OCR (Optical Character Recognition) of rural language in java

Question

0.00/5 (No votes)

See more:

Java

How can implement OCR using Java either through neural networks, for language malayalam.

Posted 27-Feb-12 17:50pm

gavkk

Add a Solution

2 solutions

Add a Solution

Add your solution here

Treat my content as plain text, not as HTML

Preview 0

…

Existing Members

Sign in to your account

...or Join us

Download, Vote, Comment, Publish.

Your Email
Password
Forgot your password?

Your Email
This email is in use. Do you need your password?
Optional Password

I have read and agree to the Terms of Service and Privacy Policy
Please subscribe me to the CodeProject newsletters

When answering a question please:

Read the question carefully.
Understand that English isn't everyone's first language so be lenient of bad spelling and grammar.
If a question is poorly phrased then either ask for clarification, ignore it, or edit the question and fix the problem. Insults are not welcome.
Don't tell someone to read the manual. Chances are they have and don't get it. Provide an answer or move on to the next question.

Let's work to help developers, not make them feel stupid.

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

Sergey Alexandrovich Kryukov · Accepted Answer · 2012-02-27T18:09:00

Solution 1

Do you really understand how big is this task? You can look at several works listed in my past answers:

OCR Software[^],
Apply online handwriting on neural network[^].

—SA

Posted 27-Feb-12 18:09pm

Sergey Alexandrovich Kryukov

krumia · Accepted Answer · 2012-02-27T18:33:00

For a moment, forget Java, forget neural networks, and forget Malayalam. Forget "implementing" too.

Just think "How to DO optical character recognition". Try googling and find some good articles/papers.

After you gain substantial knowledge on the subject, find out if there any implementations for languages with similar writing styles. I don't know this since I'm not Indian, but I guess Malayalam writing will closely resemble Hindi or Tamil. Find out if OCR has been done for those languages.

And then you should determine the method: Neural networks or whatever.

And after you determine the method, you determine the language: Java, C, or even VB :P.

And only after that should you think about implementation details.

Now you're going top-down. Since the problem is so huge, I think you should go bottom up.