Multi‐view intrinsic low‐rank representation for robust face recognition and clustering

Abstract In the last years, subspace‐based multi‐view face recognition has attracted increasing attention and many related methods have been proposed. However, the most existing methods ignore the specific local structure of different views. This drawback can cause these methods' discriminating...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhi‐yang Wang, Stanley Ebhohimhen Abhadiomhen, Zhi‐feng Liu, Xiang‐jun Shen, Wen‐yun Gao, Shu‐ying Li
Formato:	article
Lenguaje:	EN
Publicado:	Wiley 2021
Materias:	Photography TR1-1050 Computer software QA76.75-76.765
Acceso en línea:	https://doaj.org/article/3c4935c6f5154eacb6c6ceea3268317d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:3c4935c6f5154eacb6c6ceea3268317d
record_format	dspace
spelling	oai:doaj.org-article:3c4935c6f5154eacb6c6ceea3268317d2021-11-29T03:38:16ZMulti‐view intrinsic low‐rank representation for robust face recognition and clustering1751-96671751-965910.1049/ipr2.12232https://doaj.org/article/3c4935c6f5154eacb6c6ceea3268317d2021-12-01T00:00:00Zhttps://doi.org/10.1049/ipr2.12232https://doaj.org/toc/1751-9659https://doaj.org/toc/1751-9667Abstract In the last years, subspace‐based multi‐view face recognition has attracted increasing attention and many related methods have been proposed. However, the most existing methods ignore the specific local structure of different views. This drawback can cause these methods' discriminating ability to degrade when many noisy samples exist in data. To tackle this problem, a multi‐view low‐rank representation method is proposed, which exploits both intrinsic relationships and specific local structures of different views simultaneously. It is achieved by hierarchical Bayesian methods that constrain the low‐rank representation of each view so that it matches a linear combination of an intrinsic representation matrix and a specific representation matrix to obtain common and specific characteristics of different views. The intrinsic representation matrix holds the consensus information between views, and the specific representation matrices indicate the diversity among views. Furthermore, the model injects a clustering structure into the low‐rank representation. This approach allows for adaptive adjustment of the clustering structure while pursuing the optimization of the low‐rank representation. Hence, the model can well capture both the relationship between data and the clustering structure explicitly. Extensive experiments on several datasets demonstrated the effectiveness of the proposed method compared to similar state‐of‐the‐art methods in classification and clustering.Zhi‐yang WangStanley Ebhohimhen AbhadiomhenZhi‐feng LiuXiang‐jun ShenWen‐yun GaoShu‐ying LiWileyarticlePhotographyTR1-1050Computer softwareQA76.75-76.765ENIET Image Processing, Vol 15, Iss 14, Pp 3573-3584 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Photography TR1-1050 Computer software QA76.75-76.765
spellingShingle	Photography TR1-1050 Computer software QA76.75-76.765 Zhi‐yang Wang Stanley Ebhohimhen Abhadiomhen Zhi‐feng Liu Xiang‐jun Shen Wen‐yun Gao Shu‐ying Li Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
description	Abstract In the last years, subspace‐based multi‐view face recognition has attracted increasing attention and many related methods have been proposed. However, the most existing methods ignore the specific local structure of different views. This drawback can cause these methods' discriminating ability to degrade when many noisy samples exist in data. To tackle this problem, a multi‐view low‐rank representation method is proposed, which exploits both intrinsic relationships and specific local structures of different views simultaneously. It is achieved by hierarchical Bayesian methods that constrain the low‐rank representation of each view so that it matches a linear combination of an intrinsic representation matrix and a specific representation matrix to obtain common and specific characteristics of different views. The intrinsic representation matrix holds the consensus information between views, and the specific representation matrices indicate the diversity among views. Furthermore, the model injects a clustering structure into the low‐rank representation. This approach allows for adaptive adjustment of the clustering structure while pursuing the optimization of the low‐rank representation. Hence, the model can well capture both the relationship between data and the clustering structure explicitly. Extensive experiments on several datasets demonstrated the effectiveness of the proposed method compared to similar state‐of‐the‐art methods in classification and clustering.
format	article
author	Zhi‐yang Wang Stanley Ebhohimhen Abhadiomhen Zhi‐feng Liu Xiang‐jun Shen Wen‐yun Gao Shu‐ying Li
author_facet	Zhi‐yang Wang Stanley Ebhohimhen Abhadiomhen Zhi‐feng Liu Xiang‐jun Shen Wen‐yun Gao Shu‐ying Li
author_sort	Zhi‐yang Wang
title	Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
title_short	Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
title_full	Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
title_fullStr	Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
title_full_unstemmed	Multi‐view intrinsic low‐rank representation for robust face recognition and clustering
title_sort	multi‐view intrinsic low‐rank representation for robust face recognition and clustering
publisher	Wiley
publishDate	2021
url	https://doaj.org/article/3c4935c6f5154eacb6c6ceea3268317d
work_keys_str_mv	AT zhiyangwang multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering AT stanleyebhohimhenabhadiomhen multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering AT zhifengliu multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering AT xiangjunshen multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering AT wenyungao multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering AT shuyingli multiviewintrinsiclowrankrepresentationforrobustfacerecognitionandclustering
_version_	1718407637873197056

Multi‐view intrinsic low‐rank representation for robust face recognition and clustering

Ejemplares similares