Open Source BSD Handwriting Recognition Software

Neuroph OCR - Handwriting Recognition is developed to recognize hand written letter and characters. It's engine derived's from the Java Neural Network Framework - Neuroph and as such it can be used as a standalone project or a Neuroph plug in.

This system provides printed and cursive handwriting recognition service as a shared library on GNU/Linux/Unix systems. Until someone writes another client, try the S/HIP: https://sourceforge.net/projects/ship-project/

Jarnal is a plattform-indepenent programm written in Java for notetaking, sketching and PDF-/picture-annotating. It works like a normal notepad with the difference of being digital. It is thought to be used with a stylus on tablet-pcs.

http://omr-ai.sourceforge.net/ described how to use MySQL and PHP for OMR. The PHP scripts were very much dependent on scanned page size and resolution. I have written the OMR page format and PHP scripts which are more flexible in nature. This script used horizontal and vertical guides to identify area to be analysed for MCQ answer checking and also identify and correct tilt. It is tailor made for A4 page size, but resolution can be varied with little impect on results. The answer page and scripts can be modified easily with little change in major functions of the library.

Qt Handwriting Recognizing it's a simple Qt GUI interface of a artificial neural network to provide handwrite recognition. This project use FANN (Fast Artificial Neural Network) on first approach.

This project is a really small software that can be used as a demonstration of my own shape recognition algorithms. There are a process during the shape drawing and a post-processing when it is done. Finally the shape recognition is launched. All the algorithms are done for real time gaming. So they are heuristics and do not give the optimal solution. Yet the given solution is generally a good one. In this demonstration, few shapes can be recognized: * circles * triangles * lines (vertical, horizontal and diagonal) * arcs with horizontal symmetry * lowercase phi letters The code offers the possibility to add its own shapes or even letters recognition. It will be improved to trigger a specific action by shape. The source code will be available in few days.

libcrn is document image processing library written in C++11 for Linux, Windows, Mac OsX and Google Android. It is a toolbox that allows to create easily software such as OCRs and layout analysis tools.

Linux drivers for Rolsen MNT-101 (Pegasus Mobile NoteTaker) digital pen.