Multiscale Gaussian Derivative Functions for Hyperspectral Image Feature Extraction

A method for extracting spatiospectral features from hyperspectral (HS) data is proposed. Based on 2-D Gaussian derivative (GD) functions, a bank of 2-D filters is designed. These filters are utilized with various scale parameters to form a multiscale filter bank. This filter bank is applied on a few principal components extracted from HS data, resulting in a set of features called GD features. Four different scenarios are examined to employ these features in HS image classification. Some experiments are conducted on three well-known HS data sets. Based on the results, one scenario is adopted as the proposed framework. The effect of differentiation order of GD filters on classification accuracies is investigated. The proposed method is compared with some state-of-the-art spatiospectral methods. The experimental results confirm the remarkable performance of GD features in HS image classification.

[1]  Filiberto Pla,et al.  Spectral–Spatial Pixel Characterization Using Gabor Filters for Hyperspectral Image Classification , 2013, IEEE Geoscience and Remote Sensing Letters.

[2]  Bor-Chen Kuo,et al.  Nonparametric weighted feature extraction for classification , 2004, IEEE Transactions on Geoscience and Remote Sensing.

[3]  H. Ghassemian,et al.  Improving hyperspectral image classification by combining spectral, texture, and shape features , 2015 .

[4]  J. Chanussot,et al.  On the influence of feature reduction for the classification of hyperspectral images based on the extended morphological profile , 2010 .

[5]  Pedram Ghamisi,et al.  Spectral–Spatial Classification of Hyperspectral Images Based on Hidden Markov Random Fields , 2014, IEEE Transactions on Geoscience and Remote Sensing.

[6]  Hassan Ghassemian,et al.  Hyperspectral image classification using profiles based on partial differential equations , 2015, 2015 23rd Iranian Conference on Electrical Engineering.

[7]  G. Foody.  Thematic map comparison: Evaluating the statistical significance of differences in classification accuracy , 2004 .

[8]  Chih-Jen Lin,et al.  LIBSVM: A library for support vector machines , 2011, TIST.

[9]  Jun Zhou,et al.  Hyperspectral Image Classification Based on Structured Sparse Logistic Regression and Three-Dimensional Wavelet Texture Features , 2013, IEEE Transactions on Geoscience and Remote Sensing.

[10]  Jon Atli Benediktsson,et al.  Extended Self-Dual Attribute Profiles for the Classification of Hyperspectral Images , 2015, IEEE Geoscience and Remote Sensing Letters.

[11]  Hassan Ghassemian,et al.  An Adaptive Pixon Extraction Technique for Multispectral/Hyperspectral Image Classification , 2015, IEEE Geoscience and Remote Sensing Letters.

[12]  Jon Atli Benediktsson,et al.  Advances in Spectral-Spatial Classification of Hyperspectral Images , 2013, Proceedings of the IEEE.

[13]  David A. Landgrebe,et al.  Multispectral image compression by an on-board scene segmentation , 2001, IGARSS 2001. Scanning the Present and Resolving the Future. Proceedings. IEEE 2001 International Geoscience and Remote Sensing Symposium (Cat. No.01CH37217).

[14]  Qian Du,et al.  Improving hyperspectral image classification using smoothing filter via sparse gradient minimization , 2014, 2014 8th IAPR Workshop on Pattern Reconition in Remote Sensing.

[15]  Johannes R. Sveinsson,et al.  Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles , 2008, 2007 IEEE International Geoscience and Remote Sensing Symposium.

[16]  Martin E. Muldoon,et al.  Approximations for zeros of Hermite functions , 2008 .

[17]  Jon Atli Benediktsson,et al.  Morphological Attribute Profiles for the Analysis of Very High Resolution Images , 2010, IEEE Transactions on Geoscience and Remote Sensing.