Stochastic Perturbations on Low-Rank Hyperspectral Data for Image Classification

Alex Sumarsono(1*), Farnaz Ganjeizadeh(2), Ryan Tomasi(3),


(1) California State University, East Bay
(2) California State University, East Bay
(3) California State University, East Bay
(*) Corresponding Author

Abstract


Hyperspectral imagery (HSI) contains hundreds of narrow contiguous bands of spectral signals. These signals, which form spectral signatures, provide a wealth of information that can be used to characterize material substances. In recent years machine learning has been used extensively to classify HSI data. While many excellent HSI classifiers have been proposed and deployed, the focus has been more on the design of the algorithms. This paper presents a novel data preprocessing method (LRSP) to improve classification accuracy by applying stochastic perturbations to the low-rank constituent of the dataset. The proposed architecture is composed of a low-rank and sparse decomposition, a degradation function and a constraint least squares filter. Experimental results confirm that popular state-of-the-art HSI classifiers can produce better classification results if supplied by LRSP-altered datasets rather than the original HSI datasets.
 

Keywords


Hyperspectral Imagery; Hyperspectral Image Processing; Low Rank and Sparse Decomposition; Stochastic Perturbations;

Full Text:

PDF

Article Metrics

Abstract view : 34 times
PDF - 5 times

References


H. Yu, X. Shang, X. Zhang, L. Gao, “Hyperspectral Image Classifcation Based on Adjacent Constraint Representation,” IEEE Geoscience and Remote Sensing Letters, 2020.

X. Shang, M. Song, C. Yu, “Hyperspectral Image Classification with Background,” in Proceedings of IEEE International Geoscience and Remote Sensing Symposium, 2019.

B. Rasti, P. Ghamsi, J. Chanussot, “Mixed Noise Reduction in Hyperspectral Imagery,” in 10th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2019.

S. Xu, J. Li, “Combining Contextual Information for Subspace Based Hyperspectral Image Classification,” in 9th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2018.

A. Sumarsono, Q. Du and N. Younan, “Hyperspectral Image Segmentation with Low-Rank Representation and Spectral Clustering,” in Proceedings of 7th IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2015.

S. Zhong, C. Chang, J. Li, X. Shang, S. Chen and M. Song, “Class Feature Weighted Hyperspectral Image Classification,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 12, no. 12, 2019.

A. Sumarsono, Q. Du and N. Younan, “Low-Rank Subspace Representation for Supervised and Unsupervised Classification of Hyperspectral Imagery,” IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 9, 2016.

E. Candes, X. Li, Y. Ma and J. Wright, “Robust Principal Component Analysis?,” Journal of the ACM, vol. 58, no. 3, 2009.

J. Wright, Y. Peng, Y. Ma, A. Ganesh and S. Rao, “Robust Principal Component Analysis: Exact Recovery of Corrupted Low-Rank Matrices by Convex Optimization,” in Neural Information Processing Systems, NIPS, 2009.

G. Liu, Z. Lin, S. Yang, J. Sun, Y. Yu and Y. Ma, “Robust Recovery of Subspace Structures by Low-Rank Representation,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 1, 2013.

Z. Lin, A. Ganesh, L. Wu, M. Chen and Y. Ma, “Fast Convex Optimization Algorithms for Exact Recovery of a Corrupted Low-Rank Matrix,” UIUC Technical Report UILU-ENG-09-2215, 2009.

J. Li, J. Bioucas-Dias and A. Plaza, “Spectral-Spatial Hyperspectral Image Segmentation Using Subspace Multinomial Logistic Regression and Markov Random Fields,” IEEE Transactions on Geoscience and Remote Sensing, vol. 50, no. 3, 2012.

P. Sidike, C. Chen, V. Asari, Y. Xu and W. Li, “Classification of Hyperspectral Image Using Multiscale Spatial Texture Features,” in Proceedings of 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, 2016.

L. Sun, T. Zhan, Z. Wu, B. Jeon, “A Novel 3D Anistropic Total Variation Regularized Low Rank Method for Hyperspectral Image Mixed Denoising,” International Journal of Geo-Information, vol. 7, 2018.




DOI: https://doi.org/10.29099/ijair.v5i1.196

________________________________________________________

International Journal Of Artificial Intelligence Research

Organized by: Departemen Teknik Informatika STMIK Dharma Wacana
Published by: STMIK Dharma Wacana
Jl. Kenanga No.03 Mulyojati 16C Metro Barat Kota Metro Lampung
phone. +62725-7850671
Fax. +62725-7850671
Email: info@ijair.id | internationaljournalair@gmail.com | herinurdiyanto@ieee.org 

View IJAIR Statcounter

Creative Commons License
IJAIR is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.