Spectral Response Based Regularization Parameter Selection for Total Variation Image Restoration

Zheng, Yuhui; Li, Min; Ma, Kai; Wang, Shunfeng; Wang, Jin

doi:10.1007/978-981-10-5041-1_101

Cited by 1 publication

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the TV image denoising, the higher SR-index, the more important the data-fidelity term. With the consideration, in the work of [40], a regularization parameter estimation method for TV model is proposed as follows:…”

Section: Spectral Response and Regularization Parameter Selectionmentioning

confidence: 99%

“…Very lately, to enhance image denoising results of the work in [40], Zhang et al [42] presented a local parameter estimation method using LSR concept. In this work, 9 different patch shapes are employed to calculate LSR for the purpose of introducing directional structure information into parameter selection.…”

Section: Spectral Response and Regularization Parameter Selectionmentioning

confidence: 99%

“…Different from the method in [40], in our proposed method, the regularization parameter is locally estimated and adaptive to image elementary structures. Recently, fast algorithm for TV mode with adaptive regularization parameter is still an open problem.…”

Section: Mathematical Expressionmentioning

confidence: 99%

“…Through the transform a new concept called spectral response (SR) was proposed, which is the amplitude of TV transform and can be used to describe the smoothing speed of TV flow at time scales. With the observation that SR is content aware, Zheng et al [40] utilizes it to present a new global regularization parameter estimation scheme for TV model. To improve the performance of SR based parameter selection approach, Zhang et al [41] introduces a parameter estimation scheme using local spectral response.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Regularization Parameter Selection for Total Variation Model Based on Local Spectral Response

Zheng¹,

Ma²,

Yu³

et al. 2017

J Inf Process Syst

Self Cite

View full text Add to dashboard Cite

In the past decades, various image regularization methods have been introduced. Among them, total variation model has drawn much attention for the reason of its low computational complexity and well-understood mathematical behavior. However, regularization parameter estimation of total variation model is still an open problem. To deal with this problem, a novel adaptive regularization parameter selection scheme is proposed in this paper, by means of using the local spectral response, which has the capability of locally selecting the regularization parameters in a content-aware way and therefore adaptively adjusting the weights between the two terms of the total variation model. Experiment results on simulated and real noisy image show the good performance of our proposed method, in visual improvement and peak signal to noise ratio value.

show abstract

Section: Spectral Response and Regularization Parameter Selectionmentioning

confidence: 99%

Section: Spectral Response and Regularization Parameter Selectionmentioning

confidence: 99%

Section: Mathematical Expressionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations