Robust Topological Features for Deformation Invariant Image Matching

Authors:
Lobaton, Edgar J.
Vasudevan, Ram
Alterovitz, Ron
Bajcsy, Ruzena
Technical Report Identifier: EECS-2011-89
August 5, 2011
EECS-2011-89.pdf

Abstract: 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.