Hello guys I wanted to start on the implementation of the MSER[1] blob detection algorithm. I am leaning towards implementing the approach of the original paper[2], which has a linear time complexity for all practical images. The alternative is a guaranteed linear time implementation[2], but the paper does not have as many citations. Any thoughts are welcome. [1] : https://en.wikipedia.org/wiki/Maximally_stable_extremal_regions [2] : https://www.robots.ox.ac.uk/~vgg/research/affine/det_eval_files/matas_bmvc20... [3] : http://link.springer.com/chapter/10.1007%2F978-3-540-88688-4_14 Thanks Vighnesh
Hi Vighnesh On Thu, Jan 28, 2016 at 5:31 PM, Vighnesh Birodkar <vighneshbirodkar@gmail.com> wrote:
I wanted to start on the implementation of the MSER[1] blob detection algorithm. I am leaning towards implementing the approach of the original paper[2], which has a linear time complexity for all practical images. The alternative is a guaranteed linear time implementation[2], but the paper does not have as many citations.
I'd say: go with the original first, especially if it is easier to implement. Stéfan
participants (2)
-
Stéfan van der Walt -
Vighnesh Birodkar