Chris Cerrato

Characters Are Converted During OCR

5 posts in this topic

Hello,

 

I have a trial version of PDFelement 6 Professional. When I used the OCR feature on a few documents, I notice that sometimes the characters are converted to different characters, like the examples below. The illustration on the left is the original, and the illustration on the right is the converted copy. 

 

Is this because I have a trial version? Is there a remedy for this sort of behavior in the full version?

 

   

 

Thank you,

 

Chris Cerrato

Share this post


Link to post
Share on other sites

Hi Chris,

 

I am sorry for the problem. I wonder whether you choose the right OCR language to be matched with your document language? After you click Edit>OCR, please change the OCR language, just as shown below:

Image 6.png

 

If this is exactly what you do but you still get the poor result on some OCRed character, I am sorry if the OCRed file quality fails to live up to your expectation. As the OCR technique depends on the color and contrast of the original PDF files. If the color and contrast is not strong, it will affect the identification of OCR. Please kindly understand.

 

And our development team will try best to optimize the OCR feature in the future updates. 

Best Regards,

Heidi

Share this post


Link to post
Share on other sites

Thank you, Heidi. I did confirm that the language is set to English, same results. It works really well aside from this, and it seems to be confined to roughly the same area of each document.

 

Is the OCR that I have with the trial version any different from the OCR that would be available with a complete version? I am wondering if there might be a difference because I used a separate link to download the OCR plug-in.

 

Chris Cerrato 

Share this post


Link to post
Share on other sites

Hi Chris,

 

Sorry for the delayed reply due to the spring festival holiday.

 

I am sorry if some characters are not well-recognized by performing OCR. Frankly speaking, the OCR in the trial version is the same with that in the full version regardless of a separate download link. Please kindly understand.

 

And our development team will keep working hard to improve the OCR quality. 

 

Best Regards,

Heidi

Share this post


Link to post
Share on other sites

Hi Chris,

 

Sorry for the delayed reply due to the spring festival holiday.

 

I am sorry if some characters are not well-recognized by performing OCR. Frankly speaking, the OCR in the trial version is the same with that in the full version regardless of a separate download link. Please kindly understand.

 

And our development team will keep working hard to improve the OCR quality. 

 

Best Regards,

Heidi

Share this post


Link to post
Share on other sites

Create an account or sign in to comment

You need to be a member in order to leave a comment

Create an account

Sign up for a new account in our community. It's easy!


Register a new account

Sign in

Already have an account? Sign in here.


Sign In Now
Sign in to follow this  
Followers 0