.png){kind=icon}
.png){kind=icon}
Return
Efficient Algorithm for Nonconvex Minimization and Its Application to PM Regularization
.png){kind=icon}
PRE
AI
DOI：10.1109/TIP.2012.2208979.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In image processing, nonconvex regularization has the ability to smooth homogeneous regions and sharpen edges but leads to challenging computation. We propose some iterative schemes to minimize the energy function with nonconvex edge-preserving potential. The schemes are derived from the duality-based algorithm proposed by Berm dez and Moreno and the fixed point iteration. The convergence is proved for the convex energy function with nonconvex potential and the linear convergence rate is given. Applying the proposed schemes to Perona and Malik's nonconvex regularization, we present some efficient algorithms based on our schemes, and show the approximate convergence behavior for nonconvex energy function. Experimental results are presented, which show the efficiency of our algorithms, including better denoised performance of nonconvex regularization, faster convergence speed, higher calculation precision, lower calculation cost under the same number of iterations, and less implementation time under the same peak signal noise ratio level.
Keywords:
Image processing
nonconvex
duality
fixed point iteration
regularization
convergence
optimization
algorithm
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
IF:
13.7
Papers:
1.0W
Citations:
8.4W