ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Adaptive Weighted Minimax-Concave Penalty Based Dictionary Learning for Brain MR Images

Pokala, PK and Chemudupati, S and Seelamantula, CS (2020) Adaptive Weighted Minimax-Concave Penalty Based Dictionary Learning for Brain MR Images. In: 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI), 3-7 April 2020, Iowa City, IA, USA, pp. 1929-1932.

[img] PDF
INT_SYM_BIO_IMA_2020-APRIL_1929-1932_2020.pdf - Published Version
Restricted to Registered users only

Download (899kB) | Request a copy
Official URL: https://dx.doi.org/10.1109/ISBI45749.2020.9098517

Abstract

We consider adaptive weighted minimax-concave (WMC) penalty as a generalization of the minimax-concave penalty (MCP) and vector MCP (VMCP). We develop a computationally efficient algorithm for sparse recovery considering the WMC penalty. Our algorithm in turn employs the fast iterative soft-thresholding algorithm (FISTA) but with the key difference that the threshold is adapted from one iteration to the next. The new sparse recovery algorithm when used for dictionary learning has a better representation capability as demonstrated by an application to magnetic resonance image denoising. The denoising performance turns out to be superior to the state-of-the-art techniques considering the standard performance metrics namely peak signal-to-noise ratio (PSNR) and structural similarity index metric (SSIM). © 2020 IEEE.

Item Type: Conference Paper
Publication: Proceedings - International Symposium on Biomedical Imaging
Publisher: IEEE Computer Society
Additional Information: cited By 0; Conference of 17th IEEE International Symposium on Biomedical Imaging, ISBI 2020 ; Conference Date: 3 April 2020 Through 7 April 2020; Conference Code:160183
Keywords: Image denoising; Image segmentation; Magnetic resonance imaging; Medical imaging; Signal to noise ratio, Computationally efficient; Dictionary learning; Peak signal to noise ratio; Soft-thresholding algorithm; Standard performance; State-of-the-art techniques; Structural similarity indices; Weighted minimax, Iterative methods
Department/Centre: Division of Electrical Sciences > Electrical Engineering
Date Deposited: 13 Oct 2020 11:19
Last Modified: 13 Oct 2020 11:19
URI: http://eprints.iisc.ac.in/id/eprint/65865

Actions (login required)

View Item View Item