Index of /~mori/research/superpixels/code
Name Last modified Size Description
Parent Directory -
clusterLocations.m 17-Mar-2006 15:29 906
dist2.m 17-Mar-2006 15:29 888
img_000070.jpg 17-Mar-2006 15:29 25K
imncut_sp.m 17-Mar-2006 15:29 5.0K
pbThicken.m 17-Mar-2006 15:29 234
pbWrapper.m 17-Mar-2006 15:29 1.4K
segImage.m 17-Mar-2006 15:29 193
sp_demo.m 17-Mar-2006 15:29 1.3K
yu_imncut/ 17-Mar-2006 15:29 -
Code to compute superpixels.
by Greg Mori http://www.cs.sfu.ca/~mori/research/superpixels
The idea of superpixels was originally developed by Xiaofeng Ren and
Jitendra Malik . This implementation is different, and is a
version of that used in ,.
Basically, it is just a wrapper around Stella Yu's cncut code. David
Martin and Charless Fowlkes' boundary detector is used to provide an
edge map with which the "intervening contour" grouping cue is
Instructions for use:
- Run mex on *.c in yu_imncut directory
- Obtain mfm-pb boundary detector code from
- Change path names in sp_demo.m and pbWrapper.m
- Get a fast processor and lots of RAM
- Run sp_demo.m
 X. Ren and J. Malik. Learning a classification model for
segmentation. In Proc. 9th Int. Conf. Computer Vision, volume 1, pages
 G. Mori, X. Ren, A. Efros, and J. Malik, Recovering Human Body
Configurations: Combining Segmentation and Recognition, IEEE Computer
Vision and Pattern Recognition, 2004.
 G. Mori, Guiding Model Search Using Segmentation, IEEE
International Conference on Computer Vision, 2005.
 D. Martin, C. Fowlkes, and J. Malik, Learning to find brightness
and texture boundaries in natural images, NIPS, 2002.