VLFeat is an open source library that implements popular computer vision algorithms specializing in image understanding and local features extraction and matching, it 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.
G2 User in Computer Software
Advanced user of VLFeat
★★★★★
An extensive computer vision library
What do you like best?
Many good baselines for popular computer vision techniques such as SIFT and HOG, along with a good SVM implementation. Also good documentation.
What do you dislike?
Doesn't support more recent deep learning techniques (but see Matconvnet). Requires Matlab to use the high level APIs (or Octave, but this is less well supported).
Recommendations to others considering the product:
Good for baselines and reference implementations of popular computer vision methods.
What problems are you solving with the product? What benefits have you realized?
Extracting SIFT and HOG features as an object recognition baseline. Thin plate spline warps for data augmentation when training neural networks.
Review source: G2.com
