Image Analysis Based on Nonnegative/Binary Matrix Factorization

TL;DR

This paper explores nonnegative/binary matrix factorization (NBMF) for facial image analysis, demonstrating its efficiency in image reconstruction and classification using the Fujitsu Digital Annealer, with faster convergence than traditional NMF.

Contribution

It introduces NBMF as an effective method for image analysis, highlighting its faster convergence and comparable classification performance to NMF.

Findings

NBMF achieves successful image reconstruction and classification.

NBMF converges faster than NMF in the analysis process.

Both NBMF and NMF perform similarly in classification accuracy.

Abstract

Using nonnegative/binary matrix factorization (NBMF), a matrix can be decomposed into a nonnegative matrix and a binary matrix. Our analysis of facial images, based on NBMF and using the Fujitsu Digital Annealer, leads to successful image reconstruction and image classification. The NBMF algorithm converges in fewer iterations than those required for the convergence of nonnegative matrix factorization (NMF), although both techniques perform comparably in image classification.