USE OF SVM KERNEL FOR BETTER CLASSIFICATION ACCURACY FOR REMOTE SENSING DATA
Journal Title: International Journal of Engineering Sciences & Research Technology - Year 30, Vol 5, Issue 4
Abstract
The classification of remote sensing images is a challenging task, as image contains bulk of information which is to be carefully extracted and used. Support vector machine (SVM) has proven its excellence in the field of remote sensing image classification. Using SVM as a classifier multiple kernel methods can be constructed and tested over a specified set of image dataset. In this paper, we present a framework in which multiple SVM kernels are tested on a remotely sensed image for analysis of behaviour of kernel methods over image dataset. Pre-step to image classification is feature extraction on the basis of which image is classified. In our system, the image is classified into two classes on the basis of colour feature of image. Accuracy of each kernel along with delay in image classification is calculated for the task of kernel optimization over remotely sensed image. Thus a set of best suited kernel methods can be identified over a specific dataset.
Authors and Affiliations
Neha V. Mankar
Keywords
Related Articles
- EP ID EP154090
- DOI 10.5281/zenodo.49809
- Views 63
- Downloads 0
Study of CFG and System calls for Computer Virus Detection
Computer viruses are big threat to computer world; researchers doing work in this area have made various efforts in the direction of classification and detection methods of these viruses. Graph mining, system call...
STRENGTH EVALUATION OF FIBER REINFORCED CONCRETE USING POZZOLANAS
High-performance concrete is defined as concrete that meets special combinations of performance and uniformity requirements that cannot always be achieved routinely using conventional constituents and normal mixin...
A COMBINED CLOUD ARCHITECTURE FOR PREVENTION OF DUPLICATION AND ANONYMOUS USER AUTHENTICATION
Cloud computing is a rising computing standard in which assets of the computing framework are given as a service over the Internet. As guaranteeing as it may be, this standard additionally delivers a lot of people...
Alert Aggregation Agent
Intrusion detection technique is important subtask that aggregates alert. Alert aggregation goal is to identify & to cluster different alert belonging to a specific attack instance which has been initiated by...
Understanding the Self Compacting Concrete & Its Fresh Properties
A new kind of high performance concrete (HPC) i.e. self compacting concrete has been first developed in Japan in 1986. The development of SCC has made casting of dense reinforcement and mass concrete convenient, h...