RSD-DOG : A New Image Descriptor based on Second Order Derivatives

TL;DR

This paper presents RSD-DOG, a novel image descriptor based on second order derivatives that captures complex surface features, demonstrating superior robustness and discriminative power over first order descriptors like SIFT and GLOH.

Contribution

The paper introduces RSD-DOG, a new image patch descriptor combining second order derivatives with Difference of Gaussian, enhancing robustness to various image variations.

Findings

Outperforms first order descriptors in image matching tasks.

Shows robustness to illumination, scale, rotation, blur, viewpoint, and compression.

Demonstrates improved discriminative power in experiments.

Abstract

This paper introduces the new and powerful image patch descriptor based on second order image statistics/derivatives. Here, the image patch is treated as a 3D surface with intensity being the 3rd dimension. The considered 3D surface has a rich set of second order features/statistics such as ridges, valleys, cliffs and so on, that can be easily captured by using the difference of rotating semi Gaussian filters. The originality of this method is based on successfully combining the response of the directional filters with that of the Difference of Gaussian (DOG) approach. The obtained descriptor shows a good discriminative power when dealing with the variations in illumination, scale, rotation, blur, viewpoint and compression. The experiments on image matching, demonstrates the advantage of the obtained descriptor when compared to its first order counterparts such as SIFT, DAISY, GLOH, GIST and LIDRIC.