, let the user tell which charachters they are, then analyses the known candidates to create templates used by the Elite Dangerous OCR tool to scrape trading data from screenshots.