Speckle reduction with trained nonlinear diffusion filtering
From MaRDI portal
Abstract: Speckle reduction is a prerequisite for many image processing tasks in synthetic aperture radar (SAR) images, as well as all coherent images. In recent years, predominant state-of-the-art approaches for despeckling are usually based on nonlocal methods which mainly concentrate on achieving utmost image restoration quality, with relatively low computational efficiency. Therefore, in this study we aim to propose an efficient despeckling model with both high computational efficiency and high recovery quality. To this end, we exploit a newly-developed trainable nonlinear reaction diffusion(TNRD) framework which has proven a simple and effective model for various image restoration problems. {In the original TNRD applications, the diffusion network is usually derived based on the direct gradient descent scheme. However, this approach will encounter some problem for the task of multiplicative noise reduction exploited in this study. To solve this problem, we employed a new architecture derived from the proximal gradient descent method.} {Taking into account the speckle noise statistics, the diffusion process for the despeckling task is derived. We then retrain all the model parameters in the presence of speckle noise. Finally, optimized nonlinear diffusion filtering models are obtained, which are specialized for despeckling with various noise levels. Experimental results substantiate that the trained filtering models provide comparable or even better results than state-of-the-art nonlocal approaches. Meanwhile, our proposed model merely contains convolution of linear filters with an image, which offers high level parallelism on GPUs. As a consequence, for images of size , our GPU implementation takes less than 0.1 seconds to produce state-of-the-art despeckling performance.}
Recommendations
- A gray level indicator-based regularized telegraph diffusion model: application to image despeckling
- Image denoising via multiscale nonlinear diffusion models
- Speckle noise reduction via nonconvex high total variation approach
- SAR image despeckling based on adaptive non-local means
- SAR image despeckling by using nonlocal sparse coding model
Cites work
- A Review of Image Denoising Algorithms, with a New One
- A Variational Approach to Removing Multiplicative Noise
- A convex variational model for restoring blurred images with multiplicative noise
- A new similarity measure for nonlocal filtering in the presence of multiplicative noise
- A variational model for multiplicative structured noise removal
- A variational model to remove the multiplicative noise in ultrasound images
- Fields of experts
- How to compare noisy patches? patch similarity beyond Gaussian noise
- Introductory lectures on convex optimization. A basic course.
- Iterative Weighted Maximum Likelihood Denoising With Probabilistic Patch-Based Weights
- Multiplicative Noise Removal via a Learned Dictionary
- Multiplicative noise removal using L1 fidelity on frame coefficients
- Multiplicative noise removal via nonlocal similarity-based sparse representation
- On the limited memory BFGS method for large scale optimization
- Removing multiplicative noise by Douglas-Rachford splitting methods
- Speckle Reduction via Higher Order Total Variation Approach
- Total generalized variation
- Two-step approach for the restoration of images corrupted by multiplicative noise
- Why least squares and maximum entropy? An axiomatic approach to inference for linear inverse problems
- iPiano: inertial proximal algorithm for nonconvex optimization
Cited in
(6)- A gray level indicator-based regularized telegraph diffusion model: application to image despeckling
- An improved variational model for denoising magnetic resonance images
- Speckle Reduction via Higher Order Total Variation Approach
- Speckle reduction and structure enhancement by multichannel median boosted anisotropic diffusion
- Image denoising via multiscale nonlinear diffusion models
- Magnetic resonance images denoising using a wavelet solution to Laplace equation associated with a new variational model
This page was built for publication: Speckle reduction with trained nonlinear diffusion filtering
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1708000)
