Ask Your Question

How to control Dense SIFT

asked 2012-08-16 22:21:39 -0500

wmlong gravatar image
Ptr<FeatureDetector> detector = FeatureDetector::create("Dense");

I want to control how to detect features, such as step. How can I do it before calling detect instructions.

It's best to use factory method, because I want to change different feature detector conveniently.

detector->detect(image, keypoints);


edit retag flag offensive close merge delete


I have the same question, for 3.0 version. Any ideas please?

Khue gravatar imageKhue ( 2015-10-14 04:15:22 -0500 )edit

1 answer

Sort by ยป oldest newest most voted

answered 2013-02-11 10:00:10 -0500

alexcv gravatar image

Yes, i actually took a look at the code and this is not really clear how dense keypoint detection is performed. Documentation should be completed to help user not going into wrong stuff.

It seems that by default, the scale parameter of keypoints starts with value=1 and scaling factor is lower than 1. Some questions remain, one important being : _depending on the descriptor that is used how does it react ? => for example SIFT with scale=1, Does OpenCV SIFT understand native SIFT size or does it force less ?

edit flag offensive delete link more

Question Tools

1 follower


Asked: 2012-08-16 22:21:39 -0500

Seen: 1,897 times

Last updated: Aug 16 '12