Kernel-based Generative Learning in Distortion Feature Space

TL;DR

This paper introduces a kernel-based generative classifier in a distortion feature space that improves character recognition performance and offers complementary strengths to discriminative classifiers, with potential for hybrid systems.

Contribution

A novel kernel-based generative classifier in a distortion subspace using polynomial series expansion, with an iterative kernel selection algorithm for enhanced performance.

Findings

Outperforms many existing classifiers in character recognition.

Exhibits different recognition capabilities compared to deep belief networks.

Hybrid methods further improve classification accuracy.

Abstract

This paper presents a novel kernel-based generative classifier which is defined in a distortion subspace using polynomial series expansion, named Kernel-Distortion (KD) classifier. An iterative kernel selection algorithm is developed to steadily improve classification performance by repeatedly removing and adding kernels. The experimental results on character recognition application not only show that the proposed generative classifier performs better than many existing classifiers, but also illustrate that it has different recognition capability compared to the state-of-the-art discriminative classifier - deep belief network. The recognition diversity indicates that a hybrid combination of the proposed generative classifier and the discriminative classifier could further improve the classification performance. Two hybrid combination methods, cascading and stacking, have been implemented to verify the diversity and the improvement of the proposed classifier.