Clustering of Satellite Images using Big Data Platform Spark |
Author(s): |
| G. Ramya , Rathinam Technical Campus; S. Yamini, Rathinam Technical Campus; M. Pavithra, Rathinam Technical Campus |
Keywords: |
| Satellite Images, Clustering, Scalable K- Means++, Distributed Processing, Spark, Bisecting K- Means, Gaussian Mixture |
Abstract |
|
Clustering is the task of grouping a set of objects in such a way that objects in the same group are more similar to each other than to those in other groups. Image clustering used as a crucial step in mining of satellite images. Comparing to previous decades, satellite imagery is getting generated at higher rate. So we should have better solutions for that in terms of accuracy as well as performance. In this paper, we are proposing solution over big data platform Apache Spark which carry out the clustering of images using different methods Gaussian Mixture, Scalable K++, Bisecting K. These methods will not provide the details of no of clusters in advance. We are proposing an algorithm called best of breed to validate the no of clusters and provides best clustering. |
Other Details |
|
Paper ID: IJSRDV6I10576 Published in: Volume : 6, Issue : 1 Publication Date: 01/04/2018 Page(s): 860-863 |
Article Preview |
|
|
|
|
