Robust Topological Features
for Deformation Invariant Image Matching

 

Local photometric descriptors are a crucial low level component of numerous computer vision algorithms. In practice, these descriptors are constructed to be invariant to a class of transformations. However, the development of a descriptor that is simultaneously robust to noise and invariant under general deformation has proven difficult. In this paper, we introduce the Topological-Attributed Relational Graph (T-ARG), a new local photometric descriptor constructed from homology that is provably invariant to locally bounded deformation. This new robust topological descriptor is backed by a formal mathematical framework. We apply T-ARG to a set of benchmark images to evaluate its performance. Results indicate that T-ARG significantly outperforms traditional descriptors for noisy, deforming images.


  • E. Lobaton, R. Vasudevan, R. Alterovitz, and R. Bajcsy, "Robust Topological Features for Deformation Invariant Image Matching," International Conference on Computer Vision (ICCV), Spain, 2011. [PDF]
  • E. Lobaton, R. Vasudevan, R. Alterovitz, and R. Bajcsy. "Robust Topological Features for Deformation Invariant Image Matching," Technical Report UCB/EECS-2011-89, EECS Dept., University of California, Berkeley, Aug 2011. [PDF]

General Deformation Analysis:


     

The following are links to the datasets, scripts and executables used for generating the results in section 6.1 of the paper.

Homography Deformation Analysis:


     

The following are links to the datasets, scripts and executables used for generating the results in section 6.2 of the paper.