Respected Sir/madam,<br><br> I am Soumajit Pramanik, a M.Tech Computer Sc student. I had talked to you earlier. Sorry for replying late. <br> I am interested in the OCR project. As I have mentioned earlier, I have some basic knowledge about character recognition using neural network. During last 4-5 days I discussed with my teachers and got some some more ideas.<br>
Basically I think I have to first learn well the techniques for OCR used by the open source tools. I have to understand why this tools are unable to achieve very high accuracy. If I can do that, the very next thing will be to decide what extra features I have to add or how to scan the letters more accurately. Then I have to use a good machine learning algorithm(neural n/w or svm or something more appropriate). Though achieving high accuracy like 98% will be very challenging, I do not think it is unachievable. <br>
Now, what should I do next?? <br> Soumajit Pramanik<br> <br>