Click here to Skip to main content
15,616,780 members
Please Sign up or sign in to vote.
4.00/5 (1 vote)
See more:
Hi,
I want to make a C# windows application which convert a scanned image to text. Is it possible in C#.Net. Please help if you have any idea.

I searched some article in codeproject itself. But seems not working and not exactly my requirement. I will get an image contains text from the scanner. I need to convert that text in the image. Is that possible using .Net or Java?
Posted
Updated 20-Oct-20 15:32pm

What you are referring to is called Optical Character Recognition (OCR). There are a lot of great articles on CodeProject on how to OCR. Some of them talk about free methods but from my experience, they either have low accuracy or do not provide many features, such as:
http://www.codeproject.com/Articles/238114/Realtime-Webcam-Sudoku-Solver (does a lot more than OCR, but the OCR part is specific to numerical digits in Sudoku puzzles)
OCR With MODI in Visual C++ (uses MS control in C++, but can use same control in C#).

On the other hand, there are some commercial toolkits that provide more features and higher accuracy. You can find an article on one of them in the following link:
OCR with LEADTOOLS: The Better Choice
 
Share this answer
 
v2
 
Share this answer
 
To my experience, there are no good open-source solutions for this, only commercial components.

And for that reason I would suggest to check out a few of the commercial ones, to see which one performs faster and makes less mistakes in your particular case, and then just pick one. Price can also be a factor.

But if you start going through the open-source on this subject, you can get stuck there for a long time, and result will be pathetic in terms of both speed and errors.
 
Share this answer
 
I personally use 3 types of text detections in my Projects:

Tesseract (included in emgucv) - which performs a little slow IMO.

Again with emgucv there are Text detection and Text recognition Models available for emgu.dnn namespace.
Detection rate is good but you need to manually adapt exactly to your needs and there is no 1 Line of Code way ...

And third way is the Windows 10 ocr which is really fast and also free to use. Just Google for windows.media.ocr and you will find.
 
Share this answer
 
Comments
OriginalGriff 30-Nov-22 0:50am    
While I applaud your urge to help people, it's a good idea to stick to new questions, rather than 10 year old ones. After that amount of time, it's unlikely that the original poster is at all interested in the problem any more!
Answering old questions can be seen as rep-point hunting, which is a form of site abuse. The more trigger happy amongst us will start the process of banning you from the site if you aren't careful. Stick to new questions and you'll be fine.

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