Retrieval of Remote Sensing Images Using Fused Color and Texture Features with K-Means Clustering

Abstract

In the advancement of remote sensing satellite sensors, a large number of high-resolution satellite images are captured every day. To retrieve the required images from a large database has become a challenge. Here, we have used fused color and texture feature for retrieving remote sensing image. Here, we used HSV Histogram, Color moment and color autocorrelogram for color feature extraction. A wavelet transform is used for texture feature extraction. These combined color and texture are used for indexing using k-means clustering. Manhattan distance is also used for similarity matching. UC Merced Land use Land Cover Dataset has been used for the experiment. The k-means clustering with combined color and texture features has shown better retrieval performance than only color features. Indexing has been done using Manhattan distance and k-means clustering. K-means clustering gives better retrieval performance than Manhattan Distance.