H.6.5.10. Remote sensing
Nonparametric Spectral-Spatial Anomaly Detection

M. Imani

Volume 8, Issue 1 , January 2020, , Pages 95-103


  Due to abundant spectral information contained in the hyperspectral images, they are suitable data for anomalous targets detection. The use of spatial features in addition to spectral ones can improve the anomaly detection performance. An anomaly detector, called nonparametric spectral-spatial detector ...  Read More

H.6.3.2. Feature evaluation and selection
Feature extraction of hyperspectral images using boundary semi-labeled samples and hybrid criterion

M. Imani; H. Ghassemian

Volume 5, Issue 1 , March 2017, , Pages 39-53


  Feature extraction is a very important preprocessing step for classification of hyperspectral images. The linear discriminant analysis (LDA) method fails to work in small sample size situations. Moreover, LDA has poor efficiency for non-Gaussian data. LDA is optimized by a global criterion. Thus, it ...  Read More

H.6.3.3. Pattern analysis
Overlap-based feature weighting: The feature extraction of Hyperspectral remote sensing imagery

M. Imani; H. Ghassemian

Volume 3, Issue 2 , July 2015, , Pages 181-190


  Hyperspectral sensors provide a large number of spectral bands. This massive and complex data structure of hyperspectral images presents a challenge to traditional data processing techniques. Therefore, reducing the dimensionality of hyperspectral images without losing important information is a very ...  Read More

H.6.3.2. Feature evaluation and selection
Feature reduction of hyperspectral images: Discriminant analysis and the first principal component

Maryam Imani; Hassan Ghassemian

Volume 3, Issue 1 , March 2015, , Pages 1-9


  When the number of training samples is limited, feature reduction plays an important role in classification of hyperspectral images. In this paper, we propose a supervised feature extraction method based on discriminant analysis (DA) which uses the first principal component (PC1) to weight the scatter ...  Read More