Asian Journal of Information Technology
ISSN: Online 1993-5994ISSN: Print 1682-3915
Abstract
Weather forecasting applications use various pattern recognition techniques to analyze clouds information and other meteorological parameters. Different types of cloud appear in Advanced Very High Resolution Radiometer (AVHRR) image. The objective of this research is to classify the different types of clouds observed in a satellite cloud image. Image classification categorizes all pixels in a digital image into one of several classes or themes. Gray Level Co-Occurrence Matrix (GLCM) is used to extract features. All those features cannot be used precisely in classification. For precise usage, Opposition based Particle Swarm Optimization (OPSO) is used for optimization. In this study an image classification framework is developed with Support Vector Machine (SVM). Median filter is used for noise reduction. An efficient and effective image classifier system often consists of a defined set of classes. These precisely defined classes are well separated by a set of features that are typically derived from the multi-dimensional image data. Finally, SVM categorizes the image into four categories: namely clear sky, low level clouds, mid-level clouds and high level clouds.
How to cite this article:
G. Devika and S. Partha Sarathy. Modified Approach of Support Vector Machine for Classification of AVHRR Image Data.
DOI: https://doi.org/10.36478/ajit.2016.2328.2336
URL: https://www.makhillpublications.co/view-article/1682-3915/ajit.2016.2328.2336