SVM Classification of Urban High-Resolution Imagery Using Composite Kernels and Contour Information
Journal Title: International Journal of Advanced Computer Science & Applications - Year 2013, Vol 4, Issue 7
Abstract
The classification of remote sensing images has done great forward taking into account the image’s availability with different resolutions, as well as an abundance of very efficient classification algorithms. A number of works have shown promising results by the fusion of spatial and spectral information using Support Vector Machines (SVM) which are a group of supervised classification algorithms that have been recently used in the remote sensing field, however the addition of contour information to both spectral and spatial information still less explored. For this purpose we propose a methodology exploiting the properties of Mercer’s kernels to construct a family of composite kernels that easily combine multi-spectral features and Haralick texture features as data source. The composite kernel that gives the best results will be used to introduce contour information in the classification process. The proposed approach was tested on common scenes of urban imagery. The three different kernels tested allow a significant improvement of the classification performances and a flexibility to balance between the spatial and spectral information in the classifier. The experimental results indicate a global accuracy value of 93.52%, the addition of contour information, described by the Fourier descriptors, Hough transform and Zernike moments, allows increasing the obtained global accuracy by 1.61% which is very promising.
Authors and Affiliations
Aissam Bekkari, Mostafa yassa, Soufiane Idbraim, Driss Mammass, Azeddine Elhassouny, Danielle Ducrot
Keywords
Related Articles
- EP ID EP125643
- DOI 10.14569/IJACSA.2013.040718
- Views 117
- Downloads 0
SIP Signaling Implementations and Performance Enhancement over MANET: A Survey
The implementation of the Session Initiation Protocol (SIP)-based Voice over Internet Protocol (VoIP) and multimedia over MANET is still a challenging issue. Many routing factors affect the performance of SIP signaling a...
Comparative Analysis of Various Methods Treatment Expert Assessments
The paper deals with the problem of choosing the most effective methods of processing expert information if there are several results of expert evaluation on the problem. The problem of levelling expert assessments, whic...
Improved Langley and Ratio Langley Methods for Improving Sky-Radiometer Accuracy
Improved Langley Method (ILM) is proposed to improve the calibration accuracy of the sky-radiometer. The ILM uses that the calibration coefficients of other arbitrary wavelengths can be presumed from the calibration coef...
Light but Effective Encryption Technique based on Dynamic Substitution and Effective Masking
Cryptography and cryptanalysis are in ever-lasting struggle. As the encryption techniques advance, the cryptanalysis techniques advance as well. To properly face the great danger of the cryptanalysis techniques, we shoul...
Analysis of the Impact of Different Parameter Settings on Wireless Sensor Network Lifetime
The importance of wireless sensors is increasing day by day due to their large demand. Sensor networks are facing some issues in which battery lifetime of sensor node is critical. It depends on the nature and application...