Open AccessSAR image despeckling in directionlet domain based on edge detection
Author(s) -
Sethunadh R.,
Thomas T.
Publication year - 2013
Publication title -
electronics letters
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.375
H-Index - 146
ISSN - 1350-911X
DOI - 10.1049/el.2012.4533
Subject(s) - artificial intelligence , edge detection , computer vision , image (mathematics) , enhanced data rates for gsm evolution , computer science , domain (mathematical analysis) , pattern recognition (psychology) , image processing , mathematics , mathematical analysis
Presented is a novel directionally adaptive despeckling algorithm for a SAR image using a multi‐direction anisotropic wavelet transform, called a directionlet . It efficiently extracts edge information along dominant directions from the spatially segmented SAR image. Then an optimal scale dependent subband adaptive threshold, based on the generalised cross‐validation technique, is applied to the edge removed image. The despeckled image is finally synthesised using the extracted edge information to preserve the sharpness of edges and the texture. The proposed scheme outperforms many of the traditional despeckling schemes such as the Lee filter and the wavelet and bandlet based edge detection methods in terms of numeric and perceptual quality.