MODIFIED NLM MODEL FOR DESPECKLING ULTRASOUND IMAGES USING FCM CLUSTERING BASED PRE CLASSIFICATION AND RIBM

Abstract
Speckle noise is an inherent characteristic of ultrasound which reduces the classification accuracy of computer aided diagnosis (CAD) systems. A modified non local means (NLM) filter for despeckling ultrasound images is proposed in this article. The proposed NLM model utilizes a preclassification method in which the feature vectors of the input image are constructed using moment invariants and then they are clustered using fuzzy c means (FCM) algorithm. The rotationally invariant block matching (RIBM) algorithm is applied among the blocks within each cluster instead of the entire image. This intra cluster block matching reduces computational complexity of NLM process without the elimination of any pixel candidate. Further, the rotationally invariant moment distance measure improves the noise reduction performance of the algorithm by increasing the chance of getting more similar candidates for NLM process. Extensive experiments are conducted using synthetic images, phantom images and ultrasound images. The method is comparatively evaluated with other denoising methods using statistical parameters such as MSE, PSNR, SSIM, EPI and ENL. The quantitative results suggested that the proposed method outperforms other four state of the art methods in despeckling and preservation of image details.

Authors
K M Prabusankarlal1, P Thirumoorthy2, R Manavalan3, R Sivaranjani4
K.S. Rangasamy College of Arts and Science, India1, Government Arts College, Dharmapuri, India2, Arignar Anna Government Arts College, India3, K.S.R College of Arts and Science for Women, India4

Keywords
Speckle Noise, Non Local Means, Fuzzy C Means, Ultrasound, CAD Systems
Published By :
ICTACT
Published In :
ICTACT Journal on Image and Video Processing
( Volume: 8 , Issue: 3 )
Date of Publication :
Februray 2018
DOI :

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.