Speckle Noise Reduction in SAR Images Using Fuzzy Inference System

Speckle Noise Reduction in SAR Images Using Fuzzy Inference System

S Vijayakumar (VIT University, Vellore, India) and V. Santhi (VIT University, Vellore, India)
Copyright: © 2019 |Pages: 24
DOI: 10.4018/IJFSA.2019100104


In recent years, image processing has played a vital role in major research areas. In this article, a new approach using a fuzzy inference system is proposed for speckle reduction in SAR images. In general, SAR images are predominantly used to monitor coastal regions to detect oil spills, ship wake, sea shores and climate changes. In this article, a gamma distribution model is used in a fuzzy inference system to remove speckle noise from SAR images. The performance of the proposed model is tested using fuzzy inference systems, such as mamdani and sugeno. The experimental results proved the efficiency of the proposed system through objective metrics.
Article Preview

Literature Review

The presence of noise removal operation is one of the important and challenging tasks in image applications. In this section, a brief literature review on speckle noise removal approaches is presented.

In 2006, Yilun Chen et al. have proposed a new approach to remove speckle noise from SAR data. The approach presented is based on similar scattering technique between the central pixel and neighborhood pixels. In this work the local statistics of different pixels in the neighborhood window is analyzed for its contributions according to fuzzy membership values. The experiments are carried out using the national Aeronautics and Space Administration Jet Propulsion Laboratory airborne SAR data. The performance analysis of the proposed work is carried out by comparing it with existing traditional filters which is uses box-car window. The proposed approach exploits uniform properties in SAR data in performing filtering operations.

Complete Article List

Search this Journal:
Open Access Articles: Forthcoming
Volume 9: 4 Issues (2020): Forthcoming, Available for Pre-Order
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2013)
Volume 2: 4 Issues (2012)
Volume 1: 4 Issues (2011)
View Complete Journal Contents Listing