Affine Invariant, Model-Based Object Recognition Using Robust Metrics and Bayesian Statistics

TL;DR

This paper introduces an affine-invariant, model-based object recognition method that employs robust metrics and Bayesian statistics to improve robustness and applicability in general object matching tasks.

Contribution

It presents a novel approach combining a reformulated Huber metric with carefully chosen priors for affine-invariant object recognition.

Findings

Method is invariant to 2D affine transformations

Uses robust Huber metric for residuals

Suitable for general object matching

Abstract

We revisit the problem of model-based object recognition for intensity images and attempt to address some of the shortcomings of existing Bayesian methods, such as unsuitable priors and the treatment of residuals with a non-robust error norm. We do so by using a refor- mulation of the Huber metric and carefully chosen prior distributions. Our proposed method is invariant to 2-dimensional affine transforma- tions and, because it is relatively easy to train and use, it is suited for general object matching problems.