ACM OpenSource Award

The VLFeat open source library implements popular computer vision algorithms specializing in image understanding and local features extraction and matching. Algorithms include Fisher Vector, VLAD, SIFT, MSER, k-means, hierarchical k-means, agglomerative information bottleneck, SLIC superpixels, quick shift superpixels, large scale SVM training, and many others. 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 0.9.20.

Download

Documentation

MATLAB commands
C API with algorithm descriptions
Command line tools

Tutorials

Features: Covariant detectors, HOG, SIFT, MSER, Quick shift, SLIC
Clustering: IKM, HIKM, AIB
Matching: Randomized kd-trees
All 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

UCLA Vision Lab Oxford VGG.

News

14/1/2015 VLFeat 0.9.20 released: Maintenance release. Bugfixes.
12/9/1014 MatConvNet: Looking for an easy-to-use package to work with deep convolutional neural networks in MATLAB? Check out our new MatConvNet toolbox!
12/9/2014 VLFeat 0.9.19 released: Maintenance release. Minor bugfixes and fixes compilation with MATLAB 2014a.
29/01/2014 VLFeat 0.9.18 released: Several bugfixes. Improved documentation, particularly of the covariant detectors. Minor enhancements of the Fisher vectors. [Details]
22/06/2013 VLFeat 0.9.17 released: Rewritten SVM implementation, adding support for SGD and SDCA optimizers and various loss functions (hinge, squared hinge, logistic, etc.) and improving the interface. Added infrastructure to support multi-core computations using OpenMP. Added OpenMP support to KD-trees and KMeans. Added new Gaussian Mixture Models, VLAD encoding, and Fisher Vector encodings (also with OpenMP support). Added LIOP feature descriptors. Added new object category recognition example code, supporting several standard benchmarks off-the-shelf. This is the third point update supported by the PASCAL Harvest programme. [Details]
01/10/2012 VLBenchmarks 1.0-beta released.: This new project provides simple to use benchmarking code for feature detectors and descriptors. Its development was supported by the PASCAL Harvest programme. [Details]
01/10/2012 VLFeat 0.9.16 released: Added VL_COVDET() (covariant feature detector). This function implements the following detectors: DoG, Hessian, Harris Laplace, Hessian Laplace, Multiscale Hessian, Multiscale Harris. It also implements affine adaptation, estimation of feature orientation, computation of descriptors on the affine patches (including raw patches), and sourcing of custom feature frame. Added the auxiliary function VL_PLOTSS(). This is the second point update supported by the PASCAL Harvest programme. [Details]
11/9/2012 VLFeat 0.9.15 released: Added VL_HOG() (HOG features). Added VL_SVMPEGASOS() and a vastly improved SVM implementation. Added IHASHSUM (hashed counting). Improved INTHIST (integral histogram). Added VL_CUMMAX(). Improved the implementation of VL_ROC() and VL_PR(). Added VL_DET() (Detection Error Trade-off (DET) curves). Improved the verbosity control to AIB. Added support for Xcode 4.3, improved support for past and future Xcode versions. Completed the migration of the old test code in toolbox/test, moving the functionality to the new unit tests toolbox/xtest. Improved credits. This is the first point update supported by the PASCAL Harvest (several more to come shortly). A big thank to our sponsor! [Details].
10/1/2012 PASCAL2 Harvest funding: In the upcoming months many new functionalities will be added to VLFeat thanks to the PASCAL Harvest! See here for details.

VLFeat.org