PERFORMANCE EVALUATION OF SVM KERNELS ON MULTISPECTRAL LISS III DATA FOR OBJECT CLASSIFICATION

Publications

Share / Export Citation / Email / Print / Text size:

International Journal on Smart Sensing and Intelligent Systems

Professor Subhas Chandra Mukhopadhyay

Exeley Inc. (New York)

Subject: Computational Science & Engineering, Engineering, Electrical & Electronic

GET ALERTS

eISSN: 1178-5608

DESCRIPTION

19
Reader(s)
64
Visit(s)
0
Comment(s)
0
Share(s)

VOLUME 10 , ISSUE 4 (December 2017) > List of articles

PERFORMANCE EVALUATION OF SVM KERNELS ON MULTISPECTRAL LISS III DATA FOR OBJECT CLASSIFICATION

S.V.S. Prasad / T. Satya Savithri / Iyyanki V. Murali Krishna

Keywords : SVM, LibSVM, Kernels, Object based classification, Transformed Divergence

Citation Information : International Journal on Smart Sensing and Intelligent Systems. Volume 10, Issue 4, Pages 829-844, DOI: https://doi.org/10.21307/ijssis-2018-020

License : (BY-NC-ND 4.0)

Received Date : 02-October-2017 / Accepted: 17-November-2017 / Published Online: 01-December-2017

ARTICLE

ABSTRACT

Object based classification plays an important role in every field. Support vector machine is the popular algorithm for object based classification. Support vector machine classifies the data points using straight line. Some datasets are impossible to separate by straight line. To cope with this problem kernel function is used. The central idea of kernel function is to project points up in a higher dimensional space hoping that separability of data would improve. There are various kernels in the LIBSVM package. In this paper, Support Vector Machine (SVM) is evaluated as classifier with four different kernels namely linear kernel, polynomial kernel, radial basis function kernel and sigmoid kernel. Several datasets are being experimented to find out the performance of various kernels of SVM .By changing the value of ‘C’ and γ varying results are observed. Among these RBF kernel with a value of C = 1000 and gamma=0.75 got an excellent accuracy of 99.1509%.The SVM-RBF kernel gave an edge over the other kernels with an accuracy of 99.1509% while linear at 98.9623%, polynomial at 98.6792% and Sigmoid at 98.5849%.

Content not available PDF Share

FIGURES & TABLES

REFERENCES

[1] Mahendra H N, Shivakumar B R and Praveen J, “Pixel-based Classification of Multispectral Remotely Sensed Data Using Support Vector Machine Classifier”, National Conference on Advanced Innovation in Engineering and Technology (NCAIET-2015) Alva’s Institute of Engineering and Technology, Moodbidri Vol. 3, Special Issue 1, April 2015. 
[2] Huang, Chengquan, John RG Townshend, Shunlin Liang, Satya NV Kalluri, and Ruth S. DeFries, "Impact of sensor's point spread function on land cover characterization: assessment and deconvolution." Remote Sensing of Environment, Vol. 80, no. 2,2002, pp. 203-212. 
[3] Dixon, B., and Nivedita Candade, "Multispectral land use classification using neural networks and support vector machines: one or the other, or both?."International Journal of Remote Sensing, Vol.29, no.4,2008, pp.1185-1206.
[4] Melgani,F, and Bruzzone,L, “Classification of hyperspectral remote sensing images with support vector machines”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 42,no. 8, 2004,pp. 1778-1790.
[5] Huang, C, Davis, L.S., and Townshend, J.R.G., “An assessment of support vector machines for land cover classification”, Int. journal of Remote Sensing, Vol. 23, no. 4, 2002, pp. 725-749.
[6] Aiying Zhang and Ping Tang, “Fusion algorithm of pixel based and object based classifier for remote sensing image classification”, IEEE Transactions on Geo science and Remote Sensing Symposium(IGARSS), Beijing, China, 2013, pp. 2740-2743.
[7] Devadasa, R, Denhama, R.J and Pringle,M, “Support vector machine classification of object based data for crop mapping, using multi temporal landsat imagery”, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. XXXIX B7, 2012.
[8] Zhu, G and Blumberg,D.G., “Classification using ASTER data and SVM algorithms; The case study of Beer Sheva, Israel”, Remote Sensing of Environment, Vol. 80, no. 2, 2002,pp. 233-240.
[9] Su, L, Chopping, M. J., Rango, A, Martonchik, J. V., and Peters, D. P. C. , “Support vector machines for recognition of semi-arid vegetation types using MISR multiangle imagery”, Remote Sensing of Environment, Vol. 107, no. 1-2,2007, pp. 299-311.
[10] Muñoz-Marí, J, Bruzzone, L and Camps-Valls, G., “A support vector domain description approach to supervised classification of remote sensing images”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 45, 2007, pp.2683-2692.
[11] Gómez-Chova L, Camps-Valls G, Muñoz-Marí J and Calpe J., “ Semi supervised image classification with laplacian support vector machines”, IEEE Transactions on Geoscience and Remote Sensing, Vol. 5, 2008,pp.336-340.
[12] Gianinetto M., Rusmini M., Candiani G., Dalla Via G., Frassy F., Maianti P., Marchesi A., Rota Nodari F., and Dini L., “Hierarchical classification of complex landscape with VHR pan-sharpened satellite data and OBIA techniques”, European Journal of Remote Sensing, Vol.47, 2014, pp.229-250.
[13] Mountrakis , G., Im, J. and Ogole, C., “Support Vector Machines in Remote Sensing: A Review”, ISPRS Journal of Photogrammetry and Remote Sensing, Vol.66, 2011, pp.247-259.
[14] Rokni Deilmai, B, Bin Ahmad, B, and Zabihi,H, “Comparison of two classification methods (MLC and SVM) to extract land use and land cover in Johor Malaysia”,7th IGRSM International Remote Sensing & GIS Conference and Exhibition IOP Conf. Series: Earth and Environmental Science,Vol.20,2014.
[15] Abbas T, Fereydoon S, Amin M, Chamran Taghati Hossien P, and Amir Hossein Esmaile S “Land Use Classification using Support Vector Machine and Maximum Likelihood Algorithms by Landsat 5 TM Images”, Walailak J Sci & Tech vol.12 ,no 8,2015, pp, 681-687.
[16] Zylshal, Sulma, S., Yulianto, F. Nugroho J, and Sofan,P, “A support vector machine object based image analysis approach on urban green space extraction using Pleiades-1A imagery “, Model. Earth Syst. Environ. 2016, Vol. 54,no.2, 2016,pp.1-12.
[17] Yekkehkhany, B, Safari, A, Homayouni, S, and Hasanlou, M., “A Comparison Study of Different Kernel Functions for SVM-based Classification of Multi-temporal Polarimetry SAR Data”, The International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences, suppl. W3 XL.2, 2015, pp.281-285.
[18] Okwuashi, Onuwa and Isaac Ikediashi Dubem “One-Againist-all remote sensing image classification using support vector machine”, European Scientific Journal, vol 10. No27 pp,Sep 2014, 304-314.
[19] Izquierdo-Verdiguier, E, Gómez-Chova, L, Bruzzone,L and Camps-Valls, G,"Semisupervised Kernel Feature Extraction for Remote Sensing Image Analysis," in IEEE Transactions on Geoscience and Remote Sensing, vol. 52, no. 9, 2014, pp. 5567-5578.
[20] Rupali, A, Surase,R, Karbhari, B and Kale, V, “Performance Evaluation of Support Vector Machine and Maximum Likelihood Classifier For Multiple Crop Classification”, International Journal of Remote Sensing & Geoscience (IJRSG), Vol. 4,no. 1, 2015.
[21] Vikas Sharma, Diganta Baruah, Dibyajyoti Chutia, Raju, PLN, and Bhattacharya, DK, “An Assessment of Support Vector Machine Kernel Parameters using Remotely Sensed Satellite Data”,IEEE International Conference On Recent Trends In Electronics Information Communication Technology, 2016.
[22] Alim Samat , Paolo Gamba, Jilili Abuduwaili, Sicong Liu and Zelang Miao, “ Geodesic Flow Kernel Support Vector Machine for Hyperspectral Image Classification by Unsupervised Subspace Feature Transfer”, Remote Sens. Vol.8,no.3, 2016, pp.1- 23.
[23] Samat, A., Li, J., Liu, S., Du, P., Miao, Z. and Luo, J., “Improved hyperspectral image classification by active learning using pre-designed mixed pixels”,. Pattern Recognit. Vol.51,2016,pp. 43–58.
[24] Aiye Shi, Hongmin Gao, Zhenyu He, Min Li and Lizhong Xu, “A Hyperspectral Band Selection based on Game Theory and Differential Evolution Algorithm”, International Journal on Smart Sensing and Intelligent Systems, Vol.9, no,4, 2016, pp.1971-1990.
[25] Prasad , S.V.S., Satya Savithri,T, and Iyyanki V. Murali Krishna, “Comparison of Accuracy Measures for RS Image Classification using SVM and ANN Classifiers”, International Journal of Electrical and Computer Engineering (IJECE), Vol. 7, no. 3, 2017, pp. 1180-1187.
[26] Benqin Song, Peijun Li, Senior Member, Jun Li, and Antonio Plaza, “One-Class Classification of Remote Sensing Images Using Kernel Sparse Representation “ IEEE Journal of Selected topics in Applied Earth Observations and Remote Sensing, Vol. 9, no. 4, 2016 pp: 1613-1623.

EXTRA FILES

COMMENTS