Learning Similarity for Character Recognition and 3D Object Recognition

TL;DR

This paper introduces a Bayesian-inspired approach to learn a similarity function for character and 3D object recognition, demonstrating its effectiveness through experimental results.

Contribution

It presents a novel Bayesian-based method for learning similarity functions applicable to character and 3D object recognition tasks.

Findings

Effective similarity function learned for character recognition

Successful application to 3D object recognition

Comparable or improved recognition accuracy

Abstract

I describe an approach to similarity motivated by Bayesian methods. This yields a similarity function that is learnable using a standard Bayesian methods. The relationship of the approach to variable kernel and variable metric methods is discussed. The approach is related to variable kernel Experimental results on character recognition and 3D object recognition are presented..