Open AccessImproved MR image denoising via low‐ rank approximation and Laplacian‐of‐Gaussian edge detector
Author(s) -
Qiu Xiaoqun,
Chen Zhen,
Adnan Saifullah,
He Hongwei
Publication year - 2020
Publication title -
iet image processing
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.401
H-Index - 45
eISSN - 1751-9667
pISSN - 1751-9659
DOI - 10.1049/iet-ipr.2019.1648
Subject(s) - artificial intelligence , blob detection , gaussian noise , noise reduction , noise (video) , gaussian , computer vision , computer science , enhanced data rates for gsm evolution , pattern recognition (psychology) , laplace operator , detector , rank (graph theory) , mathematics , matching (statistics) , image quality , edge detection , image (mathematics) , image processing , statistics , physics , mathematical analysis , quantum mechanics , combinatorics , telecommunications
The low rank approximation for MR image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In spite of the great success of existing low rank approximation methods, these tend to lose the subtle edge texture when removing noise. It could degrade the image visual quality and affect the final clinical diagnosis. In this paper, a novel MR image denoising approach is proposed based on low rank approximation model and the Laplacian‐of‐Gaussian edge detector. In the proposed approach, a similarity evaluation scheme for noisy patch is employed to avoid the effect of the noise in the patch matching, and the details of the edge texture are preserved by the Laplacian‐of‐Gaussian edge detector. Experimental results show that the proposed approach is efficient and superior to some of the existing approaches in both objective criterion and visual fidelity. The proposed method can retrieve a clear MR image from the noisy one, with the detail of the edge texture, which could be very important in the clinical diagnosis.