Feature Detectors and Descriptors in scikit-image

[Stéfan van der Walt]

Hi Ankit

On Fri, Jun 7, 2013 at 3:32 PM, Ankit Agrawal <aaaagrawal at gmail.com> wrote:
>        I took a look at the implementation of Daisy feature descriptor in
> skimage and noticed that it finds descriptors around points that are spread
> uniformly with density based on step argument as the input. For this I
> checked its paper(Pg 3, section 3) and it said it can be used around
> feature-points as well as non feature-points. Almost all the Feature
> Descriptors(that I know of) including the ones that I am going to implement
> are calculated about keypoints. Because of the above reasons, I think an
> option should be provided in the functions of feature detectors to return
> the output as a vector containing location of feature-points. I would like
> to know the views/suggestions of community members experienced in this part
> of Computer Vision on this point and to suggest the best possible data-flow
> between functions of Feature Detectors and Feature Descriptors. Thank you.

I am in favor of developing a feature descriptor API that can
calculate descriptors only at specified positions.  As far as
structures are concerned, we try and stick to ndarrays wherever
possible; however, it may not always be possible.  Hopefully, we'll
discover a good and practical API via your project.

Regards
Stéfan