Wavelet Based Feature Extraction Techniques of Hyperspectral Data

Prabhu, N.; Arora, Manoj K.; Balasubramanian, R.

doi:10.1007/s12524-015-0506-9

Cited by 6 publications

(2 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Also, the nonlinear version of PCA named Kernel Principal Component (KPCA) is used in several studies dimensionality reduction of hyperspectral data [7,8]. The wavelet-based dimensionality reduction method is another unsupervised method [9,10]. In this method, high frequency and low-frequency components of the spectral signature curve (SSC) are separated, and the smoother version of SSC is used as the reduced features.…”

Section: Introductionmentioning

confidence: 99%

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Beirami

Mokhtarzade

2021

IJE

View full text Add to dashboard Cite

Nowadays, hyperspectral images (HIs) are widely used for land cover land use (LCLU) mapping. Hyperspectral sensors collect spectral data in numerous adjacent spectral bands, which are usually redundant. Hyperspectral data processing comes with important challenges such as huge processing time, difficulties in transfer, and storage. In this study, two supervised and unsupervised dimensionality reduction methods are proposed for hyperspectral feature extraction based on the band clustering technique. In the first method, the unsupervised method, after the unsupervised band clustering stage with some statistical attributes, the principal component transform is used in each cluster, and the first PC component is considered an extracted feature. In the second method, the supervised method, bands are clustered based on training samples mean vectors of each class, and the weighted mean operator is used for feature extraction in each cluster. The experiment is conducted on the classification of real famous HI named Indian Pines. Comparing the obtained results and some other state of art methods proved the proposed method's efficiency.

show abstract

Section: Introductionmentioning

confidence: 99%

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Beirami

Mokhtarzade

2021

IJE

View full text Add to dashboard Cite

show abstract

“…In addition to these traditional approaches, there are some advanced nonlinear manifold-based methods such as; locality preserving projection (LPP) [10] and its new two stage version (TwoSP) [11] for classification of hyperspectral images. In the recent years some pixel-based methods such wavelet decomposition [12], rational curve fitting [4] and fractal dimension of spectral response curve [13] are proposed which considered the spectral curves of each pixel for extracting the new features. In the subgroup of supervised feature extraction, there are methods such as decision boundaries (DBFE) [14], nonparametric weighted feature extraction (NWFE) [15], linear discriminant analysis (LDA) [16], spectral segmentation and integration (SSI) based on PSO optimization [17].…”

Section: Introductionmentioning

confidence: 99%

An Automatic Method for Unsupervised Feature Selection of Hyperspectral Images Based on Fuzzy Clustering of Bands

Beirami¹,

Mokhtarzade²

2020

View full text Add to dashboard Cite

Hyperspectral sensors collect spectral data in numerous adjacent spectral bands which are usually redundant and cause some challenges such as Hughes phenomenon. In this study, an automatic unsupervised method is presented for feature selection from hyperspectral images. To do so, a new statistical feature space is introduced in which each band is regarded as a sample point. This feature space is originated from the statistical attributes of image bands while these attributes are extracted from different partitions of the entire image. A fuzzy clustering of bands, performed in the PCA transformed space of previously mentioned statistical feature space, leads to band clusters with similar characteristics. The proposed band selection technique chooses a representative band in each cluster and removes the other redundant ones. The proposed method is investigated in terms of the classification accuracy of the Pavia University hyperspectral image. Obtained results, which are compared to two recent states of art methods, prove its efficiency.

show abstract

Spatial Resolution Enhancement Mapping of Hyperspectral Image via Pixel Filling Algorithm

Prabhu

Arora

Balasubramanian

2019

J Indian Soc Remote Sens

View full text Add to dashboard Cite

Wavelet Based Feature Extraction Techniques of Hyperspectral Data

Cited by 6 publications

References 22 publications

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

Supervised and Unsupervised Clustering Based Dimensionality Reduction of Hyperspectral Data

An Automatic Method for Unsupervised Feature Selection of Hyperspectral Images Based on Fuzzy Clustering of Bands

Spatial Resolution Enhancement Mapping of Hyperspectral Image via Pixel Filling Algorithm

Contact Info

Product

Resources

About