<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning
Recently, L<sub>1</sub>-norm-based robust discriminant feature extraction technique has been attracted much attention in dimensionality reduction and pattern recognition. However, it does not relate to the scatter matrix which well characterizes the geometric structure of data. In this p...
Main Authors: | , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8419246/ |
id |
doaj-20ac825142244d4d83d436555cf69c47 |
---|---|
record_format |
Article |
spelling |
doaj-20ac825142244d4d83d436555cf69c472021-03-29T21:17:47ZengIEEEIEEE Access2169-35362018-01-016407234073410.1109/ACCESS.2018.28592998419246<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold LearningYang Liu0https://orcid.org/0000-0002-9265-5842Quanxue Gao1Xinbo Gao2https://orcid.org/0000-0003-1443-0776Ling Shao3State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, ChinaState Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, ChinaInception Institute of Artificial Intelligence, Abu Dhabi, United Arab EmiratesRecently, L<sub>1</sub>-norm-based robust discriminant feature extraction technique has been attracted much attention in dimensionality reduction and pattern recognition. However, it does not relate to the scatter matrix which well characterizes the geometric structure of data. In this paper, we propose a robust formulation of graph embedding framework for dimensionality reduction. In this robust framework, we use L<sub>2</sub>-norm to measure the distance along space dimension and L<sub>1</sub>-norm to sum overall data points. The proposed robust graph embedding framework retains the traditional framework's desirable properties, such as rotational invariance and well geometric structure, and simultaneously suppresses outliers. Based on this framework, we develop a simple and robust feature extraction method, namely L<sub>2,1</sub>-norm-based discriminant locality preserving projections (L<sub>2,1</sub>-DLPP) and provide an effective iterative algorithm to solve L<sub>2,1</sub>-DLPP. Extensive experiments in artificial data and three popular face databases illustrate the effectiveness of our proposed method.https://ieeexplore.ieee.org/document/8419246/<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₁-norm<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂, ₁-normmanifold learningdimensionality reduction |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Yang Liu Quanxue Gao Xinbo Gao Ling Shao |
spellingShingle |
Yang Liu Quanxue Gao Xinbo Gao Ling Shao <inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning IEEE Access <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₁-norm <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂, ₁-norm manifold learning dimensionality reduction |
author_facet |
Yang Liu Quanxue Gao Xinbo Gao Ling Shao |
author_sort |
Yang Liu |
title |
<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning |
title_short |
<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning |
title_full |
<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning |
title_fullStr |
<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning |
title_full_unstemmed |
<inline-formula> <tex-math notation="LaTeX">${L_{2,1}}$ </tex-math></inline-formula>-Norm Discriminant Manifold Learning |
title_sort |
<inline-formula> <tex-math notation="latex">${l_{2,1}}$ </tex-math></inline-formula>-norm discriminant manifold learning |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
Recently, L<sub>1</sub>-norm-based robust discriminant feature extraction technique has been attracted much attention in dimensionality reduction and pattern recognition. However, it does not relate to the scatter matrix which well characterizes the geometric structure of data. In this paper, we propose a robust formulation of graph embedding framework for dimensionality reduction. In this robust framework, we use L<sub>2</sub>-norm to measure the distance along space dimension and L<sub>1</sub>-norm to sum overall data points. The proposed robust graph embedding framework retains the traditional framework's desirable properties, such as rotational invariance and well geometric structure, and simultaneously suppresses outliers. Based on this framework, we develop a simple and robust feature extraction method, namely L<sub>2,1</sub>-norm-based discriminant locality preserving projections (L<sub>2,1</sub>-DLPP) and provide an effective iterative algorithm to solve L<sub>2,1</sub>-DLPP. Extensive experiments in artificial data and three popular face databases illustrate the effectiveness of our proposed method. |
topic |
<italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₁-norm <italic xmlns:ali="http://www.niso.org/schemas/ali/1.0/" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance">L</italic>₂, ₁-norm manifold learning dimensionality reduction |
url |
https://ieeexplore.ieee.org/document/8419246/ |
work_keys_str_mv |
AT yangliu inlineformulatexmathnotationlatexl21texmathinlineformulanormdiscriminantmanifoldlearning AT quanxuegao inlineformulatexmathnotationlatexl21texmathinlineformulanormdiscriminantmanifoldlearning AT xinbogao inlineformulatexmathnotationlatexl21texmathinlineformulanormdiscriminantmanifoldlearning AT lingshao inlineformulatexmathnotationlatexl21texmathinlineformulanormdiscriminantmanifoldlearning |
_version_ |
1724193171968098304 |