NCsp
所属分类：图形图像处理
开发工具：matlab
文件大小：7174KB
下载次数：53
上传日期：2013-01-27 12:18:03
上 传 者：
bliss
说明： 一个非常有用的基于图的超像素算法，用于图像分割，使用时请添加目录
(a very useful superpixels algithn based on geraph theory, it can be used for image segmentation, please add file catalogue when used)
文件列表:
NC超像素\bear.jpg (30857, 2012-12-02)
NC超像素\boy.jpg (21868, 2012-12-02)
NC超像素\clusterLocations.asv (962, 2012-10-02)
NC超像素\clusterLocations.m (962, 2012-10-02)
NC超像素\dist2.m (888, 2006-03-18)
NC超像素\face.jpg (24657, 2012-12-02)
NC超像素\house.jpg (18556, 2012-12-02)
NC超像素\img70.jpg (25784, 2005-04-05)
NC超像素\imncut_sp.m (5140, 2012-12-04)
NC超像素\imncut_sp.m~ (5588, 2005-07-05)
NC超像素\kidman.jpg (258400, 2012-04-29)
NC超像素\learning a classification model for segmentation.pdf (582191, 2012-12-02)
NC超像素\lizard.jpg (37923, 2007-04-13)
NC超像素\menglalisha.bmp (479454, 2008-02-27)
NC超像素\MFM-boundaries.pdf (5371838, 2012-12-02)
NC超像素\pbThicken.m (234, 2005-04-05)
NC超像素\pbWrapper.m (1391, 2012-12-02)
NC超像素\segbench\Benchmark\affinityPRMI.m (2006, 2003-03-27)
NC超像素\segbench\Benchmark\benchNewAlg.m (1344, 2003-11-06)
NC超像素\segbench\Benchmark\boundaryBench.m (3655, 2003-11-04)
NC超像素\segbench\Benchmark\boundaryBenchGraphs.m (2220, 2003-11-13)
NC超像素\segbench\Benchmark\boundaryBenchGraphsHuman.m (2387, 2003-10-31)
NC超像素\segbench\Benchmark\boundaryBenchGraphsMulti.m (3398, 2003-11-06)
NC超像素\segbench\Benchmark\boundaryBenchHtml.m (15216, 2003-11-13)
NC超像素\segbench\Benchmark\boundaryBenchHuman.m (2664, 2003-07-04)
NC超像素\segbench\Benchmark\boundaryPR.m (2132, 2003-11-13)
NC超像素\segbench\Benchmark\boundaryPRfast.m (2520, 2004-06-23)
NC超像素\segbench\Benchmark\calcMI.m (806, 2003-02-02)
NC超像素\segbench\Benchmark\correspondPixels.cc (2171, 2003-11-01)
NC超像素\segbench\Benchmark\correspondPixels.m (1637, 2003-04-20)
NC超像素\segbench\Benchmark\demo.m (1307, 2003-11-01)
NC超像素\segbench\Benchmark\GNUmakefile (419, 2003-11-01)
NC超像素\segbench\Benchmark\match.cc (12024, 2003-04-01)
NC超像素\segbench\Benchmark\match.hh (280, 2003-01-31)
NC超像素\segbench\Benchmark\plotMatch.m (854, 2003-03-25)
NC超像素\segbench\Benchmark\testCorrespondPixels.m (760, 2003-11-01)
NC超像素\segbench\Benchmark\upsamplepb.m (289, 2003-04-20)
... ...
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 [1]. This implementation is different, and is a
version of that used in [2],[3].
Basically, it is just a wrapper around Stella Yu's cncut code. David
Martin and Charless Fowlkes' boundary detector[4] is used to provide an
edge map with which the "intervening contour" grouping cue is
computed.
Instructions for use:
- Run mex on *.c in yu_imncut directory
- Obtain mfm-pb boundary detector code from
http://www.cs.berkeley.edu/projects/vision/grouping/segbench/
- Change path names in sp_demo.m and pbWrapper.m
- Get a fast processor and lots of RAM
- Run sp_demo.m
References:
[1] X. Ren and J. Malik. Learning a classification model for
segmentation. In Proc. 9th Int. Conf. Computer Vision, volume 1, pages
10-17, 2003.
[2] G. Mori, X. Ren, A. Efros, and J. Malik, Recovering Human Body
Configurations: Combining Segmentation and Recognition, IEEE Computer
Vision and Pattern Recognition, 2004.
[3] G. Mori, Guiding Model Search Using Segmentation, IEEE
International Conference on Computer Vision, 2005.
[4] D. Martin, C. Fowlkes, and J. Malik, Learning to find brightness
and texture boundaries in natural images, NIPS, 2002.
近期下载者：
相关文件：
收藏者：