2
$\begingroup$

Are they the same in terms of their algorithm? Or do they differ in their respective detection methods?

Improve this question
$\endgroup$

1 Answer 1

Reset to default
2
$\begingroup$

Haar-like features are, as the name says, features. They are basically some filters, just like the CNN filters. The main difference is that CNN learns the filters by training, while Haar filters are hand designed. These filters are called Haar-like features due to their similarity with Haar wavelets.

Haar cascades are a bunch of Haar-like features arranged into a classifier.

Improve this answer
$\endgroup$
2
  • $\begingroup$ Oh, so if I made a Haar Cascade XML file for object detection, it's basically bunched-up Haar-like features? I'm still using Haar-like features, right? $\endgroup$
    – Kirk
    Commented Jun 4, 2019 at 10:50
  • $\begingroup$ Assuming that in the Haar Cascade XML file you put filters which are Haar-like features, you are. This might be helpful docs.opencv.org/3.4/db/d28/tutorial_cascade_classifier.html $\endgroup$
    – Paul92
    Commented Jun 4, 2019 at 10:54

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

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