« View All Resources

Andrea Vedaldis's open source contributions: SIFT and MSER implementations, bag-of-words code, etc.

Computer Vision Central - Posted on December 11, 2011 at 3:59 pm.

  • Links: http://www.vlfeat.org/~vedaldi/code/code.html
  • Details:
  • This page contains a selection of my open source contributions. Additional code related to specific publications can be found in the publications page.

    Research

    VLFeat

    VLFeat is an open source library of implementations of popular computer vision algorithms in a simple-to-use package with MATLAB bindings. It bundles algorithms such as SIFT, MSER, k-means, hierarchical k-means, kd-trees, agglomerative information bottleneck, quick shift.

    VGG MKL

    VGG MKL is an implementation of multiple kernel learning for image classification. An extended version of this code was used to implement one of the two best performing methods in the VOC 2009 PASCAL detection challenge.

    svm-struct-matlab is a MATLAB wrapper of T. Joachims's SVMstruct.It simplifies coding your SVMstruct instance by means of simple MATLAB function callbacks.

    VLPov is a package to extract depth map and camera parameter from POV-Ray 3-D scenes.

     

    Education

    This page contains pointers to a number of educational implementations of intersting algorithms (e.g. SVM).

     

    Utilities

    Autorights is a companion script that can be used to automatically extracted formatted HTML documentation from the comments embedded in a set of M-Files. Text is automatically structured by using a symple and natural syntax in the comments.

    Anaview is a MATLAB function to generate anaglyphs from MATLAB figures.

     

    Legacy

    Legacy SIFT and MSER implementations. SIFT and SIFT++ are respectively a MATLAB/C and command line/C++ implementation of the SIFT feature detector and descriptor. MSER is a MATLAB/C implementation of the MSER detector. All this is superseded by VLFeat.

    Legacy bag-of-words code. Bag is a MATLAB implementation of a bag-of-feature algorithm for object category recognition.


    k();} ?>