0
$\begingroup$

Hello I'm new on image processing.

I know there are a lot of threshold and region growing algorithms to use.

But I would like to know what is the trick for choosing suitable method for an image ?

Currently I'm trying to extract characters from this image

enter image description here

and most of the methods I've tried didn't really satisfy me. So I thought maybe I am doing it wrong. Here are some samples.

Normal Threshold

enter image description here

Sobel

enter image description here

Adaptive Threshold

enter image description here

$\endgroup$
2
$\begingroup$

The thresholding techniques that you would find here should be ideally suited to OCR applications. You could read and easily implement. They are also very efficient.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.