A New Distance Measure for Non-Identical Data with Application to Image Classification

TL;DR

This paper introduces a novel distance measure called Poisson-Binomial Radius (PBR) that accounts for non-identical distributions in feature data, improving image classification accuracy across diverse datasets.

Contribution

The paper proposes the PBR distance measure that models non-identical feature distributions, addressing a key limitation in existing distance metrics for image analysis.

Findings

PBR outperforms existing distance measures on most benchmark datasets.

PBR achieves comparable performance on datasets where other measures excel.

Accounting for non-identical distributions enhances classification accuracy.

Abstract

Distance measures are part and parcel of many computer vision algorithms. The underlying assumption in all existing distance measures is that feature elements are independent and identically distributed. However, in real-world settings, data generally originate from heterogeneous sources even if they do possess a common data-generating mechanism. Since these sources are not identically distributed by necessity, the assumption of identical distribution is inappropriate. Here, we use statistical analysis to show that feature elements of local image descriptors are indeed non-identically distributed. To test the effect of omitting the unified distribution assumption, we created a new distance measure called the Poisson-Binomial Radius (PBR). PBR is a bin-to-bin distance which accounts for the dispersion of bin-to-bin information. PBR's performance was evaluated on twelve benchmark data sets covering six different classification and recognition applications: texture, material, leaf, scene, ear biometrics and category-level image classification. Results from these experiments demonstrate that PBR outperforms state-of-the-art distance measures for most of the data sets and achieves comparable performance on the rest, suggesting that accounting for different distributions in distance measures can improve performance in classification and recognition tasks.