k Adjacent Segments detector v1.05

Vittorio Ferrari, Frederic Jurie, Cordelia Schmid


Matlab source code for the kAS local features detector. kAS are small groups of connected contour segments, forming paths through the Contour Segment Network of the image. Since each kAS has a well defined location, scale, and a descriptor invariant to translation and scale transformations, these features can be easily used for recognition and image matching.

This release covers the PAMI 2008 [1] paper.


Filename Description Size
kas_sources_V1.05.tgz Source code (Matlab) 2.6MB


New in v1.05

  • updated code to run correctly on Matlab R2014, due to the change of the semantics of ‘for’
  • changed test image to something more complex, so as to test the software fully
  • updaded README to reflect the change of test image (from blue.jpg to federer.jpg)

New in v1.04

  • corrected order of components of kAS descriptor in README
  • corrected Quickstart instructions in README

New in v1.03

  • includes routines to draw kAS overlaid on edgemaps
  • all pure matlab code

New in v1.02

  • documentation for all data-structures saved out in the Matlab file format. This enables access to detailed information about edgels, edgel-chains, contour segments, and kAS. For example, it is now possible to determine exactly which edgels belong to a kAS, which is useful for visualization, or for designing alternative descriptors.


  1. Groups of Adjacent Segments for Object Detection
    Vittorio Ferrari, Frederic Jurie, and Cordelia Schmid,
    In IEEE Transactions on Pattern Analysis and Machine Intelligence (PAMI), 2008.