We use cookies to give you the best experience on our website. If you continue to browse, then you agree to our privacy policy and cookie policy.
Unfortunately, activation email could not send to your email. Please try again.

Can the performance of the OCR process be improved?

Can the performance of the OCR process be improved?

 

Yes, it is possible to speed up the performance of OCR, for this set performance of the OCR as rapid, but the output will not the accurate as the slow mode. Below is the code snippet.

C#:

 

Benchmark:

Document Page count  

Performance slow

Performance Rapid

1  

7.9 seconds  

4 seconds  

8  

35 seconds  

22 seconds  

12  

61 seconds  

32 seconds  

55  

174 seconds  

133 seconds  

 

Note:

In this context, accuracy means recognizing the data through OCR. In both cases using rapid and slow the accuracy is almost same, but for few cases with complex document structure the slow performance performs better while recognizing the data when compared to rapid, since in slow performance we used to perform page segment analysis using Tesseract which leads to more accuracy in recognizing the data, which is not implemented using rapid performance. 

Sample Link:

http://www.syncfusion.com/downloads/support/directtrac/162811/ze/OCRPerformance-1220983573

 
Article ID: Published Date: Last Revised Date: Platform: Control:
7077 08/31/2016 08/31/2016 Windows Forms PDF
Did you find this information helpful?
Add Comment
You must log in to leave a comment

You are using an outdated version of Internet Explorer that may not display all features of this and other websites. Upgrade to Internet Explorer 8 or newer for a better experience.