This is my first contribution to the world of open source. I started developing this project in the university, and I will continue to work on it until it is stable enough to run on any operating system. For now only runs in Windows and Linux. OSX is the next step, I hope this can be available soon.
What is EnaOCR?

EnaOCR is a Optical Character Recognition desktop application, that allows you to read multiple images files and convert them to ASCII text or XML.

With this application is easy to deploy any data to any external database in a short period of time. You just need one click to process hundreds of images in seconds, is very fast and with strong accuracy in the detection of words

This application was written in Java with the help of Tesseract engine.

The project was developed in Polytechnic Institute of Setúbal, Superior School of Technology, Portugal.

At the moment this project are just in Portuguese, but shortly it will be translated to another languages like English and Spanish, is just a matter of free time.

All the information and source are available in http://code.google.com/p/enaocr/. The source is protected through the GNU LGP license. If you want to reuse any part of the code in other project, let me know first.

If you feel this project interesting and want to join the team, send me an email, I will be very happy to answer.

Here are some printscreens: