Looks like no one’s replied in a while. To start the conversation again, simply ask a new question.

which format is best for screen capture in prep for OCR?

When taking a screen capture in preparation for OCR, should one take the screen capture in PDF or is there an advantage in terms of OCR accuracy in taking the screen capture in another format, e.g., png or tiff, and then letting the OCR software or some other software do the conversion to PDF?


In my tests, I'm seeing some minor differences in image and OCR quality, and some more significant differences in file size, depending on which software, graphic format, and settings I'm using and was wondering if there was some general guidance regarding format for taking screenshots for OCR'ing.


Thoughts?

MacBook Pro with Retina display, OS X Yosemite (10.10.5)

Posted on Oct 7, 2015 12:34 AM

Reply
1 reply

Oct 9, 2015 12:56 AM in response to humanengr

Narrowing the question -- for a screen capture of a text-only part of the screen where the text was fairly small, taking the screen capture as a PDF resulted in fewer errors after OCR than starting with a png or tiff. That seems surprising given that the PDF resolution in the screen capture is half the pixels in the png or tiff.


I don't understand how a 1/2-resolution PDF image yield a better OCR than a full-resolution png or tiff? Can someone explain?


Thanks in advance for any thoughts.

which format is best for screen capture in prep for OCR?

Welcome to Apple Support Community
A forum where Apple customers help each other with their products. Get started with your Apple ID.