Face recognition using sparse representation-based classification on k-nearest subspace.

The sparse representation-based classification (SRC) has been proven to be a robust face recognition method. However, its computational complexity is very high due to solving a complex l(1)-minimization problem. To improve the calculation efficiency, we propose a novel face recognition method, calle...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Jian-Xun Mi, Jin-Xing Liu
Formato: article
Lenguaje:EN
Publicado: Public Library of Science (PLoS) 2013
Materias:
R
Q
Acceso en línea:https://doaj.org/article/93ba2e9144884899b42f25eb2b073b22
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:93ba2e9144884899b42f25eb2b073b22
record_format dspace
spelling oai:doaj.org-article:93ba2e9144884899b42f25eb2b073b222021-11-18T07:52:01ZFace recognition using sparse representation-based classification on k-nearest subspace.1932-620310.1371/journal.pone.0059430https://doaj.org/article/93ba2e9144884899b42f25eb2b073b222013-01-01T00:00:00Zhttps://www.ncbi.nlm.nih.gov/pmc/articles/pmid/23555671/?tool=EBIhttps://doaj.org/toc/1932-6203The sparse representation-based classification (SRC) has been proven to be a robust face recognition method. However, its computational complexity is very high due to solving a complex l(1)-minimization problem. To improve the calculation efficiency, we propose a novel face recognition method, called sparse representation-based classification on k-nearest subspace (SRC-KNS). Our method first exploits the distance between the test image and the subspace of each individual class to determine the k nearest subspaces and then performs SRC on the k selected classes. Actually, SRC-KNS is able to reduce the scale of the sparse representation problem greatly and the computation to determine the k nearest subspaces is quite simple. Therefore, SRC-KNS has a much lower computational complexity than the original SRC. In order to well recognize the occluded face images, we propose the modular SRC-KNS. For this modular method, face images are partitioned into a number of blocks first and then we propose an indicator to remove the contaminated blocks and choose the k nearest subspaces. Finally, SRC is used to classify the occluded test sample in the new feature space. Compared to the approach used in the original SRC work, our modular SRC-KNS can greatly reduce the computational load. A number of face recognition experiments show that our methods have five times speed-up at least compared to the original SRC, while achieving comparable or even better recognition rates.Jian-Xun MiJin-Xing LiuPublic Library of Science (PLoS)articleMedicineRScienceQENPLoS ONE, Vol 8, Iss 3, p e59430 (2013)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Jian-Xun Mi
Jin-Xing Liu
Face recognition using sparse representation-based classification on k-nearest subspace.
description The sparse representation-based classification (SRC) has been proven to be a robust face recognition method. However, its computational complexity is very high due to solving a complex l(1)-minimization problem. To improve the calculation efficiency, we propose a novel face recognition method, called sparse representation-based classification on k-nearest subspace (SRC-KNS). Our method first exploits the distance between the test image and the subspace of each individual class to determine the k nearest subspaces and then performs SRC on the k selected classes. Actually, SRC-KNS is able to reduce the scale of the sparse representation problem greatly and the computation to determine the k nearest subspaces is quite simple. Therefore, SRC-KNS has a much lower computational complexity than the original SRC. In order to well recognize the occluded face images, we propose the modular SRC-KNS. For this modular method, face images are partitioned into a number of blocks first and then we propose an indicator to remove the contaminated blocks and choose the k nearest subspaces. Finally, SRC is used to classify the occluded test sample in the new feature space. Compared to the approach used in the original SRC work, our modular SRC-KNS can greatly reduce the computational load. A number of face recognition experiments show that our methods have five times speed-up at least compared to the original SRC, while achieving comparable or even better recognition rates.
format article
author Jian-Xun Mi
Jin-Xing Liu
author_facet Jian-Xun Mi
Jin-Xing Liu
author_sort Jian-Xun Mi
title Face recognition using sparse representation-based classification on k-nearest subspace.
title_short Face recognition using sparse representation-based classification on k-nearest subspace.
title_full Face recognition using sparse representation-based classification on k-nearest subspace.
title_fullStr Face recognition using sparse representation-based classification on k-nearest subspace.
title_full_unstemmed Face recognition using sparse representation-based classification on k-nearest subspace.
title_sort face recognition using sparse representation-based classification on k-nearest subspace.
publisher Public Library of Science (PLoS)
publishDate 2013
url https://doaj.org/article/93ba2e9144884899b42f25eb2b073b22
work_keys_str_mv AT jianxunmi facerecognitionusingsparserepresentationbasedclassificationonknearestsubspace
AT jinxingliu facerecognitionusingsparserepresentationbasedclassificationonknearestsubspace
_version_ 1718422868400799744