Impact Factor : 6.225 
PAPER ID:IJIM/V.II(IV)/ 184-192/28
AUTHOR: Manpreet Kaur and Saranjeet Singh
TITLE: IMPROVED NON LOCAL MEANS METHOD FOR SONAR IMAGE DENOISING
ABSTRACT: : Due to poor visibility conditions, the underwater rich in abundant resource is still not well explored. The imaging technique is one of the methods to reveal the hidden treasure to the world. For this purpose optical imaging technique is used. Optical images suffer from poor visibility condition due to limited range of light and attenuation. So SONAR images based on acoustic or “Echo Sounding” principle, which suffers less attenuation, is used for exploring the underwater. Sonar photos are laid low with spatially varying clutters. Moreover there’s a robust ardor in knowing what lies in underwater, So Side Scan SONAR device is used in underwater to capture the sea ground which hides maximum of the treasure. Sonar images play a critical position in oil exploration, mine’s detection navigation, seabed mapping, fishing, ocean drilling, and etc. Therefore it will become a difficult challenge to captured sonar images that are susceptible to speckle noises, ambient noises, and so on. To dispose of noise from the picture without affecting the high-quality edges and edge maintaining filters need to be applied. So that a variety of methods have been introduced to remove noise from sonar images. However, many algorithms remove the fine details and structure of the image. Over the years a variety of methods have been introduced to remove noise from sonar images, such as Gaussian filtering, anisotropic filtering, and Total Variation minimization. However, many of these algorithms remove the fine details and structure of the image in addition to the noise because of assumptions made about the frequency content of the image. The non-local means algorithm does not make these assumptions, but instead assumes that the image contains an extensive amount of redundancy. These redundancies can then be exploited to remove the noise in the image. This project will implement the non-local means algorithm and compare it to other denoising methods using the method noise measurement. The main focus of this work is to propose an improved non-local means algorithm addressing the preservation of structure in a sonar image.
KEYWORDS:Side Scan Sonar imaging, Non Local Means, Method Noise, Poisson Noise.
Click here to download fulltext