1. Home
  2. Issues
  3. Volume 30, Issue 2 (2019)
  4. Hyperspectral Image Classification Using ...

Informatica


Hyperspectral Image Classification Using Isomap with SMACOF
Volume 30, Issue 2 (2019), pp. 349–365
Pub. online: 1 January 2019      Type: Research Article      Open accessOpen Access
Received
1 October 2018
Accepted
1 January 2019
Published
1 January 2019

Abstract

The isometric mapping (Isomap) algorithm is often used for analysing hyperspectral images. Isomap allows to reduce such hyperspectral images from a high-dimensional space into a lower-dimensional space, keeping the critical original information. To achieve such objective, Isomap uses the state-of-the-art MultiDimensional Scaling method (MDS) for dimensionality reduction. In this work, we propose to use Isomap with SMACOF, since SMACOF is the most accurate MDS method. A deep comparison, in terms of accuracy, between Isomap based on an eigen-decomposition process and Isomap based on SMACOF has been carried out using three benchmark hyperspectral images. Moreover, for the hyperspectral image classification, three classifiers (support vector machine, k-nearest neighbour, and Random Forest) have been used to compare both Isomap approaches. The experimental investigation has shown that better classification accuracy is obtained by Isomap with SMACOF.

References

 
Almeida, M., Logrado, L., Zacca, J., Correa, D., Poppi, R. (2017). Raman hyperspectral imaging in conjunction with independent component analysis as a forensic tool for explosive analysis: the case of an ATM explosion. Talanta, 174, 628–632.
 
Altman, N. (1992). An introduction to kernel and nearest-neighbor nonparametric regression. The American Statistician, 46(3), 175–185.
 
Asaari, M., Mishra, P., Mertens, S., Dhondt, S., Inzé, D., Wuyts, N., Scheunders, P. (2018). Close-range hyperspectral image analysis for the early detection of stress responses in individual plants in a high-throughput phenotyping platform. ISPRS Journal of Photogrammetry and Remote Sensing, 138, 121–138.
 
AVIRIS Salinas Valley (2019). Rosis pavia university hyperspectral datasets.
 
Bengio, Y., Paiement, J., Vincent, P., Delalleau, O., Roux, N., Ouimet, M. (2004). Out-of-sample extensions for LLE, Isomap, MDS, eigenmaps, and spectral clustering. In: Advances in Neural Information Processing Systems, pp. 177–184.
 
Bernatavičienė, J., Dzemyda, G., Marcinkevičius, V. (2007). Conditions for optimal efficiency of relative MDS. Informatica, 18(2), 187–202.
 
Borengasser, M., Hungate, W., Watkins, R. (2007). Hyperspectral Remote Sensing: Principles and Applications. CRC Press.
 
Borg, I., Groenen, P. (2005). Modern Multidimensional Scaling: Theory and Applications. Springer Science & Business Media.
 
Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32.
 
Bruce, L., Koger, C., Li, J. (2002). Dimensionality reduction of hyperspectral data using discrete wavelet transform feature extraction. IEEE Transactions on Geoscience and Remote Sensing, 40(10), 2331–2338.
 
Chang, C., Ren, H., Chiang, S. (2001). Real-time processing algorithms for target detection and classification in hyperspectral imagery. IEEE Transactions on Geoscience and Remote Sensing, 39(4), 760–768.
 
Chang, C., Lin, C. (2011). Libsvm: a library for support vector machines. ACM Transactions on Intelligent Systems and Technology (TIST), 2(3), 27.
 
Cortes, C., Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297.
 
De Leeuw, J., Mair, P. (2011). Multidimensional Scaling Using Majorization: Smacof in R.
 
Deng, Y., Chen, Y., Zhang, Y., Mahadevan, S. (2012). Fuzzy Dijkstra algorithm for shortest path problem under uncertain environment. Applied Soft Computing, 12(3), 1231–1237.
 
Dijkstra, E. (1959). A note on two problems in connexion with graphs. Numerische Mathematik, 1(1), 269–271.
 
Dzemyda, G., Kurasova, O., Žilinskas, J. (2013). Multidimensional Data Visualization: Methods and Applications. Springer.
 
Ekanayake, J., Li, H., Zhang, B., Gunarathne, T., Bae, S., Qiu, J., Fox, G. (2010). Twister: a runtime for iterative mapreduce. In: Proceedings of the 19th ACM International Symposium on High Performance Distributed Computing. ACM, pp. 810–818.
 
Filatovas, E., Podkopaev, D., Kurasova, O. (2015). A visualization technique for accessing solution pool in interactive methods of multiobjective optimization. International Journal of Computers Communications & Control, 10(4), 508–519.
 
Fletcher, R., Galiauskas, N., Zilinskas, J. (2014). Quadratic programming with complementarity constraints for multidimensional scaling with city-block distances. Baltic Journal of Modern Computing, 2(4), 248–259.
 
Granato, D., Ares, G. (2014). Mathematical and Statistical Methods in Food Science and Technology. John Wiley & Sons.
 
Green, P. (1975). Marketing applications of MDS: assessment and outlook. The Journal of Marketing, 24–31.
 
Groenen, P., Mathar, R., Heiser, W. (1995). The majorization approach to multidimensional scaling for Minkowski distances. Journal of Classification, 12(1), 3–19.
 
Gupta, K., Ray, I. (2015). Cryptographically significant MDS matrices based on circulant and circulant-like matrices for lightweight applications. Cryptography and Communications, 7(2), 257–287.
 
Harsanyi, J., Chang, C. (1994). Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach. IEEE Transactions on Geoscience and Remote Sensing, 32(4), 779–785.
 
Hsu, C., Chang, C., Lin, C. (2003). A practical guide to support vector classification, pp. 1–16.
 
Ingram, S., Munzner, T., Olano, M. (2009). Glimmer: multilevel MDS on the GPU. IEEE Transactions on Visualization and Computer Graphics, 15(2), 249–261.
 
Keogh, E., Kasetty, S. (2002). On the need for time series data mining benchmarks: a survey and empirical demonstration. In: Proceedings of the Eighth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 102–111.
 
Leavesley, S., Deal, J., Hill, S., Martin, W., Lall, M., Lopez, C., Boudreaux, C. (2018). Colorectal cancer detection by hyperspectral imaging using fluorescence excitation scanning. Optical Biopsy XVI: Toward Real-Time Spectroscopic Imaging and Diagnosis, 10489.
 
Li, W., Zhang, L., Zhang, L., Du, B. (2017). GPU parallel implementation of isometric mapping for hyperspectral classification. IEEE Geoscience and Remote Sensing Letters, 14(9), 1532–1536.
 
Lim, I., de Heras, P., Sarni, S., Thalmann, D. (2003). Planar arrangement of high-dimensional biomedical data sets by Isomap coordinates. In: 16th IEEE Symposium Computer-Based Medical Systems, pp. 50–55.
 
Mairal, J., Bach, F., Ponce, P. (2014). Sparse modeling for image and vision processing. Foundations and Trends in Computer Graphics and Vision, 8(2–3), 85–283.
 
Manolakis, D., Marden, D., Shaw, G. (2003). Hyperspectral image processing for automatic target detection applications. Lincoln Laboratory Journal, 14(1), 79–116.
 
Medvedev, V., Kurasova, O., Bernatavičienė, J., Treigys, P., Marcinkevičius, V., Dzemyda, G. (2017). A new web-based solution for modelling data mining processes. Simulation Modelling Practice and Theory, 76, 34–46.
 
Aviris, N.W. (2012). Indianas indian pines 1992 data set.
 
Orts, F., Filatovas, E., Ortega, G., Kurasova, O., Garzón, E.M. (2018). Improving the energy efficiency of smacof for multidimensional scaling on modern architectures. The Journal of Supercomputing, 1–13.
 
Plaza, A., Martinez, P., Plaza, J., Perez, R. (2005). Dimensionality reduction and classification of hyperspectral image data using sequences of extended morphological transformations. IEEE Transactions on Geoscience and Remote Sensing, 43(3), 466–479.
 
Pulkkinen, T., Roos, T., Myllymaki, P. (2011). Semi-supervised learning for wlan positioning. In: International Conference on Artificial Neural Networks. Springer, pp. 355–362.
 
Rizzo, F., Carpentieri, B., Motta, G., Storer, J. (2005). Low-complexity lossless compression of hyperspectral imagery via linear prediction. IEEE Signal Processing Letters, 12(2), 138–141.
 
Rosenberg, S. (2014). The method of sorting in multivariate research with applications selected from cognitive psychology and person perception. Multivariate Applications in the Social Sciences, 123–148.
 
Sibson, R. (1979). Studies in the robustness of multidimensional scaling: perturbational analysis of classical scaling. Journal of the Royal Statistical Society, Series B, Methodological, 217–229.
 
Tay, B., Hyun, J., Oh, S. (2014). A machine learning approach for specification of spinal cord injuries using fractional anisotropy values obtained from diffusion tensor images. Computational and Mathematical Methods in Medicine.
 
Tenenbaum, J., De Silva, V., Langford, J. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319–2323.
 
Virlet, N., Sabermanesh, K., Sadeghi-Tehran, P., Hawkesford, M. (2017). Field Scanalyzer: An automated robotic field phenotyping platform for detailed crop monitoring. Functional Plant Biology, 44(1), 143–153.
 
Wang, J., Chang, C. (2006). Independent component analysis-based dimensionality reduction with applications in hyperspectral image analysis. IEEE Transactions on Geoscience and Remote Sensing, 44(6), 1586–1600.
 
Wang, L., Zhang, J., Liu, P., Choo, K., Huang, F. (2017). Spectralspatial multi-feature-based deep learning for hyperspectral remote sensing image classification. Soft Computing, 21(1), 213–221.
 
Wei, L., Keogh, E. (2006). Semisupervised time series classification. In: KDD 2006, pp. 748–753.
 
Wu, Y., Chan, K. (2004). An extended Isomap algorithm for learning multi-class manifold. In: Proceedings of 2004 International Conference IEEE Machine Learning and Cybernetics, Vol. 6, pp. 3429–3433.
 
Xing, Z., Pei, J., Philip, S. (2009). Early prediction on time series: a nearest neighbor approach. In: IJCAI, pp. 1297–1302.
 
Yang, M. (2002a). Face recognition using extended Isomap. In: IEEE Proceedings 2002 International Conference.
 
Yang, M. (2002b). Extended Isomap for pattern classification. In: Proceedings of the Eighteenth National Conference on Artificial Intelligence and Fourteenth Conference on Innovative Applications of Artificial Intelligence, pp. 224–229.

Biographies

Orts Gómez Francisco José
francisco.orts@ual.es

F.J. Orts Gómez is a predoctoral researcher at the Informatics Department at University of Almería, Spain. He studied the master in computer engineering at the University of Almería. He is currently doing his PhD thanks to the Spanish FPI program. His publications and more information about him can be found in http://hpca.ual.es/~forts/. His research interests are multiDimensional scaling, quantum computation and high performance computing.

Ortega López Gloria
gloriaortega@uma.es

G. Ortega López (https://sites.google.com/site/gloriaortegalopez/) received the PhD degree from the University of Almería (Spain) in 2014. From 2009, she has been working as a member of the TIC-146 supercomputing-algorithms research group. Currently, she has a post-doctoral fellowship at the University of Málaga and her current research work is focused on high performance computing and optimization. Some of her research interest includes the study of strategies for load balancing the workload on heterogeneous systems, the parallelization of optimization problems and image processing.

Filatovas Ernestas
ernest.filatov@gmail.com

E. Filatovas received the PhD in informatics engineering from the Vilnius University in 2012, Lithuania. He is currently a senior researcher at Vilnius University, and an associate professor at of Vilnius Gediminas Technical University. His main research interests include blockchain technologies, global optimization, multi-objective optimization, multi-objective evolutionary algorithms, multiple criteria decision making, high-performance computing, and image processing. He has published more than 20 scientific papers.

Kurasova Olga
olga.kurasova@mii.vu.lt

O. Kurasova received the doctoral degree in computer science (PhD) from Institute of Mathematics and Informatics jointly with Vytautas Magnus University in 2005. Recent employment is at the Institute of Data Science and Digital Technologies of the Vilnius University as a principal researcher and professor. Research interests include data mining methods, optimization theory and applications, artificial intelligence, neural networks, visualization of multidimensional data, multiple criteria decision support, parallel computing, image processing. She is the author of more than 70 scientific publications.

Garzón Gracia Ester Martın
gmartin@ual.es

Full article Related articles Cited by PDF XML
Full article Related articles Cited by PDF XML

Copyright
© 2019 Vilnius University
Open access article under the CC BY license.

Keywords
dimensionality reduction hyperspectral imaging isometric mapping (Isomap) manifold learning SMACOF algorithm

Metrics
since January 2020
1834

Article info
views

914

Full article
views

652

PDF
downloads

254

XML
downloads


Share


RSS