Click here to Skip to main content
15,896,453 members
Please Sign up or sign in to vote.
0.00/5 (No votes)
See more:
Hello folks,

I am working on a handwriting recognition android application project. I should recognize characters by online recognition.(I mean there are no words or images). I searched lots of websites about it. I learned that I would use neural network and I also learned how I can use neural network. But, I am confused about how I can set neural network by using inputs from user. Should I use points of characters or turn the characters into image? And then how can I create neural network by just using this inputs?
Posted
Comments
Sergey Alexandrovich Kryukov 26-Dec-11 21:20pm    
At this stage, "I am working on a handwriting recognition android application project" sounds like a slight exaggeration. :-)
--SA

1 solution

You are asking your questions on a right site. Most of the information on OCR, in particular, using the approaches based on neural network, I found in CodeProject articles. Please see:

Neural Network OCR[^],
Creating Optical Character Recognition (OCR) applications using Neural Networks[^],
Neural Network Classifier[^],
A C# Project in Optical Character Recognition (OCR) Using Chain Code[^],
Unicode Optical Character Recognition[^],
Hebb neural network[^],
Backpropagation Artificial Neural Network in C++[^].

Sorry, none of then are in Java, but such tiny a difficulty cannot be a problem for you, can it?

—SA
 
Share this answer
 
Comments
Çağlar Tolga Tetik 28-Dec-11 9:17am    
Ok. Thanks. I continue searching on it, I hope I can handle it in 4 days. :) It will be a good project which you can connect your smart tv with your mobile phone and do every possible task with just writing on your mobile's screen or use gestures. If I can do it, I will explain it for java here. Thanks again.

This content, along with any associated source code and files, is licensed under The Code Project Open License (CPOL)



CodeProject, 20 Bay Street, 11th Floor Toronto, Ontario, Canada M5J 2N8 +1 (416) 849-8900