【图像去噪】QAB-去噪（matlab实现）_qt 判断波峰-可排除噪声毛刺-优快云博客

本文链接：https://blog.youkuaiyun.com/Matlab88888/article/details/137080951

💥💥💞💞欢迎来到本博客❤️❤️💥💥

🏆博主优势：🌞🌞🌞博客内容尽量做到思维缜密，逻辑清晰，为了方便读者。

⛳️座右铭：行百里者，半于九十。

📋📋📋本文目录如下：🎁🎁🎁

💥1 概述

QAB（Quantitative Analysis of Biosystems）是一种用于生物系统定量分析的方法。在QAB中，图像去噪是一个重要的步骤，旨在减少或消除图像中的噪声，以便更准确地分析图像中的生物系统结构和功能。图像去噪是通过应用各种数字信号处理技术来实现的，这些技术可以从图像中识别和过滤掉噪声，同时尽可能地保留有用的信息。常用的图像去噪方法包括均值滤波、中值滤波、高斯滤波、小波变换等。在QAB中，图像去噪的目标是使图像更清晰、更易于分析，并提高后续分析步骤的准确性和可靠性。去噪后的图像可以更好地用于定量分析生物系统的各种特征，例如细胞形态、蛋白质表达水平、细胞器分布等。

📚2 运行结果

主函数部分代码：

close all
clc; clear;

%load data
load('sample_image.mat')

%size of signal
[M,N] = size(I);
NN = N^2;
%generate the noise
SNR = 15;
pI = sum(I(:) .^2) / length(I(:));
B = randn(N,N) .* sqrt(abs(I));  % Poisson noise
pB_tmp = sum(sum(B .^2)) / NN;
B = B / sqrt(pB_tmp) * sqrt(pI * 10^(- SNR / 10));
J = B + I;  %noisy image

% Data
Ms = 20; % number of iteration in reconstruction
pds = 3; % value of palnck's constant
sg = 7.5; % Gaussian Variance (smoothing)

%image denoising using QAB
[I_result] = image_denoising_QAB(I,J,Ms,pds,sg);

% Here one may think why we need I as input, since I is the clean image.
% Actually in the program, the clean image data I is used just to find out the 
% best thresholding hyperparameter. In the code, one can see that the clean 
% image I is only used for the computation of signal-to-noise-ratio (SNR) 
% and based on this one can tune the best thresholding hyperparameter.
% So, one does not need any knowledge about the clean image I for computing
% the quantum adaptive basis (QAB) and can tune the thresholding hyperparameter
% manually up to their best possible values and modify the code accordingly.
% Therefore, one should not get confused after seeing I as an input, because I
% does not have any impact on the denoising process.


% Calculation of SNR, PSNR and SSIM
pnB = sum((I_result(:) - I(:)) .^2) / length(I(:));
SNR_end = 10 * log10(pI / pnB);
PSNR_end = calc_PSNR(I,I_result);
SSIM_end = ssim_index(I_result, I, [0.01 0.03], fspecial('gaussian', 3, 1.5), max(I(:)))
% Print data
fprintf('\n\n OUTPUT:\n SNR = %.2f, PSNR = %.2f, and SSIM = %.2f \n\n',SNR_end,PSNR_end,SSIM_end);

%plot figures
font_size = 12;