文件列表:

matlab\GCO_BuildLib.m (2522, 2010-04-27)
matlab\GCO_ComputeEnergy.m (387, 2009-10-27)
matlab\GCO_Create.m (526, 2010-04-26)
matlab\GCO_Delete.m (223, 2010-04-13)
matlab\GCO_ExpandOnAlpha.m (303, 2009-10-27)
matlab\GCO_Expansion.m (1091, 2010-04-28)
matlab\GCO_GetLabeling.m (670, 2009-10-27)
matlab\GCO_ListHandles.m (370, 2010-04-13)
matlab\GCO_LoadLib.m (378, 2010-04-26)
matlab\gco_matlab.cpp (18532, 2010-04-28)
matlab\GCO_SetDataCost.m (2068, 2010-04-23)
matlab\GCO_SetLabelCost.m (1695, 2010-04-23)
matlab\GCO_SetLabeling.m (787, 2010-04-23)
matlab\GCO_SetLabelOrder.m (607, 2010-04-22)
matlab\GCO_SetNeighbors.m (1198, 2010-04-20)
matlab\GCO_SetSmoothCost.m (1380, 2010-04-23)
matlab\GCO_SetVerbosity.m (1155, 2010-04-26)
matlab\GCO_Swap.m (702, 2010-04-19)
matlab\GCO_UnitTest.m (16580, 2010-04-28)
matlab\bin\gco_matlab.mexw32 (73728, 2010-06-07)
matlab\MyTest.m (1501, 2010-06-07)
matlab\MyTest.asv (1719, 2010-06-07)
matlab\bin (0, 2010-06-07)
matlab (0, 2010-06-04)

/************************************************************************************** GCO_MATLAB - a Matlab wrapper for Olga Veksler's C++ graph-cut optimization library GCO_MATLAB Author(s): Andrew Delong Anton Osokin We're especially grateful to Lena Gorelick for helpful suggestions and for helping us fix so many bugs! GCoptimization Author(s): Olga Veksler Description: This download provides a Matlab wrapper for the latest version of 'GCoptimization', Olga Veksler's multi-label optimization library written in C++. Note: A wrapper for an earlier version GCoptimization was authored by Shai Bagon and is available at http://www.wisdom.weizmann.ac.il/~bagon/matlab.html Revision History: Apr 25, 2010; - Faster code path for sparse data costs; fixed related bug in higher-order labels Apr 21, 2010; - Added basic "verbose" mode (print cycle, energy, timings etc) - Expansion cycles now focus on labels for which the energy decreased (faster) Apr 19, 2010; - Added sparse datacost support - Allow GCO_SetLabelOrder to specify exact label order Apr 13, 2010; - Potts model is now the default if SetNeighbors is called without SetSmoothCost - Fixed bug in higher-order label costs - Expansion is now interruptable from MATLAB; temporary memory is freed - Added GCO_ListHandles and allow GCO_Delete to accept multiple handles - Better error message if a bad handle is passed to GCO_* Nov 17, 2009; - Fixed integer overflow in label-cost construction - Fixed bug where greedy algorithm would sometimes skip a label Nov 6, 2009; - Fixed bug in re-setting label costs after Expansion - Fixed bug in GCO_LoadLib Oct 27, 2009; - Removed support for arbitrary smoothcost (too slow, hard to maintain) - Added support for re-setting data, smooth, and label costs after Expansion - Added support for label subset costs - Changed build process to directly use MEX command - Added integer overflow checks into GCoptimization - GCoptimization now uses maxflow-3.0 library Sep 12, 2009; - Added support for arbitrary smoothcost from Matlab via a function_handle - Added GCO_UnitTest - Build script now handles spaces in paths properly Aug 23, 2009; - First version for internal testing ***************************************************************************************/ 0. System Requirements - Matlab 7.4.0 (R2007a) or above for 32-bit. Matlab 7.6.0 (R2008) or above for ***-bit. - Mex must be pre-configured to use a C++ compiler. (Run "mex -setup" if you have not already.) The C++ code requires at least Visual C++ 2005 (VC8). ---------------------------------------------------------------------------------------- 1. Installation - The package should contain the following files: GCO_MATLAB files: gco\matlab\GCO_*.m ; the Matlab commands that you can run gco\matlab\gco_matlab.cpp ; the library that links Matlab to GCoptimization GCoptimization files: gco\*.{h,cpp} ; the GCoptimization C++ library - Start Matlab, and make gco\matlab your working directory or add it to your path. - To test your installation of GCO_MATLAB, run the GCO_UnitTest command. You should hopefully see output like below. >> GCO_UnitTest BuildLib PASSED LoadLib PASSED Create/Delete PASSED ... >> ---------------------------------------------------------------------------------------- 2. Getting Started -- A basic example, and important usage notes Once GCO_UnitTest passes, you should be able run the example sequence of commands below. >> h = GCO_Create(4,3); % Create new object with NumSites=4, NumLabels=3 >> GCO_SetDataCost(h,[0 9 2 0; % Sites 1,4 prefer label 1 3 0 3 3; % Site 2 prefers label 2 (strongly) 5 9 0 5;]); % Site 3 prefers label 3 >> GCO_SetSmoothCost(h,[0 1 2; % 1 0 1; % Linear (Total Variation) pairwise cost 2 1 0;]); % >> GCO_SetNeighbors(h,[0 1 0 0; % Sites 1 and 2 connected with weight 1 0 0 1 0; % Sites 2 and 3 connected with weight 1 0 0 0 2; % Sites 3 and 4 connected with weight 2 0 0 0 0;]); >> GCO_Expansion(h); % Compute optimal labeling via alpha-expansion >> GCO_GetLabeling(h) ans = 1 % Optimal labeling is (1,2,1,1) 2 1 1 >> [E D S] = GCO_ComputeEnergy(h) % Energy = Data Energy + Smooth Energy E = 4 D = 2 S = 2 >> GCO_Delete(h); % Delete the GCoptimization object when finished *** Before using the MATLAB wrapper, please note the following: *** - Sites and labels are identified with 1-based indices (i.e. 1..N and *not* 0..N-1) - All numeric costs must be INTEGER (int32), not float! (The "getting started" example above uses small float matrices, which are silently converted to int32 for the sake of convenience.) The only function that accepts floats is GCO_SetNeighbors, since it needs a sparse matrix. ** The weights themselves must still be integer valued!! ** (1.0, 17.0, 42.0 etc) ---------------------------------------------------------------------------------------- 3. GCO_MATLAB functions Run 'help' in MATLAB to see the documentation of each function, e.g. >> help GCO_SetSmoothCost Most of the GCO_MATLAB functions are one-to-one with the C++ methods in the GCoptimization library. For more detailed documentation, please refer to the C++ library itself. Relevant files are: gco_matlab\src\GCv3\GC_README.txt gco_matlab\src\GCv3\example.cpp gco_matlab\src\GCv3\GCoptimization.h gco_matlab\src\GCv3\LICENSE.txt

近期下载者：

相关文件：

评论：[我要评论] [举报此文件]

收藏者：