A Hierarchical Non-Parametric Method for Capturing Non-Rigid Deformations

We present a novel approach for measuring image similarity based on the composition of parts. The measure identifies common subregions between the images at multiple sizes, and evaluates the amount of deformation required to align the common regions. The scheme allows complex, non-rigid deformation of the images, and penalizes irregular deformations more than coherent shifts of larger sub-parts. The measure is implemented by an algorithm which is a variant of dynamic programming, extended to multi-dimensions, and is using scores measured on a relative scale. The similarity measure is shown to be robust to non-rigid deformations of parts at various positions and scales, and to capture basic characteristics of human similarity judgments. Ó 2008 Published by Elsevier B.V.

• Type: Conference
• Year: 2005
• Where: CRV
• Authors: Ady Ecker, Shimon Ullman
• Keywords: CRV 2005, Image Similarity, Non-rigid Deformations, Penalizes Irregular Deformations, Robotics