Jump to content

UWPOCR - Windows Platform Optical character recognition API Implementation


Danyfirex
 Share

Recommended Posts

Ufff @Danyfirex, you rock! Thanks!

I've been using Tesseract to OCRing this kind of image a lot:

image.jpeg.a382a74e0c4ca9f7dc3d2d5cc29000ca.jpeg

A coordinate: [1-255],[1-255]

I have trained Tesseract on this kind of image (which I can create with the values I want -> I have the ground truth for training) and it works like a charm! However, it takes too long. With UWPOCR I was able to reduce the time by nearly 90% (yes, there is a "0" after the "9" ;) ).

I've read the comment about prepending an image with the characters I want to recognize. I imagine this helps the tool to guess what comes immediately after. I will use the sequence 0-9 and "," but extracted from previous images instead of Arial font.

My question is: Is it possible to restrict the set of characters or install a custom language only with those characters?

Link to comment
Share on other sites

Hello AUTOITER, unfortunately it does not provide such feature You can't restrict characters 

 

Saludos

Link to comment
Share on other sites

  • 2 months later...
  • 6 months later...
Link to comment
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
 Share

×
×
  • Create New...