Explaining Away Results in Accurate and Tolerant Template Matching

TL;DR

This paper introduces an explaining away probabilistic inference method for template matching in computer vision, improving robustness to appearance changes like occlusion and deformation, and demonstrating superior accuracy over existing methods.

Contribution

It applies explaining away inference to template matching, enhancing tolerance to appearance variations and achieving better accuracy than current state-of-the-art techniques.

Findings

Superior accuracy in image patch matching

Enhanced robustness to occlusion and deformation

First application of explaining away in this context

Abstract

Recognising and locating image patches or sets of image features is an important task underlying much work in computer vision. Traditionally this has been accomplished using template matching. However, template matching is notoriously brittle in the face of changes in appearance caused by, for example, variations in viewpoint, partial occlusion, and non-rigid deformations. This article tests a method of template matching that is more tolerant to such changes in appearance and that can, therefore, more accurately identify image patches. In traditional template matching the comparison between a template and the image is independent of the other templates. In contrast, the method advocated here takes into account the evidence provided by the image for the template at each location and the full range of alternative explanations represented by the same template at other locations and by other templates. Specifically, the proposed method of template matching is performed using a form of probabilistic inference known as "explaining away". The algorithm used to implement explaining away has previously been used to simulate several neurobiological mechanisms, and been applied to image contour detection and pattern recognition tasks. Here it is applied for the first time to image patch matching, and is shown to produce superior results in comparison to the current state-of-the-art methods.