I have read the paper Chris Harris , Mike Stephens - A Combined Corner and Edge Detector about the Harris Corner and Edge Detector, but I didn't understand the point that after low and high threshold they have got 5 regions, specially the point where he has got 2 corner classes, can you please explain that to me with image so I can get that point?

  • here is the part of the paper which I didn't understand:

    • By applying low and high thresholds, edge hysteresis can be carried out, and this can enhance the continuity of edges.

      • These classifications thus result in a 5-level image comprising:
    1. Background.
    2. Two corner classes.
    3. Two edge classes.
**Thanks in advance**

image after high and low threshold


1 Answer 1


After doing the low and high thresholds to the eigenvalues, there will be 2 types of corners:

  1. weak corners which are close to the low thresholding value.

  2. strong corners which are above the high thresholding value.

Harris Corner


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.