Image Restoration Using Anisotropic Stochastic Diffusion Collaborated with Non Local Means

Borkowski, Dariusz; Jańczak-Borkowska, Katarzyna

doi:10.1007/978-3-642-40925-7_18

Cited by 2 publications

(1 citation statement)

References 33 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We consider an additional component -the function g. The task of the function g will be to determine the weights based on the similarity of patches like in the NLM algorithm [18,19]. The concept of using the similarity of patches with stochastic diffusion was presented in [9,12,14,15], but only at the numerical level. In this paper, we have taken that idea to a BSDE continuous model (in the form of the function g).…”

Section: Approximationmentioning

confidence: 99%

Implementation of Image Denoising based on Backward Stochastic Differential Equations

Borkowski

2023

Image Processing on Line

View full text Add to dashboard Cite

In this paper, we give the implementation of an image denoising algorithm based on backward stochastic differential equations. In our algorithm, we consider two stochastic processes. One of them has values in the image domain and determines pixels that will be involved in the reconstruction, the second one has values in the image codomain and gives weights to values of pixels. The reconstructed image is characterized by smoothing noisy pixels and at the same time enhancing edges. Our experiments show that the new approach gives very good results and can be successfully used to reconstruct images. Source CodeThe reviewed source code and documentation for this algorithm are available at the IPOL web page of this article 1 . Compilation and usage instructions are included in the README.txt file of the archive.

show abstract