A New Manifold Distance Measure for Visual Object Categorization

TL;DR

This paper introduces a robust manifold distance measure based on CW-SSIM for visual object recognition, improving invariance to rotations and translations, and demonstrates its effectiveness in clustering tasks.

Contribution

The paper proposes a novel manifold distance using CW-SSIM that enhances robustness to image transformations for object categorization.

Findings

Outperforms traditional manifold distances in categorization accuracy

More robust to rotations and translations of images

Effective in clustering on multiple datasets

Abstract

Manifold distances are very effective tools for visual object recognition. However, most of the traditional manifold distances between images are based on the pixel-level comparison and thus easily affected by image rotations and translations. In this paper, we propose a new manifold distance to model the dissimilarities between visual objects based on the Complex Wavelet Structural Similarity (CW-SSIM) index. The proposed distance is more robust to rotations and translations of images than the traditional manifold distance and the CW-SSIM index based distance. In addition, the proposed distance is combined with the $k$-medoids clustering method to derive a new clustering method for visual object categorization. Experiments on Coil-20, Coil-100 and Olivetti Face Databases show that the proposed distance measure is better for visual object categorization than both the traditional manifold distances and the CW-SSIM index based distances.