Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels
Numerous studies have been conducted for hyperspectral image (HSI) classification by assuming that the label information of training data is fully available and correct. However, such an assumption may not always be true in practical applications, which could impact feature extraction methods and ev...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8787880/ |
| _version_ | 1829508918240346112 |
|---|---|
| author | Shan Zeng Xiangjun Duan Hao Li Zuyin Xiao Zhiyong Wang David Feng |
| author_facet | Shan Zeng Xiangjun Duan Hao Li Zuyin Xiao Zhiyong Wang David Feng |
| author_sort | Shan Zeng |
| collection | DOAJ |
| description | Numerous studies have been conducted for hyperspectral image (HSI) classification by assuming that the label information of training data is fully available and correct. However, such an assumption may not always be true in practical applications, which could impact feature extraction methods and eventually compromise the performance of hyperspectral image classification. To address this issue in hyperspectral image classification, we propose a Regularized Fuzzy Discriminant Analysis (RFDA) based feature extraction method to effectively utilize the spatial and spectral information of HSIs with noisy labels. Firstly, the physical properties of HSIs are explored to reconstruct the data. Secondly, the labeled training samples and their unlabeled spatial neighborhood samples are fuzzified using the Fuzzy K-Nearest Neighbor (FKNN) method. Finally, a regularization term using a Fuzzy Locality Preserving Scatter (FLPS) matrix is integrated into fuzzy discriminant analysis, and the spatial-spectral information of HSIs is effectively fused to construct the projection matrix. As a result, the proposed method not only corrects the mislabeled samples effectively, but also preserves the neighborhood relationship among the pixels in the spatial domain and the fundamental structure among the samples in the spectral-domain, which is beneficial for hyperspectral image classification. Experimental results on three synthetic datasets and three public hyperspectral datasets show that our proposed RFDA method outperforms several state-of-the-art feature extraction methods in terms of classification accuracy. |
| first_indexed | 2024-12-16T11:36:14Z |
| format | Article |
| id | doaj.art-8fc4987b28cd490d81a4a8f69fca2730 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-16T11:36:14Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-8fc4987b28cd490d81a4a8f69fca27302022-12-21T22:33:06ZengIEEEIEEE Access2169-35362019-01-01710812510813610.1109/ACCESS.2019.29329728787880Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy LabelsShan Zeng0https://orcid.org/0000-0003-1142-5613Xiangjun Duan1Hao Li2Zuyin Xiao3Zhiyong Wang4David Feng5College of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, ChinaCollege of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, ChinaCollege of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, ChinaCollege of Mathematics and Computer Science, Wuhan Polytechnic University, Wuhan, ChinaSchool of Computer Science, The University of Sydney, Sydney, NSW, AustraliaSchool of Computer Science, The University of Sydney, Sydney, NSW, AustraliaNumerous studies have been conducted for hyperspectral image (HSI) classification by assuming that the label information of training data is fully available and correct. However, such an assumption may not always be true in practical applications, which could impact feature extraction methods and eventually compromise the performance of hyperspectral image classification. To address this issue in hyperspectral image classification, we propose a Regularized Fuzzy Discriminant Analysis (RFDA) based feature extraction method to effectively utilize the spatial and spectral information of HSIs with noisy labels. Firstly, the physical properties of HSIs are explored to reconstruct the data. Secondly, the labeled training samples and their unlabeled spatial neighborhood samples are fuzzified using the Fuzzy K-Nearest Neighbor (FKNN) method. Finally, a regularization term using a Fuzzy Locality Preserving Scatter (FLPS) matrix is integrated into fuzzy discriminant analysis, and the spatial-spectral information of HSIs is effectively fused to construct the projection matrix. As a result, the proposed method not only corrects the mislabeled samples effectively, but also preserves the neighborhood relationship among the pixels in the spatial domain and the fundamental structure among the samples in the spectral-domain, which is beneficial for hyperspectral image classification. Experimental results on three synthetic datasets and three public hyperspectral datasets show that our proposed RFDA method outperforms several state-of-the-art feature extraction methods in terms of classification accuracy.https://ieeexplore.ieee.org/document/8787880/Hyperspectral images classificationnoisy labelsfuzzy discriminant analysisfuzzy K-nearest neighbor |
| spellingShingle | Shan Zeng Xiangjun Duan Hao Li Zuyin Xiao Zhiyong Wang David Feng Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels IEEE Access Hyperspectral images classification noisy labels fuzzy discriminant analysis fuzzy K-nearest neighbor |
| title | Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels |
| title_full | Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels |
| title_fullStr | Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels |
| title_full_unstemmed | Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels |
| title_short | Regularized Fuzzy Discriminant Analysis for Hyperspectral Image Classification With Noisy Labels |
| title_sort | regularized fuzzy discriminant analysis for hyperspectral image classification with noisy labels |
| topic | Hyperspectral images classification noisy labels fuzzy discriminant analysis fuzzy K-nearest neighbor |
| url | https://ieeexplore.ieee.org/document/8787880/ |
| work_keys_str_mv | AT shanzeng regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels AT xiangjunduan regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels AT haoli regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels AT zuyinxiao regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels AT zhiyongwang regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels AT davidfeng regularizedfuzzydiscriminantanalysisforhyperspectralimageclassificationwithnoisylabels |