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 112
- Downloads 0
Applications of Some Topological Near Open Sets to Knowledge Discovery
In this paper, we use some topological near open sets to introduce the rough set concepts such as near open lower and near open upper approximations. Also, we study the concept of near open, rough set and some of their b...
Developing A Model to Predict the Occurrence of the Cardio-Cerebrovascular Disease for the Korean Elderly using the Random Forests Algorithm
This study aimed to develop a model for predicting the cardio-cerebrovascular disease of the South Korean elderly using the random forests technique. This study analyzed 2,111 respondents (879 males and 1,232 females), w...
Roadmap to Project Management Office (PMO) and Automation using a Multi-Stage Fuzzy Rules System
The Project Management Office (PMO) has proven to be a successful approach to enhance the control on projects and improve their success rate. One of the main functions of the PMO is monitoring projects and ensuring that...
A New CAD System for Breast Microcalcifications Diagnosis
Breast cancer is one of the most deadly cancers in the world, especially among women. With no identified causes and absence of effective treatment, early detection remains necessary to limit the damages and provide possi...
Validating Utility of TEIM: A Comparative Analysis
Concrete efforts to integrate Software Engineering and Human Computer Interaction exist in the form of models by many researchers. An unconventional model called TEIM (The Evolved Integrated Model) of Software Engineerin...