Effective feature extraction through segmentation-based folded-PCA for hyperspectral image classification

Uddin, Md. Palash; Mamun, Md. Al; Hossain, Md. Ali

doi:10.1080/01431161.2019.1601284

Cited by 57 publications

(22 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare the performance of the KLRECA with the multiple HSI classification methods, including SVM [35], KPCA [26], EMPs [18], NSSNet [33], RVCANet [34], PCA-EPFs [22], SSFPCA [21] and IAPs [24]. KPCA is a classical kernel-based method.…”

Section: B Experimental Setup 1) Comparison In Related Workmentioning

confidence: 99%

“…To further improve classification results of HSIs, the feature-selection step is usually employed. It is a popular practice to apply PCA and its variants [16][17][18][19][20][21][22][23][24] to perform such data transformation. For instance, the extended morphological profiles (EMPs) are built on the first principal component of HSI to eliminate the effects of spectral variability [18].…”

Section: Introductionmentioning

confidence: 99%

“…Zabalza et al [19] proposed the folded-PCA (FPCA) to handle with the high computational cost and large memory requirement for the usage of PCA in HSI data reduction. Considering the superior properties of FPCA, several FPCA-based models are newly designed for HSI classification [20][21]. In special, Uddin et al [21] proposed a novel method so-called spectrally-segmented-FPCA (SSFPCA), in which they apply FPCA on the HSI datasets mixed with highly correlated and spectrally separated segments instead of directly applying the FPCA on the entire data, to obtain better classification performances.…”

Section: Introductionmentioning

confidence: 99%

“…Considering the superior properties of FPCA, several FPCA-based models are newly designed for HSI classification [20][21]. In special, Uddin et al [21] proposed a novel method so-called spectrally-segmented-FPCA (SSFPCA), in which they apply FPCA on the HSI datasets mixed with highly correlated and spectrally separated segments instead of directly applying the FPCA on the entire data, to obtain better classification performances. PCA is also employed to reduce spectral dimension of HSIs preprocessed by the edge-preserving filters (EPFs) [22][23] and the invariant attribute profiles (IAPs) [24], to name but a few (see [25] for more details of PCA-based methods on extracting HSI features).…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Kernel Low-Rank Entropic Component Analysis for Hyperspectral Image Classification

Bai

Zhang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

Principal component analysis (PCA) and its variations are still the primary tool for feature extraction (FE) in remote sensing community. This is unfortunate, as there has been strong argument against using PCA for this purpose due to its inherent linear properties and uninformative principal components. Therefore, several critical issues still should be considered in hyperspectral image classification when using PCA, among which: 1) the large number of spectral channels and small number of training samples; 2) the nonlinearities of hyperspectral data; 3) the small-sample issue. In order to alleviate these problems, this paper employs a new information-theoretic FE method so-called kernel entropic component analysis (KECA), which can not only extract more nonlinear information, but also be adapt to limited-sample environment. A theorem of the pivoted Cholesky decomposition is also introduced to improve the efficiency of the KECA. The optimized version can more rapidly implement spectral-spatial features extraction, particularly for large-scale HSIs, while effectively maintaining the clustering performances of KECA. Experiments implemented on several real HSIs verify the effectiveness of the new method armed with a support vector machine (SVM) classifier, in comparison with other PCA-based and state-of-the-art HSI classification algorithms. The code will be also made publicly available.

show abstract

Section: B Experimental Setup 1) Comparison In Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Kernel Low-Rank Entropic Component Analysis for Hyperspectral Image Classification

Bai

Zhang

et al. 2020

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

View full text Add to dashboard Cite

show abstract

“…This CNN architecture, referred to as ResNet, is based on a residual network specifically designed for hyperspectral image classification. Additionally, the performance of the classification method proposed in [53] has been evaluated. This method, referred to as SSFPCA+SVM, relies on a so-called spectrally-segmented folded PCA (SSFPCA) as a feature extraction step, followed by a RBF-kernel SVM classifier.…”

Section: Synthetic Hyperspectral Imagementioning

confidence: 99%

Matrix cofactorization for joint representation learning and supervised classification – Application to hyperspectral image analysis

et al. 2020

View full text Add to dashboard Cite

Supervised classification and representation learning are two widely used classes of methods to analyze multivariate images. Although complementary, these methods have been scarcely considered jointly in a hierarchical modeling. In this paper, a method coupling these two approaches is designed using a matrix cofactorization formulation. Each task is modeled as a factorization matrix problem and a term relating both coding matrices is then introduced to drive an appropriate coupling. The link can be interpreted as a clustering operation over the low-dimensional representation vectors. The attribution vectors of the clustering are then used as features vectors for the classification task, i.e., the coding vectors of the corresponding factorization problem. A proximal gradient descent algorithm, ensuring convergence to a critical point of the objective function, is then derived to solve the resulting non-convex non-smooth optimization problem. An evaluation of the proposed method is finally conducted both on synthetic and real data in the specific context of hyperspectral image interpretation, unifying two standard analysis techniques, namely unmixing and classification.

show abstract

A Hybrid Metaheuristic Algorithm for Features Dimensionality Reduction in Network Intrusion Detection System

Balogun¹,

Gbolagade²,

Arowolo³

et al. 2021

Computational Science and Its Applications – ICCSA 2021

View full text Add to dashboard Cite

Effective feature extraction through segmentation-based folded-PCA for hyperspectral image classification

Cited by 57 publications

References 58 publications

Kernel Low-Rank Entropic Component Analysis for Hyperspectral Image Classification

Kernel Low-Rank Entropic Component Analysis for Hyperspectral Image Classification

Matrix cofactorization for joint representation learning and supervised classification – Application to hyperspectral image analysis

A Hybrid Metaheuristic Algorithm for Features Dimensionality Reduction in Network Intrusion Detection System

Contact Info

Product

Resources

About