Multiple pattern classification by sparse subspace decomposition

TL;DR

This paper introduces a robust classification method based on sparse subspace decomposition, enabling simultaneous classification of multiple queries by decomposing data into class-specific subspaces, achieving high accuracy and robustness.

Contribution

It proposes a novel sparse subspace decomposition approach for multi-class classification that handles multiple queries simultaneously with a practical greedy algorithm.

Findings

High recognition rate achieved

Robust performance demonstrated

Effective joint sparsity exploitation

Abstract

A robust classification method is developed on the basis of sparse subspace decomposition. This method tries to decompose a mixture of subspaces of unlabeled data (queries) into class subspaces as few as possible. Each query is classified into the class whose subspace significantly contributes to the decomposed subspace. Multiple queries from different classes can be simultaneously classified into their respective classes. A practical greedy algorithm of the sparse subspace decomposition is designed for the classification. The present method achieves high recognition rate and robust performance exploiting joint sparsity.