what can I use for OCR project

Question

0.00/5 (No votes)

See more:

VS2013

Hy,

I am currently working on a project for a license plate reader. I used opencv to extract the lincense plate and binarize it. Now I have a binary image of the license plate with 3 number and 3 letters.

For OCR I tried to use tesseract but it seems I can't make it run. It compiles correctly but when I hit run it gives me an unhandled exception(details about the errror :http://stackoverflow.com/questions/27588822/unhandled-exception-when-running-tesseract-ocr[^])

I am thinking I need to make my own neural network for OCR from scratch, but I am trying to avoid that. Maybe you have another solution ? Please help me.

Posted 24-Dec-14 0:11am

Codrut Rotaru

Add a Solution

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 · 2014-12-24T05:15:00

Solution 1

You can consider this list: http://en.wikipedia.org/wiki/Comparison_of_optical_character_recognition_software[^].

Some of the solutions are open-source. Note, good open-source OCR is hard to find.

—SA

Posted 24-Dec-14 5:15am

Sergey Alexandrovich Kryukov

Comments

Codrut Rotaru 25-Dec-14 3:15am

do you have any suggestions for a OCR neural network ? some tutorials maybe?

Sergey Alexandrovich Kryukov 25-Dec-14 11:58am

I collected some interesting CodeProject (incomplete to be fully-functional products, but one could do a derived work) neural-based OCR works, but they are for .NET. If you are interesting, I'll share the links, but they are mostly for handwritten recognition. The license plate recognition is much simpler, it is based on fixed font, so you can even use systems based on teaching.
—SA

Codrut Rotaru 26-Dec-14 8:16am

I think I am going to use opencv's ML library to implement a neural network for OCR.
Tesseract proved to be such a pain in the a**. I cannot make it run in VS 2013, and i tried every solution on the internet, the most promissing being this one: http://vorba.ch/2014/tesseract-3.03-vs2013.html but at the very last step it doesn't compile because it cannot open include file allheaders.h. I tried copying it everywere it made sense but nothing. It needs to compile because i need the resulting binaries( the static libraries, to be exact) so that i can add them to linker input in VS).
Thanks for your advice.

Sergey Alexandrovich Kryukov 26-Dec-14 12:54pm

You are welcome (but are you going to accept the answer formally?)
To me, Tesseract code looked rather illiterate; no wonder you face problems, even if it works in principle.
—SA

Codrut Rotaru 25-Dec-14 3:32am

can I run another program from VS ? For example Abbyy OCR from your list to recognize the text from my image.

Sergey Alexandrovich Kryukov 25-Dec-14 11:55am

This would be a bad option, Abby OCR is proprietary. You could better use, for example open-source CuneiForm. Even pure Tesseract could work...
—SA