An MMSE approach to nonlocal image denoising: Theory and practical implementation

Chul Lee; Chulwoo Lee; Chang-Su Kim

doi:10.1016/j.jvcir.2012.01.007

An MMSE approach to nonlocal image denoising: Theory and practical implementation

Chul Lee, Chulwoo Lee, Chang-Su Kim

Research output: Contribution to journal › Article › peer-review

11 Citations (Scopus)

Abstract

A nonlocal minimum mean square error (MMSE) image denoising algorithm is proposed in this work. Based on the Bayesian estimation theory, we first derive that the conventional nonlocal means filter is an MMSE estimator in the special case of noise-free nonlocal neighbors. Then, we develop the nonlocal MMSE denoising filter that can minimize the mean square error (MSE) of a denoised block in more general cases of noisy nonlocal neighbors. Furthermore, the proposed algorithm searches nonlocal neighbors from an external database as well as the entire input image to improve the performance even when a noisy block may not have similar blocks within the image. Since the extended search range demands a higher computational burden, we develop a probabilistic tree-based search method to reduce the computational complexity. Simulation results show that the proposed algorithm provides significantly better denoising performance than the conventional nonlocal means filter.

Original language	English
Pages (from-to)	476-490
Number of pages	15
Journal	Journal of Visual Communication and Image Representation
Volume	23
Issue number	3
DOIs	https://doi.org/10.1016/j.jvcir.2012.01.007
Publication status	Published - 2012 Apr

Bibliographical note

Funding Information:
This work was supported partly by the Global Frontier R&D Program on Human-centered Interaction for Coexistence, funded by the NRF of Korea grant funded by the Korean Government (MEST) (NRF-M1AXA003-2011-0031648), and partly by Basic Science Research Program through the NRF funded by the MEST (2011- 0001271).

Keywords

Bayesian estimation
External database
Image denoising
Image restoration
Minimum mean square error (MMSE) denoising
Noisy nonlocal neighbors
Nonlocal means filter
Probabilistic tree search

ASJC Scopus subject areas

Signal Processing
Media Technology
Computer Vision and Pattern Recognition
Electrical and Electronic Engineering

Access to Document

10.1016/j.jvcir.2012.01.007

Cite this

@article{b472a618a11d4e29a8bcb55bd4e5544c,

title = "An MMSE approach to nonlocal image denoising: Theory and practical implementation",

abstract = "A nonlocal minimum mean square error (MMSE) image denoising algorithm is proposed in this work. Based on the Bayesian estimation theory, we first derive that the conventional nonlocal means filter is an MMSE estimator in the special case of noise-free nonlocal neighbors. Then, we develop the nonlocal MMSE denoising filter that can minimize the mean square error (MSE) of a denoised block in more general cases of noisy nonlocal neighbors. Furthermore, the proposed algorithm searches nonlocal neighbors from an external database as well as the entire input image to improve the performance even when a noisy block may not have similar blocks within the image. Since the extended search range demands a higher computational burden, we develop a probabilistic tree-based search method to reduce the computational complexity. Simulation results show that the proposed algorithm provides significantly better denoising performance than the conventional nonlocal means filter.",

keywords = "Bayesian estimation, External database, Image denoising, Image restoration, Minimum mean square error (MMSE) denoising, Noisy nonlocal neighbors, Nonlocal means filter, Probabilistic tree search",

author = "Chul Lee and Chulwoo Lee and Chang-Su Kim",

note = "Funding Information: This work was supported partly by the Global Frontier R&D Program on Human-centered Interaction for Coexistence, funded by the NRF of Korea grant funded by the Korean Government (MEST) (NRF-M1AXA003-2011-0031648), and partly by Basic Science Research Program through the NRF funded by the MEST (2011- 0001271). ",

year = "2012",

month = apr,

doi = "10.1016/j.jvcir.2012.01.007",

language = "English",

volume = "23",

pages = "476--490",

journal = "Journal of Visual Communication and Image Representation",

issn = "1047-3203",

publisher = "Academic Press Inc.",

number = "3",

}

TY - JOUR

T1 - An MMSE approach to nonlocal image denoising

T2 - Theory and practical implementation

AU - Lee, Chul

AU - Lee, Chulwoo

AU - Kim, Chang-Su

N1 - Funding Information: This work was supported partly by the Global Frontier R&D Program on Human-centered Interaction for Coexistence, funded by the NRF of Korea grant funded by the Korean Government (MEST) (NRF-M1AXA003-2011-0031648), and partly by Basic Science Research Program through the NRF funded by the MEST (2011- 0001271).

PY - 2012/4

Y1 - 2012/4

N2 - A nonlocal minimum mean square error (MMSE) image denoising algorithm is proposed in this work. Based on the Bayesian estimation theory, we first derive that the conventional nonlocal means filter is an MMSE estimator in the special case of noise-free nonlocal neighbors. Then, we develop the nonlocal MMSE denoising filter that can minimize the mean square error (MSE) of a denoised block in more general cases of noisy nonlocal neighbors. Furthermore, the proposed algorithm searches nonlocal neighbors from an external database as well as the entire input image to improve the performance even when a noisy block may not have similar blocks within the image. Since the extended search range demands a higher computational burden, we develop a probabilistic tree-based search method to reduce the computational complexity. Simulation results show that the proposed algorithm provides significantly better denoising performance than the conventional nonlocal means filter.

AB - A nonlocal minimum mean square error (MMSE) image denoising algorithm is proposed in this work. Based on the Bayesian estimation theory, we first derive that the conventional nonlocal means filter is an MMSE estimator in the special case of noise-free nonlocal neighbors. Then, we develop the nonlocal MMSE denoising filter that can minimize the mean square error (MSE) of a denoised block in more general cases of noisy nonlocal neighbors. Furthermore, the proposed algorithm searches nonlocal neighbors from an external database as well as the entire input image to improve the performance even when a noisy block may not have similar blocks within the image. Since the extended search range demands a higher computational burden, we develop a probabilistic tree-based search method to reduce the computational complexity. Simulation results show that the proposed algorithm provides significantly better denoising performance than the conventional nonlocal means filter.

KW - Bayesian estimation

KW - External database

KW - Image denoising

KW - Image restoration

KW - Minimum mean square error (MMSE) denoising

KW - Noisy nonlocal neighbors

KW - Nonlocal means filter

KW - Probabilistic tree search

UR - http://www.scopus.com/inward/record.url?scp=84862816934&partnerID=8YFLogxK

U2 - 10.1016/j.jvcir.2012.01.007

DO - 10.1016/j.jvcir.2012.01.007

M3 - Article

AN - SCOPUS:84862816934

SN - 1047-3203

VL - 23

SP - 476

EP - 490

JO - Journal of Visual Communication and Image Representation

JF - Journal of Visual Communication and Image Representation

IS - 3

ER -

An MMSE approach to nonlocal image denoising: Theory and practical implementation

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this