Mining images using clustering and data compressing techniques

Abstract

Satellite images of clouds play a significant role in predicting weather conditions. Frequency of image acquisition varies from one image per minute to one image per hour depending on the climatic conditions. These phenomena result in huge collection and creation of image data warehouse. Permanent storage and transmission of images is a challenging task. In this paper, data mining clustering technique along with Vector Quantisation (VQ) is applied to cluster and compress static colour image. Results are shown to demonstrate the findings both subjectively and visually.