Ex3 1b

Moderator: Computer Vision

Marc Schmitt
Beiträge: 7
Registriert: 29. Apr 2010 12:12

Ex3 1b

Beitrag von Marc Schmitt »

Hi @all,

we are not sure how the output Hessian matrix (H in hessian.m) should look like.

Do we have to concatenate the single derivatives [Ixx Ixy; Ixy Iyy] or do we have to provide the determinant det(H) like the cornerness map from the harris detector?


Beiträge: 25
Registriert: 21. Jun 2009 17:33

Re: Ex3 1b

Beitrag von diane »

The exercise sheet is indeed not so clear about this detail.
For the Hessian function (hessian.m), the H variable shouldn't output the actual Hessian matrix, but the values of the Hessian determinant, which is the information necessary to extract the interest points, as it gives something similar to the cornerness in the case of Harris.


Zurück zu „Computer Vision“