Computer vision vs OCR

Hi,

I came across activities called computer vision which reads data from image. so what is the difference between use of OCR and Computer Vision activity.

1 Like

So OCR is Optical Character Recognition which is used to convert the image, printed text etc into machine-encoded text.

Computer vision utilises OCR to retrieve the information but then uses that along with AI and various methods in order to automatically identify fields / information from that image.

3 Likes

Aah that’s a good question
They look alike but There is a huge difference between them

That is
—OCR is completely based in the image
That is the automation is done based on the images on the UI
And if those images slightly changes with its structure then ocr won’t be reliable in those situations
But if they remain same they are reliable

—while CV activities helps us to identify those image elements as a individual elements with human like recognition which is far more reliable than OCR and such application based, including Flash, Silverlight, PDFs, and images

Next is
—though CV activities has more advantages they do have some restrictions like Due to the fact that the Computer Vision activities have moved to the UIAutomation pack in 19.10, Installing the UIAutomation v19.10.1 pack in a project that already contains a version of the Computer Vision pack throws an error.

While ocr activities doesn’t have any such

And another one difference is
—ocr doesn’t need network to be in server while CV requires network with the server

Then
Finding with such dissimilarity we still have more similarities like CV activities includes The activities that have this feature are:

And so does OCR as well

Well these are few but important one
But still we may find many difference when we use them in our process development

Hope this would help you

Cheers @monish06

3 Likes

This topic was automatically closed 3 days after the last reply. New replies are no longer allowed.