The VLFeat open
source library implements popular computer vision algorithms
including
SIFT, MSER, k-means, hierarchical
k-means, agglomerative information bottleneck, and quick
shift. It is written in C for efficiency and compatibility,
with interfaces in MATLAB for ease of use, and detailed
documentation throughout. It supports
Windows, Mac OS X, and Linux. The latest version of
VLFeat is 0.9.14.
Download
|
Documentation
|
Tutorials
Example applications |
Citing
@misc{vedaldi08vlfeat,
Author = {A. Vedaldi and B. Fulkerson},
Title = {{VLFeat}: An Open and Portable Library
of Computer Vision Algorithms},
Year = {2008},
Howpublished = {\url{http://www.vlfeat.org/}}
Acknowledgments |
News
- 24/12/2011 VLFeat 0.9.14 released
- VLFeat 0.9.14 adds SLIC superpixels, improves the documentation, and contains other improvements and bugfixes. Furthermore, starting from this release VLFeat is distributed under the BSD license. [Details].
- 12/7/2011 VLFeat 0.9.13 released
- VLFeat 0.9.13 fixes the Windows binary package. [Details].
- 5/7/2011 VLFeat 0.9.12 released
- VLFeat 0.9.12 contains minor bugfixes. [Details].
- 19/6/2011 VLFeat 0.9.11 released
- VLFeat 0.9.11 solves a compatibility issue with old versions of Mac OS X and brings other minor bug fixes as well. [Details].
- 11/6/2011 VLFeat 0.9.10 released
- VLFeat 0.9.10 rolls out numerous bug fixes and improvements, especially to the homogeneous kernel map implementation. [Details].
- 28/10/2010 VLFeat wins the ACM Multimedia Open Source Awards!
- VLFeat 0.9.9 was awarded the ACM Multimedia Open Source Award 2010.
- 14/6/2010 VLFeat 0.9.9 released
- VLFeat 0.9.9 adds a new sample application (SIFT matching) and minor refinements. [Details].
- 14/6/2010 Open Source Vision Software Tutorial
- VLFeat presented at the CVPR 2010 Open Source Vision Software Tutorial. Slides of the presentation are available from the tutorial web page.
- 10/5/2010 VLFeat 0.9.8 released
- VLFeat 0.9.8 adds new tutorials, (hierarchical) k-means support for floating point data, homogeneous kernel maps, a basic implementation of PEGASOS for SVM learning, and many other improvements. [Details].