Despeckling of Ultra sound Images using spatial filters - A Fusion Approach

Title

Despeckling of Ultra sound Images using spatial filters - A Fusion Approach

Creator

Nikesh P.; Raju G.

Description

Ultra sound images are normally affected by speckle noise which is typically multiplicative in nature. This study proposes different fusion based despeckling methods for ultra sound images. The output of existing spatial domain despeckling methods viz. Lee filter, Bayesian Non Local Means (BNLM) filter and Frost filter are fused pairwise. Fusion is implemented in two steps, first an inter-scale stationary wavelet coefficient fusion followed by an intra-scale wavelet coefficient fusion. Analysis of these projected despeckling strategies are conducted using metrics like Peak Signal to Noise Ratio (PSNR), Equivalent Number of Looks (ENL), Structural Similarity Index (SSIM) and Universal Image Quality Index (UIQI). The results show that the performance of fusion based methods is better than the respective individual filters for despeckling ultra sound images. 2019 IEEE.

Source

2019 International Conference on Data Science and Communication, IconDSC 2019

Date

2019-01-01

Publisher

Institute of Electrical and Electronics Engineers Inc.

Subject

BNLM; Frost; Fusion; LEE; speckle noise; Ultra sound image

Coverage

Nikesh P., School Of Computer Sciences, Mahathma Gandhi University, Kottayam, Kerala, India; Raju G., Department of CSE, Faculty of Engineering, Christ, Deemed to be University, Bengaluru, Karnataka, India

Rights

Restricted Access

Relation

ISBN: 978-153869319-3

Format

Online

Language

English

Type

Conference paper

Identifier

https://doi.org/10.1109/IconDSC.2019.8816989

https://www.scopus.com/inward/record.uri?eid=2-s2.0-85072775578&doi=10.1109%2fIconDSC.2019.8816989&partnerID=40&md5=bca12ce0f91ca313767173b0245359ab