Benchmarking KAZE and MCM for Multiclass Classification

TL;DR

This paper introduces a new feature fusion method combining KAZE and SIFT features with MCM for multiclass classification, demonstrating improved performance over existing methods.

Contribution

It proposes a novel fusion of KAZE and SIFT features with MCM, showing enhanced classification accuracy in multiclass tasks.

Findings

Fusion of KAZE and SIFT features outperforms state-of-the-art methods.

Elementary integration of features improves classification results.

KAZE and SIFT features are complementary for object classification.

Abstract

In this paper, we propose a novel approach for feature generation by appropriately fusing KAZE and SIFT features. We then use this feature set along with Minimal Complexity Machine(MCM) for object classification. We show that KAZE and SIFT features are complementary. Experimental results indicate that an elementary integration of these techniques can outperform the state-of-the-art approaches.