Ask Your Question

How can I normaliza MSER regions after they are fitted to ellipses?

asked 2012-10-29 02:47:18 -0600

How can I normaliza MSER regions after they are fitted to ellipses?

edit retag flag offensive close merge delete


What do you mean by 'normalize'?

Ben gravatar imageBen ( 2012-10-29 04:38:48 -0600 )edit

In order to build affine invariant feature descriptors in MESR regions, one must normalize the MSER regions. for details see the subsection: 3.1.2 Region Normalization in the paper of "A Performance Evaluation of Local Descriptors." IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 27, NO. 10, OCTOBER 2005 Thanks!

rokywang gravatar imagerokywang ( 2012-10-29 06:59:46 -0600 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2012-10-29 08:36:57 -0600

Ben gravatar image

For the descriptor extraction you will need a vector<cv::Keypoint> as input.

You can set a cv::KeyPoints size and angle by using the ellipse's RotatedRect's width, height and angle. This will define the region used to compute your descriptor.

I haven't tried this myself, but I think this should work.

edit flag offensive delete link more


Thanks for your suggestion! I will try this method.

rokywang gravatar imagerokywang ( 2012-10-30 20:24:03 -0600 )edit

Question Tools

1 follower


Asked: 2012-10-29 02:47:18 -0600

Seen: 575 times

Last updated: Oct 29 '12