Skip to content

Xingorno/Optimized-Bayesian-Nonlocal-means-with-block-OBNLM

Repository files navigation

Optimized-Bayesian-Nonlocal-means-with-block(OBNLM)

Optimized bayesian nonlocal-means algorithm for denoising ultrasound image

Description

  • BayesianNLM.m : the OBNLM algorithm
  • getPearsonDistance.m: compute the pearson distance based bayesian framework
  • ImgNormalize.m: pre-processing the image (histogram stretching)
  • testBayesianNLM.m: test our algorithm using the input (noisyImage.png) and get the output (despeckledImage.png)

Reference Paper

Coupé, Pierrick, et al. "Nonlocal means-based speckle filtering for ultrasound images." IEEE transactions on image processing 18.10 (2009): 2221-2229.

Basic Principle

The blockwise Nonlocal Means algorithm is completed. The basic principle is shown below: basic principle

Object Function: with

: the blockwise of image

:the pearson distance between blockwise

Results

The original ultrasound image (with speckle) vs the despeckled ultrasound image:

About

Optimized bayesian nonlocal-means algorithm for denoising ultrasound image

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages