meanshift_seg
所属分类:图形图像处理
开发工具:matlab
文件大小:112KB
下载次数:417
上传日期:2012-03-04 12:12:08
上 传 者:
cailijun2010
说明: mean shift进行图像分割的matlab代码 非常好用 可直接对灰度或者彩色图像进行分割
(matlab code for image segmentation by mean shift)
文件列表:
mmeanshift_seg (0, 2007-12-20)
mmeanshift_seg\.#RGB2Luv.m (45, 2008-03-31)
mmeanshift_seg\.#test.m (45, 2008-03-31)
mmeanshift_seg\compile_edison_wrapper.m (483, 2007-12-20)
mmeanshift_seg\edison_wrapper.m (6072, 2007-12-20)
mmeanshift_seg\edison_wrapper_mex.cpp (8891, 2007-12-20)
mmeanshift_seg\edison_wrapper_mex.h (776, 2007-12-20)
mmeanshift_seg\edison_wrapper_mex.mexa64 (115147, 2007-12-20)
mmeanshift_seg\edison_wrapper_mex.mexglx (105137, 2007-12-20)
mmeanshift_seg\edison_wrapper_mex.mexw32 (49152, 2007-12-20)
mmeanshift_seg\Luv2RGB.m (765, 2007-12-20)
mmeanshift_seg\msfilt.m (1195, 2007-12-20)
mmeanshift_seg\msseg.m (1470, 2010-12-18)
mmeanshift_seg\RGB2Luv.m (798, 2007-12-20)
Welcome to the EDISON Wrapper for Matlab
The EDISON system contains the image segmentation/edge preserving filtering
algorithm described in the paper Mean shift: A robust approach toward feature
space analysis and the edge detection algorithm described in the paper Edge
detection with embedded confidence.
More information about EDISON (and the original codes) can be found here:
(http://www.caip.rutgers.edu/riul/research/code/EDISON/index.html)
This interface allows these codes to be run from Matlab using MEX files.
To use this wrapper, first run
>>compile_edison_wrapper
This will mex-ify all necessary codes. Then you can begin segmenting images.
Here are some sample calls:
>> %% This will load, segment, and display the "peppers" image
>> I = imread('peppers.png');
>> [fimg labels modes regsize grad conf] = edison_wrapper(I,@RGB2Luv);
>> imshow(Luv2RGB(fimg))
>> %% This sets some specific parameters and segments the gantrycrane image
>> I = imread('gantrycrane.png');
>> [fimg labels modes regsize grad conf] = edison_wrapper(I,@RGB2Luv,...
>> 'SpatialBandWidth',8,'RangeBandWidth',4,...
>> 'MinimumRegionArea',50);
>> subplot(2,1,1), imshow(I); subplot(2,1,2), imshow(Luv2RGB(fimg));
>> %% This performs filtering only the grayscale "cameraman" image
>> I = imread('cameraman.tif');
>> I = repmat(I,[1 1 3]);
>> [fimg labels modes regsize grad conf] = edison_wrapper(I,@RGB2Luv,...
>> 'steps', 1, 'SpatialBandWidth',8,'RangeBandWidth',4);
>> I = rgb2gray(Luv2RGB(fimg));
>> subplot(2,1,1), imshow(I); subplot(2,1,2), imshow(I);
近期下载者:
相关文件:
收藏者: