Robust non-negative supervised low-rank discriminant embedding algorithm
Non-negative matrix factorization (NMF) has been widely used.However, NMF pays more attention to the local information of the data, it ignores the global representation of the data.In terms of image classification, the global information of the data is often more robust to noise than the local infor...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2021-09-01
|
| Series: | 智能科学与技术学报 |
| Subjects: | |
| Online Access: | http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202135 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850194578334810112 |
|---|---|
| author | Yu YAO Minghua WAN |
| author_facet | Yu YAO Minghua WAN |
| author_sort | Yu YAO |
| collection | DOAJ |
| description | Non-negative matrix factorization (NMF) has been widely used.However, NMF pays more attention to the local information of the data, it ignores the global representation of the data.In terms of image classification, the global information of the data is often more robust to noise than the local information.In order to improve the robustness of the algorithm, combined with the data of local and global representation, and considered the characteristics of low-rank representation, a non-negative supervised low-rank discriminant embedded algorithm was proposed.This algorithm assumed the existence of noise in the data, decomposed the data into clean data and noise data, and made sparse constraints on the noise matrix through the L<sub>1</sub>norm, so as to enhance the robustness to noise.In addition, the algorithm used low-rank representation to learn a low-rank matrix, then through non-negative decomposition, the robustness of the algorithm was enhanced again.Finally, combined with a study of graph embedding method, the local and global data were retained at the same time.The algorithm is applied to various noisy databases, and the recognition rate of this algorithm is improved by about 5%～15% compared with the comparison algorithm. |
| format | Article |
| id | doaj-art-052fdce9c2fa405393591bef1f15890c |
| institution | OA Journals |
| issn | 2096-6652 |
| language | zho |
| publishDate | 2021-09-01 |
| publisher | POSTS&TELECOM PRESS Co., LTD |
| record_format | Article |
| series | 智能科学与技术学报 |
| spelling | doaj-art-052fdce9c2fa405393591bef1f15890c2025-08-20T02:13:58ZzhoPOSTS&TELECOM PRESS Co., LTD智能科学与技术学报2096-66522021-09-01334235059640145Robust non-negative supervised low-rank discriminant embedding algorithmYu YAOMinghua WANNon-negative matrix factorization (NMF) has been widely used.However, NMF pays more attention to the local information of the data, it ignores the global representation of the data.In terms of image classification, the global information of the data is often more robust to noise than the local information.In order to improve the robustness of the algorithm, combined with the data of local and global representation, and considered the characteristics of low-rank representation, a non-negative supervised low-rank discriminant embedded algorithm was proposed.This algorithm assumed the existence of noise in the data, decomposed the data into clean data and noise data, and made sparse constraints on the noise matrix through the L<sub>1</sub>norm, so as to enhance the robustness to noise.In addition, the algorithm used low-rank representation to learn a low-rank matrix, then through non-negative decomposition, the robustness of the algorithm was enhanced again.Finally, combined with a study of graph embedding method, the local and global data were retained at the same time.The algorithm is applied to various noisy databases, and the recognition rate of this algorithm is improved by about 5%～15% compared with the comparison algorithm.http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202135non-negative matrix factorization;low-rank representation;feature extraction;graph embedding |
| spellingShingle | Yu YAO Minghua WAN Robust non-negative supervised low-rank discriminant embedding algorithm 智能科学与技术学报 non-negative matrix factorization;low-rank representation;feature extraction;graph embedding |
| title | Robust non-negative supervised low-rank discriminant embedding algorithm |
| title_full | Robust non-negative supervised low-rank discriminant embedding algorithm |
| title_fullStr | Robust non-negative supervised low-rank discriminant embedding algorithm |
| title_full_unstemmed | Robust non-negative supervised low-rank discriminant embedding algorithm |
| title_short | Robust non-negative supervised low-rank discriminant embedding algorithm |
| title_sort | robust non negative supervised low rank discriminant embedding algorithm |
| topic | non-negative matrix factorization;low-rank representation;feature extraction;graph embedding |
| url | http://www.cjist.com.cn/thesisDetails#10.11959/j.issn.2096-6652.202135 |
| work_keys_str_mv | AT yuyao robustnonnegativesupervisedlowrankdiscriminantembeddingalgorithm AT minghuawan robustnonnegativesupervisedlowrankdiscriminantembeddingalgorithm |