Description:

The framework includes a wide range of standard machine learning and graphical models algorithms as well as reference implementations for common applications particularly in computer vision. It also includes Matlab wrappers for many components of the library and an experimental GUI for designing machine learning data flows.

Changes to previous version:

Version 1.9:

• Replaced drwnInPaint class with drwnImageInPainter class and added inPaint application
• Added function to read CIFAR-10 and CIFAR-100 style datasets (see http://www.cs.utoronto.ca/~kriz/cifar.html)
• Added drwnMaskedPatchMatch, drwnBasicPatchMatch, drwnSelfPatchMatch and basicPatchMatch application
• drwnPatchMatchGraph now allows multiple matches to the same image
• Upgraded wxWidgets to 3.0.2 (problems on Mac OS X)
• Switched Mac OS X compilation to libc++ instead of libstdc++
• Added Python scripts for running experiments and regression tests
• Refactored drwnGrabCutInstance class to support both GMM and colour histogram model
• Added cacheSortIndex to drwnDecisionTree for trading-off speed versus memory usage
• Added mexLoadPatchMatchGraph for loading drwnPatchMatchGraph objects into Matlab
• Improved documentation, other bug fixes and performance improvements

BibTeX Entry: Download

Corresponding Paper BibTeX Entry: Download

Supported Operating Systems: Linux, Windows, Mac Os X

Data Formats: Agnostic

Tags: Machine Learning, Graphical Models, Computer Vision

Archive: download here

Other available revisons

Version	Changelog	Date
1.9	Version 1.9: Replaced drwnInPaint class with drwnImageInPainter class and added inPaint application Added function to read CIFAR-10 and CIFAR-100 style datasets (see http://www.cs.utoronto.ca/~kriz/cifar.html) Added drwnMaskedPatchMatch, drwnBasicPatchMatch, drwnSelfPatchMatch and basicPatchMatch application drwnPatchMatchGraph now allows multiple matches to the same image Upgraded wxWidgets to 3.0.2 (problems on Mac OS X) Switched Mac OS X compilation to libc++ instead of libstdc++ Added Python scripts for running experiments and regression tests Refactored drwnGrabCutInstance class to support both GMM and colour histogram model Added cacheSortIndex to drwnDecisionTree for trading-off speed versus memory usage Added mexLoadPatchMatchGraph for loading drwnPatchMatchGraph objects into Matlab Improved documentation, other bug fixes and performance improvements	September 8, 2015, 06:50:37
1.8	Version 1.8: Added Superpixel Graph Label Transfer (nnGraph) Project project Added Python scripts for automating some projects Added ability to pre-process features on-the-fly with one drwnFeatureTransform when applying or learning another drwnFeatureTransform Fixed race condition in Windows threading (thanks to Edison Guo) Switched Windows and Linux to build against OpenCV 2.4.9 Changed drwnMAPInference::inference to return upper and lower energy bounds Added pruneRounds function to drwnBoostedClassifier Added drwnSLICSuperpixels function Added drwnIndexQueue class mexLearnClassifier and mexAnalyseClassifier now support integer label types Bug fix in mexSaveSuperpixels to support single channel	September 3, 2014, 08:42:53
1.7	Version 1.7: Log file now shows the command line Utility application added for viewing multi-class segmentation legend Added LBP filter response features to multi-class segmentation model Added drwnColourHistogram class Added k-means segmentation method for creating superpixels Application visualizeSuperpixels and mex routines for loading and saving superpixels Improved mex parsing of Matlab objects to support more matrix types Bug fix in drwnOptimizer (thanks to Subarna Tripathi) Updated copyright notice to 2007-2014 Other bug fixes and performance improvements Version 1.6.1: Maximum size of drwnShowDebuggingImage can be set from command line Windows MSVC projects updated to link against OpenCV 2.4.6 Fixes for gcc 4.7 (thanks to Sarma Tangirala) Bug fixes and performance improvements Version 1.6: Changed vision code from OpenCV 1.x C API to OpenCV 2.x C++ API Added drwnHistogram class by Jason Corso Added separate EPSG, EPSF and EPSX parameters to drwnOptimizer and changed signature of solve function Added "-outUnary" option to inferPixelLabels for writing out unary potentials Improved Matlab mex interfaces Added drwnFeatureTransformFactory and improved drwnFactory class Added drwnLinearTransform class Bug fixes and performance improvements	January 10, 2014, 01:33:01
1.6.1	Version 1.6.1: Maximum size of drwnShowDebuggingImage can be set from command line Windows MSVC projects updated to link against OpenCV 2.4.6 Fixes for gcc 4.7 (thanks to Sarma Tangirala) Bug fixes and performance improvements Version 1.6: Changed vision code from OpenCV 1.x C API to OpenCV 2.x C++ API Added drwnHistogram class by Jason Corso Added separate EPSG, EPSF and EPSX parameters to drwnOptimizer and changed signature of solve function Added "-outUnary" option to inferPixelLabels for writing out unary potentials Improved Matlab mex interfaces Added drwnFeatureTransformFactory and improved drwnFactory class Added drwnLinearTransform class Bug fixes and performance improvements Version 1.5.1: Bug fixes and performance improvements in drwnPCA and drwnKMeans Version 1.5: Win32 threading implementation (drwnThreadPool) Added standard command line option for setting random seed Made drwnPersistentStorage thread safe (on Linux and Mac OS X) Added drwnAverageRegions function Added fast superpixel code (drwnFastSuperpixels) Implemented drwnPersistentRecord interface for drwnSuperpixelContainer Enhanced drwnSuperpixelContainer with additional member functions Added image inpainting routines (drwnInPaint) Bug fixes and performance improvements	August 27, 2013, 06:23:04
1.6	Version 1.6: Changed vision code from OpenCV 1.x C API to OpenCV 2.x C++ API Added drwnHistogram class by Jason Corso Added separate EPSG, EPSF and EPSX parameters to drwnOptimizer and changed signature of solve function Added "-outUnary" option to inferPixelLabels for writing out unary potentials Improved Matlab mex interfaces Added drwnFeatureTransformFactory and improved drwnFactory class Added drwnLinearTransform class Bug fixes and performance improvements Version 1.5.1: Bug fixes and performance improvements in drwnPCA and drwnKMeans Version 1.5: Win32 threading implementation (drwnThreadPool) Added standard command line option for setting random seed Made drwnPersistentStorage thread safe (on Linux and Mac OS X) Added drwnAverageRegions function Added fast superpixel code (drwnFastSuperpixels) Implemented drwnPersistentRecord interface for drwnSuperpixelContainer Enhanced drwnSuperpixelContainer with additional member functions Added image inpainting routines (drwnInPaint) Bug fixes and performance improvements	June 18, 2013, 07:39:41
1.5.1	Version 1.5.1: Bug fixes and performance improvements in drwnPCA and drwnKMeans Version 1.5: Win32 threading implementation (drwnThreadPool) Added standard command line option for setting random seed Made drwnPersistentStorage thread safe (on Linux and Mac OS X) Added drwnAverageRegions function Added fast superpixel code (drwnFastSuperpixels) Implemented drwnPersistentRecord interface for drwnSuperpixelContainer Enhanced drwnSuperpixelContainer with additional member functions Added image inpainting routines (drwnInPaint) Bug fixes and performance improvements Version 1.4: dense and sparse linear program solver upgraded to Eigen 3.1.1 sparse dot product thread safe persistent storage improved installation documentation bug fixes and performance improvements	March 31, 2013, 00:07:57
1.5	Version 1.5: Win32 threading implementation (drwnThreadPool) Added standard command line option for setting random seed Made drwnPersistentStorage thread safe (on Linux and Mac OS X) Added drwnAverageRegions function Added fast superpixel code (drwnFastSuperpixels) Implemented drwnPersistentRecord interface for drwnSuperpixelContainer Enhanced drwnSuperpixelContainer with additional member functions Added image inpainting routines (drwnInPaint) Bug fixes and performance improvements Version 1.4: dense and sparse linear program solver upgraded to Eigen 3.1.1 sparse dot product thread safe persistent storage improved installation documentation bug fixes and performance improvements	February 12, 2013, 03:22:40
1.4	Version 1.4: dense and sparse linear program solver upgraded to Eigen 3.1.1 sparse dot product thread safe persistent storage improved installation documentation bug fixes and performance improvements Version 1.3.x: improved performance of multi-class image segmentation (about 3% higher on MSRC) implementation of the PatchMatch algorithm (Barnes et al., ECCV 2010) implementation of the PatchMatchGraph data structure and label transfer (Gould and Zhang, ECCV 2012) mex interface to max-flow algorithm XML code tidy up improved user documentation bug fixes and performance enhancements	December 1, 2012, 11:46:17
1.3.2	Version 1.3.2: improved performance of multi-class image segmentation (about 3% higher on MSRC) Version 1.3: implementation of the PatchMatch algorithm (Barnes et al., ECCV 2010) implementation of the PatchMatchGraph data structure and label transfer (Gould and Zhang, ECCV 2012) mex interface to max-flow algorithm XML code tidy up improved user documentation bug fixes and performance enhancements	October 16, 2012, 04:01:31
1.3.1	implementation of the PatchMatch algorithm (Barnes et al., ECCV 2010) implementation of the PatchMatchGraph data structure and label transfer (Gould and Zhang, ECCV 2012) mex interface to max-flow algorithm XML code tidy up improved user documentation bug fixes and performance enhancements	September 24, 2012, 03:44:09
1.2	improved user documentation switched to RapidXML for XML parsing added features: drwnRemoveFile, drwnDataset::subSample, drwnConnectedComponents bug fixes and performance enhancements	August 22, 2012, 06:22:44
1.1.3	Version 1.1.3: fixed bug in compressed drwnPersistentStorage Version 1.1.2: fixed bug in writing drwnCompositeClassifier Version 1.1.1: fixed bug in PCA and Fisher LDA modules for non-zero mean data Version 1.1: changed from Eigen 2.0.17 to Eigen 3.0.5 changed from OpenCV 2.1 to OpenCV 2.4 added k-means clustering class experimental GUI now works on Linux, Mac OS X and Win32 bug fixes and performance enhancements	August 13, 2012, 09:52:37
1.1.1	Version 1.1.1: fixed bug in PCA and Fisher LDA modules for non-zero mean data Version 1.1: changed from Eigen 2.0.17 to Eigen 3.0.5 changed from OpenCV 2.1 to OpenCV 2.4 added k-means clustering class experimental GUI now works on Linux, Mac OS X and Win32 bug fixes and performance enhancements	July 5, 2012, 01:41:42
1.1	Version 1.1: changed from Eigen 2.0.17 to Eigen 3.0.5 changed from OpenCV 2.1 to OpenCV 2.4 added k-means clustering class experimental GUI now works on Linux, Mac OS X and Win32 bug fixes and performance enhancements Version 1.0.2: fixed bug in matlab factor graph inference mac osx install fix windows debug mode compilation fix experimental gui (linux only) removed factory auto-register documentation improvements composite classifier bug fixes and performance enhancements	June 25, 2012, 01:30:07
1.0.2	Version 1.0.2: fixed bug in matlab factor graph inference Version 1.0.1: mac osx install fix windows debug mode compilation fix Version 1.0: experimental gui (linux only) removed factory auto-register documentation improvements composite classifier bug fixes and performance enhancements	May 16, 2012, 02:02:27
1.0.1	Version 1.0.1: - mac osx install fix - windows debug mode compilation fix Version 1.0: - experimental gui (linux only) - removed factory auto-register - documentation improvements - composite classifier - bug fixes and performance enhancements	May 2, 2012, 01:52:04
1.0	experimental gui removed factory auto-register documentation improvements composite classifier bug fixes and performance enhancements	April 12, 2012, 02:34:28
0.9	0.9: thread safety on image cache image pyramid cache improvements to multi-class segmentation pipeline changes to persistent records; persistent record manager and buffer bug fixes and performance enhancements 0.8.1: fixed loading empty matrix bug 0.8: dynamic libraries on Mac OS X classifier meta-parameter cross-validator image cache row and column pixel features for image labeling Meshi and Globerson's ADMM inference code (ECML 2011)	March 20, 2012, 23:39:36
0.8.1	0.8.1: - fixed loading empty matrix bug 0.8: - dynamic libraries on Mac OS X - classifier meta-parameter cross-validator - image cache - row and column pixel features for image labeling - Meshi and Globerson's ADMM inference code (ECML 2011)	February 9, 2012, 03:07:44
0.8	dynamic libraries on Mac OS X classifier meta-parameter cross-validator image cache row and column pixel features for image labeling Meshi and Globerson's ADMM inference code (ECML 2011)	January 4, 2012, 00:22:47
0.7.1	fixed Mac OS X compilation bug	December 20, 2011, 23:57:24
0.7	Initial Announcement on mloss.org.	December 15, 2011, 18:37:58

Comments

Honglin Yu (on May 10, 2012, 08:08:34)

I met one error when install the wxWidget by install.sh: the configure.h can not find opengl on my computer. I use ubuntu 12.04 64bit. After some google, I found it is because "apt" on my computer puts "mesa folder" into "/usr/lib/x86_64-linux-gnu/". Then I use the following method to fix this error: 1. Open the file "wxGTK-2.8.12/configure". 2. Go to line 25062 and add "/usr/lib/x86_64-linux-gnu/" to the tail of the micro "SEARCH_LIB". 3. Then use "install.sh wxWidgets" again, and everything works fine. Hope this helps.

Leave a comment

You must be logged in to post comments.