Dimensionality Reduction of Hyperspectral Data via Spectral Feature Extraction

Mojaradi, Barat; Abrishami-Moghaddam, Hamid; Zoej, Mohammad Javad Valadan; Duin, Robert P. W.

doi:10.1109/tgrs.2008.2010346

Cited by 85 publications

(29 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The dimensionality of such a space is equal to the number of participating image pixels. Some others, such as prototype feature selection (PFS) and maximum tangent discrimination (MTD) [18] extract informative bands in an unsupervised manner via geometrical interpretation of distinctive bands in the Prototype Space (PS) [9]. In this way, the axes of the PS are defined based on the spectrum of the extracted endmembers or the clusters' center of the existing classes in the scene.…”

Section: Feature Selection Algorithms To Decrease the Spectral Correlmentioning

confidence: 99%

“…Bands are categorized into three classes in the PS: (1) informative bands: the lager the distance of bands from the main diagonal of the space, the better the bands can separate the image' classes; (2) correlated bands: the bands that have a similar spectral response of endmembers are gathered close together in this space-this concept is beyond the correlation of the adjacent bands in the hyperspectral images, because it would have occurred for those bands that are not adjacent; (3) non-informative bands: those bands that are located close to the main diagonal of the space, which have the exact same response for different classes [9].…”

Section: Reducing the Correlation Of Endmembers By Selecting The Indementioning

confidence: 99%

“…This paper presents a novel and effective approach for managing the SV and decreasing spectral correlation among the endmembers based on the selection of the optimal bands in the Prototype Space (PS) [9]. The proposed method consists of two main steps.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Reducing the Effect of the Endmembers’ Spectral Variability by Selecting the Optimal Spectral Bands

2017

View full text Add to dashboard Cite

Abstract:Variable environmental conditions cause different spectral responses of scene endmembers. Ignoring these variations affects the accuracy of fractional abundances obtained from linear spectral unmixing. On the other hand, the correlation between the bands of hyperspectral data is not considered by conventional methods developed for dealing with spectral variability. In this paper, a novel approach is proposed to simultaneously mitigate spectral variability and reduce correlation among different endmembers in hyperspectral datasets. The idea of the proposed method is to utilize the angular discrepancy of bands in the Prototype Space (PS), which is constructed using the endmembers of the image. Using the concepts of PS, in which each band is treated as a space point, we proposed a method to identify independent bands according to their angles. The proposed method comprised two main steps. In the first step, which aims to alleviate the spectral variability issue, image bands are prioritized based on their standard deviations computed over some sets of endmembers. Independent bands are then recognized in the prototype space, employing the angles between the prioritized bands. Finally, the unmixing process is done using the selected bands. In addition, the paper presents a technique to form a spectral library of endmembers' variability (sets of endmembers). The proposed method extracts endmembers sets directly from the image data via a modified version of unsupervised spatial-spectral preprocessing. The performance of the proposed method was evaluated by five simulated images and three real hyperspectral datasets. The experiments show that the proposed method-using both groups of spectral variability reduction methods and independent band selection methods-produces better results compared to the conventional methods of each group. The improvement in the performance of the proposed method is observed in terms of more appropriate bands being selected and more accurate fractional abundance values being estimated.

show abstract

Section: Feature Selection Algorithms To Decrease the Spectral Correlmentioning

confidence: 99%

Section: Reducing the Correlation Of Endmembers By Selecting The Indementioning

confidence: 99%

See 1 more Smart Citation

Reducing the Effect of the Endmembers’ Spectral Variability by Selecting the Optimal Spectral Bands

2017

View full text Add to dashboard Cite

show abstract

“…The extracted features can't represent the properties of each sleep stage well. Prototype Space Feature Extraction (PSFE) based on Fuzzy C-Means (FCM) is an effective algorithm to identify the highly correlated features in prototype space and reduce the feature dimension [12].…”

Section: Dimension Reductionmentioning

confidence: 99%

Applying the fuzzy c-means based dimension reduction to improve the sleep classification system

Huang

Lin

Wenyu

et al. 2013

2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)

View full text Add to dashboard Cite

Having a well sleep quality is important factor in our daily life. The evaluation of sleep stages has become an important issue due to the distribution of sleep stages across a whole night relates to sleep quality. This study aims to propose a sleep classification system, consists of a preliminary wake detection rule, sleep feature extraction, fuzzy c-means based dimension reduction, support vector machine with radial basis function kernel, and adaptive adjustment scheme, with only FP1 and FP2 electroencephalography. Compared with the results from the sleep technologist, the average accuracy and Kappa coefficient of the proposed sleep classification system is 70.92% and 0.6130, respectively, for individual 10 normal subjects. Thus, the proposed sleep classification system could provide a preliminary report of sleep stages to assistant doctors to make decision if a patient needs to have a detailed testing in a sleep laboratory.

show abstract

“…A variety of methods have been developed to deal with the dimensionality reduction problem, which can be broadly categorized as feature extraction [8] and feature selection [9] algorithms. Traditionally, feature extraction is more effective than feature selection due to the algebraic transformation adapted in feature extraction algorithms; However, feature extraction algorithms may break down in high dimensional problems since they typically assign nonzero loading to all the features; By contrast, the computational requirement for feature selection algorithms is always much lower than that of extraction algorithms since they usually depend on a binary transformation [10]. More importantly, most feature extraction approaches, such as principal component analysis (PCA) and linear discriminant analysis (LDA), involve eigenvalue decomposition, which is extremely time-consuming.…”

Section: Introductionmentioning

confidence: 99%

Dimensionality reduction using compressed sensing and its application to a large-scale visual recognition task

Yang

Bouzerdoum

Tivive

et al. 2010

The 2010 International Joint Conference on Neural Networks (IJCNN)

View full text Add to dashboard Cite

This paper presents a novel algorithm for the dimensionality reduction which employs compressed sensing (CS) to improve the generalization capability of a classifier, especially for large-scale data. Compared to traditional dimensionality reduction methods, the proposed algorithm makes no use of the problemdependent parameters, nor does it require additional computation for the eigenvalue decomposition like PCA or LDA. Mathematically, the derived algorithm regards the input features as the dictionary in CS, and selects the features that minimize the residual output error iteratively, thus the resulting features have a direct correspondence to the performance requirements of the given problem. Furthermore, the proposed algorithm can be regarded as a sparse classifier, which selects discriminative features and classifies the training data simultaneously. Experimentally, the CS-based algorithm is tested with a hierarchical visual pattern recognition architecture. The simulation results show that not only does the proposed method utilize only 25% of full features while achieving the test accuracy of the original full architecture, but also its performance is competitive when compared to existing dimensionality reduction methods. Abstract-This paper presents a novel algorithm for the dimensionality reduction which employs compressed sensing (CS) to improve the generalization capability of a classifier, especially for large-scale data. Compared to traditional dimensionality reduction methods, the proposed algorithm makes no use of the problem-dependent parameters, nor does it require additional computation for the eigenvalue decomposition like PCA or LDA. Mathematically, the derived algorithm regards the input features as the dictionary in CS, and selects the features that minimize the residual output error iteratively, thus the resulting features have a direct correspondence to the performance requirements of the given problem. Furthermore, the proposed algorithm can be regarded as a sparse classifier, which selects discriminative features and classifies the training data simultaneously.Experimentally, the CS-based algorithm is tested with a hierarchical visual pattern recognition architecture. The simulation results show that not only does the proposed method utilize only 25% of full features while achieving the test accuracy of the original full architecture, but also its performance is competitive when compared to existing dimensionality reduction methods.

show abstract

Dimensionality Reduction of Hyperspectral Data via Spectral Feature Extraction

Cited by 85 publications

References 28 publications

Reducing the Effect of the Endmembers’ Spectral Variability by Selecting the Optimal Spectral Bands

Reducing the Effect of the Endmembers’ Spectral Variability by Selecting the Optimal Spectral Bands

Applying the fuzzy c-means based dimension reduction to improve the sleep classification system

Dimensionality reduction using compressed sensing and its application to a large-scale visual recognition task

Contact Info

Product

Resources

About