TY - JOUR
T1 - Image analysis based on nonnegative/binary matrix factorization
AU - Asaoka, Hinako
AU - Kudo, Kazue
N1 - Funding Information:
H.A. thanks the METI and IPA for their support through the MITOU Target program. This work was partially supported by the JSPS KAKENHI Grant Number JP18K11333.
Funding Information:
Acknowledgment H.A. thanks the METI and IPA for their support through the MITOU Target program. This work was partially supported by the JSPS KAKENHI Grant Number JP18K11333.
Publisher Copyright:
© 2020 The Physical Society of Japan.
PY - 2020/8
Y1 - 2020/8
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85090786321&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85090786321&partnerID=8YFLogxK
U2 - 10.7566/JPSJ.89.085001
DO - 10.7566/JPSJ.89.085001
M3 - Article
AN - SCOPUS:85090786321
VL - 89
JO - Journal of the Physical Society of Japan
JF - Journal of the Physical Society of Japan
SN - 0031-9015
IS - 8
M1 - 085001
ER -