International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 105 - Number 11 |
Year of Publication: 2014 |
Authors: Gurudatta V Nayak, Anuja A Rao, Nandana Prabhu |
10.5120/18421-9723 |
Gurudatta V Nayak, Anuja A Rao, Nandana Prabhu . K-Means Clustering Algorithm with Color-based Thresholding for Satellite Images. International Journal of Computer Applications. 105, 11 ( November 2014), 17-20. DOI=10.5120/18421-9723
Land cover classification is an essential input to environmental and land use planning . Clustering is a technique used for land cover classification. Clustering is the assignment of objects into groups called clusters so that objects from the same cluster are more similar to each other than objects from different clusters. The proposed work presents an algorithm Using K means clustering algorithm with color based thresholding for classification of a satellite image. It is observed that this method gives better accuracy as compared using only K means clustering algorithm. The image quality metrics used are overall accuracy, user's accuracy, producer accuracy, average accuracy for user and producer.