Speeded up robust feature(SURF) ?

2 次查看（过去 30 天）
Kyle
Kyle 2011-8-2
Hi,
SURF uses scale-space created by applying kernels of increasing size to the original image, to make it scale invariant.
Now since each level of the space has, image with their own feature point. I'm wandering how SURF determine which level of scale it has to take to determine the dominant orientation of the feature point to be rotation invariant?

请先登录，再回答此问题。

回答（1 个）

David Young
David Young 2011-8-2
Not really a MATLAB question - but anyway, the scale at which the feature was detected is used to determine its dominant orientation. See the second sentence of section 4.1 of the paper by Bay et al.
  6 个评论
显示 4更早的评论
Kyle
Kyle 2011-8-4
I think my understanding problem lies in the descriptor itself. I dont really understand how the information it stores can help in matching of feature point.
David Young
David Young 2011-8-15
The descriptor has information about the pattern of light and dark in the pixels around the feature point - but this information is independent (to a good approximation) of the scale or orientation of the pattern.

请先登录，再进行评论。

类别

在 Help Center 和 File Exchange 中查找有关 Semantic Segmentation 的更多信息

标签

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by