I want to adapt an english unicode ocr for recognizing another language? i have no idea how to do it

Question

1.00/5 (2 votes)

See more:

C#

I want to adapt an ENGLISH unicode OCR for recognizing another language? I have no idea how to do it, I used the source code in here.
<a href="http://www.codeproject.com/Articles/15304/Unicode-Optical-Character-Recognition">Unicode Optical Character Recognition</a>[<a href="http://www.codeproject.com/Articles/15304/Unicode-Optical-Character-Recognition" target="_blank" title="New Window">^</a>]
It works fine until training phase.
But it prints the recognized characters as symbols

What I have tried:

Already set up the UNICODE OCR project in here

Posted 7-Mar-16 3:02am

Member 11842212

Updated 8-Mar-16 5:29am

v2

Add a Solution

Comments

F-ES Sitecore 7-Mar-16 9:11am

How you do it depends on how the code is implemented, which we don't know so no-one can answer this question.

Member 11842212 7-Mar-16 9:36am

MLP neural network using an example published here http://www.codeproject.com/Articles/15304/Unicode-Optical-Character-Recognition

F-ES Sitecore 7-Mar-16 9:41am

Just train it using images for the characters in your chosen language.

Member 11842212 7-Mar-16 9:44am

It works for my language in training phase and I can create the neural network file also.But in recognizing it prints the output as symbols such as question marks. Please help

1 solution

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 · 2016-03-08T05:29:00

I remember this article but don't remember if I tried to implement and test working with Unicode. You should better ask the author of your questions to the article. Add a comment with your question on the article page. The author will get a notification and a chance to answer you.

But I certainly tried some works and successfully obtained recognition of Unicode characters. I want to bring some more CodeProject articles on the topic to your attention. Please see my past answers:,
Apply online handwriting on neural network[^],
i need an ocr for a camera image capture[^].

Good OCR with the source code is hard to find. However, such works do exist and can be used for Unicode OCR. So far, I saw wonderful works on CodeProject, but all I tried needed some more development, to create a usable OCR system.

—SA