Call for Paper - August 2022 Edition
IJCA solicits original research papers for the August 2022 Edition. Last date of manuscript submission is July 20, 2022. Read More

Spectral and Spatial Classification of High Resolution Urban Satellites Images using Haralick features and SVM with SAM and EMD distance Metrics

Print
PDF
International Journal of Computer Applications
© 2012 by IJCA Journal
Volume 46 - Number 11
Year of Publication: 2012
Authors:
Aissam Bekkari
Soufian Idbraim
Azeddine Elhassouny
Driss Mammass Danielle Ducrot
Mostapha El Yassa
Danielle Ducrot
10.5120/6956-9585

Aissam Bekkari, Soufian Idbraim, Azeddine Elhassouny, Driss Mammass Danielle Ducrot, Mostapha El Yassa and Danielle Ducrot. Article: Spectral and Spatial Classification of High Resolution Urban Satellites Images using Haralick features and SVM with SAM and EMD distance Metrics. International Journal of Computer Applications 46(11):28-37, May 2012. Full text available. BibTeX

@article{key:article,
	author = {Aissam Bekkari and Soufian Idbraim and Azeddine Elhassouny and Driss Mammass Danielle Ducrot and Mostapha El Yassa and Danielle Ducrot},
	title = {Article: Spectral and Spatial Classification of High Resolution Urban Satellites Images using Haralick features and SVM with SAM and EMD distance Metrics},
	journal = {International Journal of Computer Applications},
	year = {2012},
	volume = {46},
	number = {11},
	pages = {28-37},
	month = {May},
	note = {Full text available}
}

Abstract

The classification of remotely sensed images knows a large progress taking into consideration the availability of images with different resolutions as well as the abundance of classification's algorithms. Support Vector Machines (SVMs) are a group of supervised classification algorithms that have been recently used in the remote sensing field, a number of works have shown promising results by the fusion of spatial and spectral information using SVM. For this purpose, we propose a methodology allowing to combine these two information. The SVM classification was conducted using a combination of multi-spectral features and Haralick texture features as data source. We have used homogeneity, contrast, correlation, entropy and local homogeneity, which were the best texture features to improve the classification algorithm. Two kernels have been considered, the RBF kernel based on Euclidean minimum distance (EMD) and a RBF kernel based on the Spectral Angle Mapper (SAM). The proposed approach was tested on common scenes of urban imagery. Results showed, especially with the use of Haralick texture features, that SVMs using RBF kernel based on EMD outperform the SVMs with RBF kernel based on SAM in term of the global accuracy and Kappa coefficeint. The experimental results indicate a mean accuracy value of 93. 406% for EMD kernel and 92. 896% for SAM kernel which is very promising.

References

  • Samson C. 2000. Contribution à la classification des images satellitaires par approche variationnelle et équations aux dérivées partielles : Thesis of doctorate, university of Nice-Sophia Antipolis.
  • Townshend, J. R. G. , 1992. Land cover. International Journal of Remote Sensing 13:1319–1328.
  • Hall, F. G. , Townshend, J. R. , Engman, E. T. , 1995. Status of remote sensing algorithms for estimation of land surface state parameters. Remote Sensing of Environment 51:138–156.
  • Lu, D. ,Weng, Q. , 2007. A survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing 28:823–870.
  • Huang, C. , Davis, L. S. , and Townshed, J. R. G. , 2002. An assessment of support vector machines for land cover classification. International Journal of Remote Sensing 23:725–749.
  • Kavzoglu, T. , Reis, S. , 2008. Performance analysis of maximum likelihood and artificial neural network classifiers for training sets with mixed pixels. GIScience and Remote Sensing 45:330–342.
  • Pal, M. , and Mather, P. M. 2005. Support vector machines for classification in remote sensing. International Journal of Remote Sensing, 26:1007?1011.
  • Zhu, G. , and Blumberg, D. G. 2002. Classification using ASTER data and SVM algorithms: The case study of Beer Sheva, Israel. Remote Sensing of Environment, 80:233-240.
  • Scholkopf, B. , Sung, K. , Burges, C. , Girosi, F. , Niyogi, P. , Poggio, T. , et al. 1997. Comparing support vector machines with gaussian kernels to radial basis function classifiers. IEEE Transactions on Signal Processing, 45:2758?2765.
  • Cao X. , Chen J. , Imura H. , Higashi O. , 2009. A SVM-based method to extract urban areas from DMSP-OLS and SPOT VGT data. Remote Sensing of Environment 113:2205–2209.
  • Inglada J. , 2007. Automatic recognition of man-made objects in high resolution optical remote sensing images by SVM classification of geometric image features. ISPRS Journal of Photogrammetry & Remote Sensing 62: 236–248.
  • Kruse, F. A. , Lekoff, A. B. , Boardman, J. W. , Heidebrecht K. B. , Shapiro, A. T. , Barloon, P. J. and Goetz, A. F. H. 1993. The Spectral Image Processing System (SIPS) – interactive visualization and analysis of imaging spectrometer data. Remote Sensing of Environment, 44 : 145-163.
  • De Carvalho, O. A. and Meneses, P. R. 2000. Spectral Correlation Mapper (SCM): An Improvement on the Spectral Angle Mapper (SAM). NASA JPL AVIRIS Workshop.
  • Chang, C. -I. 2000. An information theoretic-based approach to spectral variability, similarity and discriminability for hyperspectral image analysis," IEEE Trans. Inf. Theory 46(5):1927–1932.
  • Robila, S. A. 2005. Using spectral distances for speedup in hyperspectral image processing. International Journal of Remote Sensing 26(24): 5629-5650.
  • Angelopoulou, E. , Lee, S. and Bajcsy, R. 1999. Spectral gradient: a material descriptor invariant to geometry and incident illumination. The Seventh IEEE International Conference on Computer Vision, IEEE Computer Society, 861–867.
  • Keshava, N. , 2004. Distance metrics and band selection in hyperspectral processing with applications to material identification and spectral libraries. IEEE Transactions on Geoscience and Remote Sensing 42: 1552–1565.
  • Wang, Z. , Hu, G. , Zhou, Y. and Liu, X. 2008. A classification model of Hyperion image base on SAM combined decision tree. Proc. of SPIE 7146, 71461W.
  • Bekkari A. , Idbraim S. , Mammass D. and El yassa M. 2011. Exploiting spectral and space information in classification of high resolution urban satellites images using Haralick features and SVM. IEEE 2ed International Conference on Multimedia Computing and Systems ICMCS'11 , Ouarzazate, Morocco.
  • Fauvel M. , Benediktsson, J. A. , Chanussot J. and Sveinsson, J. R. , 2007. Spectral and Spatial Classi?cation of Hyperspectral Data Using SVMs and Morphological Pro?les. IEEE International Geoscience and Remote Sensing Symposium, IGARSS 07, Barcelona Spain.
  • Haralick, R. 1979. Statistical and structural approaches to texture. Proceedings of the IEEE 67:786–804
  • Ohanian, P. , Dubes, R. 1992. Performance evaluation for four classes of textural features. Pattern Recognition 25 :819–833
  • Chiu, W. Y. , and Couloigner I. 2004. Evaluation of incorporating texture into wetland mapping from multispectral images. University of Calgary, Department of Geomatics Engineering, Calgary, Canada, EARSeL eProceedings.
  • Gotlieb, C. C. , Kreyszig, H. E. 1990. Texture descriptors based on co-occurrence matrices. Computer Vision, Graphics and Image Processing 51:70–86
  • Haralick, R. M. , Shanmugam K. , and Dinstein I. , 1973. Textural Features for Image Classification. IEEE Transactions on Systems Man and Cybernetics.
  • Weszka, J. S. , Dyer, C. R. and Rosenfeld, A. 1976. A Comparative Study of Texture measures for Terrain Classification. IEEE Transactions on Systems Man and Cybernetics.
  • Conners, R. W. and Harlow, C. A. , 1980. A Theoretical Comaprison of Texture Algorithms. IEEE Transactions on Pattern Analysis and Machine Intelligence.
  • Conners, R. W. , Trivedi, M. M. , and Harlow, C. A. , 1984. Segmentation of a High-Resolution Urban Scene using Texture Operators. Computer Vision, Graphics and Image Processing.
  • Arvis V. ; Debain C. ; Berducat M. ; Benassi A. 2004). Generalization of the cooccurrence matrix for colour images: application to colour texture classification. Journal Image Analysis and Stereology, 23:63-72.
  • Chapel L. 2007. Maintenir la viabilité ou la résilience d'un système : les machines à vecteurs de support pour rompre la malédiction de la dimensionnalité ?. Thesis of doctorate, university of Blaise Pascal - Clermont II.
  • Aseervatham S. 2007. Apprentissage à base de Noyaux Sémantiques pour le traitement de données textuelles. Thesis of doctorate, university of Paris 13 –Galilée Institut Laboratory of Data processing of Paris Nord.
  • Bousquet O. , 2001. Introduction au Support Vector Machines (SVM). Center mathematics applied, polytechnique school of Palaiseau. http://www. math. u-psud. fr/~blanchard/gtsvm/index. html.
  • Keshava, N. and Boettcher, P. , 2001. On the relationships between physical phenomena, distance metrics, and best bands algorithms in hyperspectral processing. Proc. Of SPIE, 4381:55–67.
  • Fauvel M. , Chanussot J. and Benediktsson J. A. 2006. A Combined Support Vector Machines Classification Based on Decision Fusion. IEEE International Geoscience and Remote Sensing Symposium, IGARSS 06, Denver, USA.
  • Hsu, C. W. , Chang, C. C. , Lin, C. J. , 2008. A practical guide to support vector classification. http://www. csie. ntu. edu. tw/~cjlin/papers/guide/guide. pdf.
  • Chen, S. T. , Yu, P. S. , 2007. Real-time probabilistic forecasting of flood stages. Journal of Hydrology 340:63–77.
  • SVMlight Version: 6. 02 2008. Developed at University of Dortmund, Informatik, AI-Unit Collaborative Research Center on 'Complexity Reduction in Multivariate Data' (SFB475). http://svmlight. joachims. org/
  • Scholkopf, B. and Smola, A. J. 2002. Learning with Kernels, MIT Press.