VLFeat Library implements popular computer vision algorithms specialising 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, with interface in MATLAB. Though there exists Pyvlfeat, it does not contain all the functions. That’s why, I decided to improve it as a GSOC project under Portland State University. A Python Interface will make this robust library accessible to the open source computer vision community as a replacement to proprietary tools like MATLAB.

The Matlab version of VLFeat is open source. The project is well documented too. So It’ll help me to develop at much faster pace.




  • Simon N.