The classification of hyperspectral images is more
challenging because of the very high dimensionality of the
pixels and the small number of labelled examples typically
available for learning. These peculiarities lead to particular
signal processing problems, mainly characterized by
indetermination and complex manifolds. In our project a new
novel method has been introduced that is Harmonic Analysis
based classification such as HA-BFO-SVM approach. This
new approach accurately classifies the cluster band with
respect to their amplitude and phase. Harmonic Analysis
(HA) is introduced to extract the feature from hyperspectral
image. Amplitude and phase a feature has been obtained by
derived HA. Then select best feature among extracted feature
by Bacterial Foraging Optimization (BFO). Finally, classify
the respective band with related cluster which is performed
with the help of Support Vector Machine (SVM). This
classifier accurately classifies the band to respective cluster
form. In prior work, instead of HA, used MNF, PCA, and
ICA could extract features and also classification has been
performed by BFO-SVM instead of using PSO-SVM, CVSVM
and GA-SVM.
Bhanupriya Gaikwad : Department of CSE, MGM’s JNEC (Dr. BAMU University), Aurangabad,
Maharashtra, India
Vijaya Musande : Department of CSE, MGM’s JNEC (Dr. BAMU University), Aurangabad,
Maharashtra, India
Harmonic analysis (HA)
hyper spectral image
classification (HSI)
Bacterial Foraging optimization (BFO)
Support vector machine (SVM)
Developed a novel HA-based feature extraction method,
exploited a BFO optimized SVM classification scheme,
and evaluated the performance of the proposed HA-BFOSVM
classification scheme with respect to different
combinations of feature extraction and parameter
optimization methods. The proposed method leads to
improved performance, and the BFO optimized SVM
presents a good trade-off between accuracy and
computational time. Specifically, we adapt the HA
technique for hyperspectral image analysis and transform
the spectral domain into frequency domain represented by
amplitude and phase features that are experimentally
proofed sensitive and discriminative for classification
purpose. That is due to the fact that HA takes adjacent
spectral band into account to generate these features,
capturing more functional information between bands.
Further experiments with additional scenes and
comparison methods should be conducted in future.
Furthermore, we also envisage the following future
perspectives for the development of the presented work.
[1] J. A. Richards and X. Jia, Remote Sensing Digital
Image Analysis: An Introduction, 4th ed. New York,
NY, USA: Springer-Verlag, 2006.
[2] J. Pontius, M. Martin, L. Plourde, and R. Hallett, “Ash
decline assessment in emerald ash borer-infested
regions: A test of tree-level, hyperspectral
technologies,” Remote Sens. Environ., vol. 112, no. 5,
pp. 2665–2676, 2008.
[3] U. Amato, A. Antoniadis, M. F. Carfora, P. Colandrea,
V. Cuomo, M. Franzese et al., “Statistical classification
for assessing PRISMA hyperspectral potential for
agricultural land use,” IEEE J. Sel. Topics Appl. Earth
Observ. Remote Sens., vol. 6, no. 2, pp. 615–625, Apr.
2013.
[4] G. Camps-Valls, L. Gómez-Choval, J. Calpe-
Maravilla, J. D. Martin- Guerrero, E. Soria-Olivas, L. Alonso-Chorda et al., “Robust support vector method
for hyperspectral data classification and knowledge
discovery,” IEEE Trans. Geosci. Remote Sens., vol.
42, no. 7, pp. 1530–1542, Jul. 2004.
[5] Y. Bazi and F. Melgani, “Toward an optimal SVM
classification system for hyperspectral remote sensing
images,” IEEE Trans. Geosci. Remote Sens., vol. 44,
no. 11, pp. 3374–3385, Nov. 2006.
[6] G. Camps-Valls, D. Tuia, L. Bruzzone et al.,
“Advances in hyperspectral image classification,”
IEEE Signal Process. Mag., vol. 31, no. 1, pp. 45–54,
Jan. 2014.
[7] P. Du, K. Tan, and J. Xia, “A novel binary tree support
vector machine for hyperspectral remote sensing image
classification,” Optics Commun., vol. 285, pp. 3054–
3060, Jun. 2012.
[8] G. C. Cawley and N. L. C. Talbot, “Over-fitting in
model selection and subsequent selection bias in
performance evaluation,” J. Mach. Learn. Res., vol. 11,
pp. 2079–2107, Jul. 2010.
[9] A. Plaza, J. A. Benediktsson, J. W. Boardman, J.
Brazile, L. Bruzzone, G. Camps-Valls, J. Chanussot,
M. Fauvel, P. Gamba, A. Gualtieri, M. Marconcini, J.
C. Tilton, and G. Trianni, “Recent advances in
techniques for hyperspectral image processing,”
Remote Sens. Environ., vol. 113, pp. S110–S122,
2009.
[10] F.Melgani and Y. Bazi, “Classification of
electrocardiogram signals with support vector
machines and particle swarm optimization,” IEEE
Trans. Inf. Technol. Biomed., vol. 12, no. 5, pp. 667–
677, Sep. 2008.
[11] M. Chi, R. Feng, and L. Bruzzone, “Classification of
hyperspectral remotesensing data with primal SVM for
small-sized training dataset problem,” Adv. Space
Res., vol. 41, no. 11, pp. 1793–1799, Mar. 2008.
[12] I.Jolliffe,PrincipalComponentAnalysis.NewYork,NY,U
SA:Wiley, 2005.
[13] Zhen Ye , Saurabh Prasad, Wei Li, James E. Fowler,
Mingyi He, Classification Based on 3-D DWT and
Decision Fusion for Hyperspectral Image Analysis,
VOL. 11, NO. 1, JANUARY 2014
[14] C. Davis, Statistics and Data Analysis in Geology, 3rd
ed. New York, NY, USA: Wiley, 2008, pp. 238–244.
[15] C.-C. Chang and C.-J. Lin, LIBSVM:Alibrary for
support vector machines, ACM Trans. Intell. Syst.
Technol., vol. 2, no. 27, pp. 1–27, 2011
[16] D. L. Donoho, “High-dimensional data analysis: The
curses and blessings of dimensionality,” in Proc. AMS
Math Challenges Lecture, 2000, pp. 1–32.
[17] V. N. Vapnik, The Nature of Statistical Learning
Theory, 2nd ed.
[18] New York, NY, USA: Springer-Verlag, 1995, pp. 138–
141.
[19] F. Melgani and L. Bruzzone, “Classification of
hyperspectral remote sensing images with support
vector machines,” IEEE Trans. Geosci.
[20] Remote Sens., vol. 42, no. 8, pp. 1778–1790, Aug.
2004.
[21] P. Du, K. Tan, and J. Xia, “A novel binary tree support
vector machine for hyperspectral remote sensing image
classification,” Optics Commun., vol. 285, pp. 3054–
3060, Jun. 2012.
[22] Y. Bazi and F. Melgani, “Toward an optimal SVM
classification system for hyperspectral remote sensing
images,” IEEE Trans. Geosci. Remote Sens.,vol. 44,
no. 11, pp. 3374–3385, Nov. 2006.
[23] G. C. Cawley and N. L. C. Talbot, “Over-fitting in
model selection and subsequent selection bias in
performance evaluation,” J. Mach. Learn. Res., vol. 11,
pp. 2079–2107, Jul. 2010.
[24] J. Kennedy and R. C. Eberhart, Swarm Intelligence.
San Mateo, CA, USA: Morgan Kaufmann, pp. 192–
206.
[25] F.Melgani and Y. Bazi, “Classification of
electrocardiogram signals with support vector
machines and particle swarm optimization,” IEEE
Trans. Inf. Technol. Biomed., vol. 12, no. 5, pp. 667–
677, Sep. 2008.
[26] T. Hastie, R. Tibshirani, and J. Friedman, The
Elements of Statistical Learning. New York, NY, USA:
Springer-Verlag, 2008.
[27] H. Frohlich, O. Chapelle, and B. Scholkopf, “Feature
selection for support vector machines by means of
genetic algorithm,” in Proc. 15th IEEE Int. Conf.
Comput. Process. (Hardware/Software), Nov. 2003, pp.
142–148.
[28] S. Tang and X. Cheng, “A harmonic measuring
approach based on multilayered feed forward neural
network,” in Proc. CSEE, 2006, vol. 26,no. 18, pp. 90–
94.
[29] E. J. Mark, R. L. David, and J. H. Kastens, “Harmonic
analysis of time-series AVHRR NDVI data,”
Photogramm. Eng. Remote Sens., vol. 67, no. 4, pp.
461–470, Apr. 2001.
[30] E. J. Mark, R. L. David, and J. H. Kastens, “Crop
identification using harmonic analysis of time-series
AVHRR NDVI data,” Comput. Electron. Agric., vol.
37, pp. 127–139, Dec. 2002.
