Linear Feature Extraction for Hyperspectral Images Based on Information Theoretic Learning

Kamandar, Mehdi; Ghassemian, Hassan

doi:10.1109/lgrs.2012.2219575

Cited by 35 publications

(9 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A definition of the object function in variable and feature selection, feature ranking, feature construction and a wide range of related aspects are represented in (Guyon and Elisseeff, 2003). Feature extraction methods extract a set of new features from the original ones through some functional mapping (Dhanjal et al, 2009;Ghassemian and Landgrebe, 1988;Zhang et al, 2013;Hsu, 2007;Yin et al, 2013;Kamandar and Ghassemian, 2013). Features selected by feature selection techniques maintain the physical meaning of data while features obtained by feature extraction methods are more discriminative than those selected by feature selection approaches.…”

Section: Introductionmentioning

confidence: 99%

Feature space discriminant analysis for hyperspectral data feature reduction

Imani

Ghassemian

2015

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

Feature space discriminant analysis for hyperspectral data feature reduction

Imani

Ghassemian

2015

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

“…The former selects an appropriate subset of original features and thus, maintains the physical meaning of features [3], [4]. The latter transforms the feature space of data usually by using a projection matrix [5]. Feature extraction methods can be divided into: unsupervised ones, supervised ones, and semisupervised ones.…”

Section: Introductionmentioning

confidence: 99%

Feature Extraction Using Weighted Training Samples

Imani

Ghassemian

2015

IEEE Geosci. Remote Sensing Lett.

View full text Add to dashboard Cite

Feature extraction using weighted training (FEWT) samples is proposed in this letter. Different spectral bands (features) play different roles in identification of land-cover classes. In the FEWT, the relative importance of each feature of a training sample in predicting the class label of that sample is obtained and considered as a weight for that feature. Then, the weighted training samples can be used in each arbitrary feature extraction method. In this letter, we use the weighted training samples in supervised locality preserving projection. The experimental results on three popular hyperspectral images show that FEWT has better performance and more speed than some state-of-the-art supervised feature extraction methods using limited number of available training samples.

show abstract

“…Feature extraction algorithms can be divided into supervised, unsupervised and semisupervised ones. Supervised methods use Labeled samples so they are usually appropriate for classification purposes (Kamandar and Ghassemian, 2013;Imani and Ghassemian, 2014;Imani and Ghassemian, 2015c;Imani and Ghassemian, 2015d). They find a low dimension space where all labeled samples are provided.…”

Section: Introductionmentioning

confidence: 99%

Unlabeled Selected Samples in Feature Extraction for Classification of Hyperspectral Images With Limited Training Samples

Kianisarkaleh

Ghassemian

Razzazi

2015

Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci.

Self Cite

View full text Add to dashboard Cite

ABSTRACT:Feature extraction plays a key role in hyperspectral images classification. Using unlabeled samples, often unlimitedly available, unsupervised and semisupervised feature extraction methods show better performance when limited number of training samples exists. This paper illustrates the importance of selecting appropriate unlabeled samples that used in feature extraction methods. Also proposes a new method for unlabeled samples selection using spectral and spatial information. The proposed method has four parts including: PCA, prior classification, posterior classification and sample selection. As hyperspectral image passes these parts, selected unlabeled samples can be used in arbitrary feature extraction methods. The effectiveness of the proposed unlabeled selected samples in unsupervised and semisupervised feature extraction is demonstrated using two real hyperspectral datasets. Results show that through selecting appropriate unlabeled samples, the proposed method can improve the performance of feature extraction methods and increase classification accuracy.

show abstract

Linear Feature Extraction for Hyperspectral Images Based on Information Theoretic Learning

Cited by 35 publications

References 20 publications

Feature space discriminant analysis for hyperspectral data feature reduction

Feature space discriminant analysis for hyperspectral data feature reduction

Feature Extraction Using Weighted Training Samples

Unlabeled Selected Samples in Feature Extraction for Classification of Hyperspectral Images With Limited Training Samples

Contact Info

Product

Resources

About