图像中添加二项式分布噪声

clc,clear,close all
warning off
feature jit off
im = imread('coloredChips.png');
Z0 = imnoise_B(im,size(im,1),size(im,2),0.5);
Z1 = im2uint8(Z0);   % 类型转换
figure('color',[1,1,1]),
im(:,:,1) = im(:,:,1) + Z1;  % R
im(:,:,2) = im(:,:,2) + Z1;  % G
im(:,:,3) = im(:,:,3) + Z1;  % B
subplot(121); imshow(im);title('加二项式分布噪声图像')
subplot(122); imhist(Z1); title('加二项式分布噪声图像直方图')

function R = imnoise_B(im,M, N, b)
% input:
%       二项式B分布，噪声的类型；
%       M,N：输出噪声图像矩阵的大小
%       a,b：各种噪声的分布参数
% output:
%       R: 输出的噪声图像矩阵，数据类型为double型
% 设定默认值
% 考虑第floor(a/2)次命中
if nargin < 4
   b = 0.5;
end
   % 产生二项式分布噪声
    for i = 1:M
        for j=1:N
           a = double( floor(im(i,j)/30)+1 );
           R(i,j) = nchoosek(a,floor(a/2)) * b.^(floor(a/2)) .* (1-b).^(a- floor(a/2));
        end
    end
end

nchoosek Binomial coefficient or all combinations

Syntax

   C = nchoosek(n,k)

   C = nchoosek(v,k)

Description

C = nchoosek(n,k) where n and k are nonnegative integers, returns n!/((n–k)! k!).
This is the number of combinations of n things taken k at a time.

C = nchoosek(v,k), where v is a row vector of length n, creates a matrix whose rows consist of all possible combinations of the n elements of v taken k at a time.

Matrix C contains n!/((n–k)! k!) rows and k columns.

Inputs n, k, and v support classes of float double and float single.

Examples

The command nchoosek(2:2:10,4) returns the even numbers from two to ten, taken four at a time: 

      2     4     6     8
     2     4     6    10
     2     4     8    10
     2     6     8    10
     4     6     8    10