Integrating Taylor–Krill herd‐based SVM to fuzzy‐based adaptive filter for medical image denoising. Issue 3 (6th February 2020)

• Record Type: Journal Article
• Authors: Narasimha, C.; Rao, A. Nagaraja
• Is Part Of: IET image processing. Volume 14:Issue 3(2020)
• Page Start: 442
• Page End: 450
• Publication Date: 2020-02-06
• Subjects: support vector machines -- adaptive filters -- optimisation -- medical image processing -- image denoising -- image filtering -- fuzzy set theory -- decision making -- search problems -- stochastic processes; Taylor–Krill herd‐based support vector machine -- Taylor–KH‐based SVM -- Taylor series -- KH optimisation algorithm -- SVM classifier -- Taylor–Krill herd‐based SVM -- medical image denoising -- medical imaging systems -- effective decision‐making -- medical devices -- fuzzy‐based adaptive filter -- optimal weights -- local optimisers -- adaptive operators -- stochastic search -- hyperplane parameters -- noisy pixels -- optimal identification -- peak signal‐to‐noise ratio -- PSNR -- structural similarity -- SSIM; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2018.6434
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Medical imaging systems contribute much towards effective decision‐making by the physicians, which is highly essential in the day‐to‐day life of humans. In this study, Taylor–Krill herd (KH)‐based support vector machine (SVM) is proposed for medical image denoising. The Taylor–KH‐based SVM is the integration of Taylor series in KH optimisation algorithm, which is used for tuning the optimal weights of the SVM classifier. The efficiency of KH is due to two global and two local optimisers, and the adaptive operators ensure the adaptive nature of KH. Above all, KH never uses the derivative information as it employs the stochastic search and thereby, reduces the complexity of the algorithm. The proposed method tunes the hyperplane parameters of SVM optimally so that the optimal identification of the noisy pixels in the image is ensured and replaced with adaptive weights. The proposed method is analysed based on the metrics, such as peak signal‐to‐noise ratio (PSNR), structural similarity (SSIM) and the comparative analysis is done with existing methods for showing the effectiveness of the proposed method. The simulation result shows that the proposed method acquired a PSNR of 30.36 dB and SSIM of 0.89, respectively.