Improved feature extraction scheme for satellite images using NDVI and NDWI technique based on DWT and SVD

Abstract

In this paper, an improved feature extraction technique using Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI) with discrete wavelet transform (DWT) and singular value decomposition (SVD) enhancement approach has been proposed. DWT-SVD is used for quality improvement of the low-contrast satellite images. The NDVI and NDWI have been successfully used to delineate vegetation land cover and surface water features. The method employs multispectral remote sensing data technique to find spectral signature of different objects such as vegetation index and water body classification presented in the satellite image. The input image is decomposed into the four frequency subbands through DWT, and then obtains the singular value matrix of the low–low thresholded subband image, and finally, it reconstructs the enhanced image by applying inverse DWT. The basic enhancement occurs due to scaling of singular values of DWT coefficients. The simulation results clearly show the increased efficiency and flexibility of the proposed method over existing methods such as decorrelation stretching technique.