Classification with Incoherent Kernel Dictionary Learning

TL;DR

This paper introduces a kernel-based incoherent dictionary learning method for classification, improving the AK-SVD algorithm and demonstrating effectiveness on multiple datasets.

Contribution

It presents a novel kernel version of incoherent dictionary learning and an improved AK-SVD algorithm for better representation updates.

Findings

Effective classification on multiple datasets

Improved AK-SVD algorithm performance

Kernel incoherent DL outperforms linear methods

Abstract

In this paper we present a new classification method based on Dictionary Learning (DL). The main contribution consists of a kernel version of incoherent DL, derived from its standard linear counterpart. We also propose an improvement of the AK-SVD algorithm concerning the representation update. Our algorithms are tested on several popular databases of classification problems.