1 简介
为快速准确地将图像中目标和背景分离开来,将新型群体智能模型中的人工蜂群算法、二维直线交叉熵相结合,提出了一种图像分割新方法.该方法将图像阈值看成人工蜂群算法中的蜜源,利用信息熵和最大熵原理设计人工蜂群算法的适应度函数;通过采蜜蜂、侦查蜂和观察蜂的分工协作和信息共享,逐代逼近最佳阈值.并利用Matlab实现了图像分割算法,对分割的结果进行分析.实验结果表明,该方法在阈值分割图像时,蜂群算法能够快速准确地将图像目标分离出来,分离出来的目标更加适合后序的分析和处理.
2 部分代码
%%%%%ARTIFICIAL BEE COLONY ALGORITHM%%%%
%Artificial Bee Colony Algorithm was developed by Dervis Karaboga in 2005
%by simulating the foraging behaviour of bees.
%Copyright ?2008 Erciyes University, Intelligent Systems Research Group, The Dept. of Computer Engineering
%Contact:
%Dervis Karaboga (karaboga@erciyes.edu.tr )
%Bahriye Basturk Akay (bahriye@erciyes.edu.tr)
function [SO,TO] = runABC(N,D,Iter,Pr,run)
%
clear all
close all
clc
Iter = 100;
N = 10;
BEA = 7;
D = 2;
Pr=0.5;
run=50;
% load temp.mat
img=imread('1.png');
im = rgb2gray(img);
mat = im;
tic
% Set ABC Control Parameters
ABCOpts = struct( 'ColonySize', N, ... % Number of Employed Bees+ Number of Onlooker Bees
'MaxCycles', Iter,... % Maximum cycle number in order to terminate the algorithm
'ErrGoal', 1e-20, ... % Error goal in order to terminate the algorithm (not used in the code in current version)
'Dim', D, ... % Number of parameters of the objective function
'Limit', 100, ... % Control paramter in order to abandone the food source
'lb', 1, ... % Lower bound of the parameters to be optimized
'ub', 256, ... %Upper bound of the parameters to be optimized
'ObjFun' , 'Hgrey', ... %Write the name of the objective function you want to minimize
'RunTime',run); % Number of the runs
GlobalMins=zeros(ABCOpts.RunTime,ABCOpts.MaxCycles);
for r=1:ABCOpts.RunTime
% Initialise population
Range = repmat((ABCOpts.ub-ABCOpts.lb),[ABCOpts.ColonySize 1]);%ABCOpts.Dim]);
Lower = repmat(ABCOpts.lb, [ABCOpts.ColonySize 1]);%ABCOpts.Dim]);
XColony = rand(ABCOpts.ColonySize,1) .* Range + Lower;
YColony = rand(ABCOpts.ColonySize,1).* Range + Lower;
Colony = [XColony , YColony];
size(Colony);
Colony = ceil(Colony);
Employed=Colony(1:(ABCOpts.ColonySize/2),:);
%evaluate and calculate fitness
ObjEmp=feval(ABCOpts.ObjFun,Employed,mat)
%fprintf('obj = %d \t',ObjEmp);
%fprintf('\n');
%ObjEmp = Location(pos,Employed);
%display(ObjEmp);
FitEmp=calculateFitness(ObjEmp);
display(FitEmp);
%fprintf('%d \t',FitEmp);
%set initial values of Bas
Bas=zeros(1,(ABCOpts.ColonySize/2));
%
%
fprintf('Cycle=%d ObjVal=%g\n',Cycle,GlobalMin);
%
%Bestcycle(Cycle,:) = CycleBestParams;
%Bestcyval(Cycle) = CycleMin;
Cycle=Cycle+1;
%
end % End of s
Bestcycle(r,:) = CycleBestParams;
Bestcyval(r) = CycleMin;
end; %end of runs
toc
%semilogy(mean(GlobalMins))
% Global = GlobalMins;
% Cyc = rand()* ABCOpts.MaxCycles;
% for r = 1: 5
% for C = 1: Cyc
% Global(r,C) = Global(r,C) * rand();
% end
% so = sort(Global(r,:));
% end
%so = sort(Global);
%Gls = unique(Globals)
%Glt = unique(Globalt)
[c ,i] = max(GlobalMins)
[cc , ro] = max(c)
co = i(ro)
SO = Globals(co,ro)
TO = Globalt(co,ro)
plot(GlobalMins(1,:));
title('Mean of Best function values');
xlabel('cycles');
ylabel('Mean Values');
fprintf('Mean =%g Std=%g\n',mean(GlobalMins(:,end)),std(GlobalMins(:,end)));
S = uint8(SO);
[r,c] = size(im);
% whos S
%wim = whiten(uint8(gimg),uint8(S));
thr = S / 256;
%wim = im2bw(gimg);
img = zeros(r,c);
for i = 1:r
for j = 1:c
if im(i,j) >= S
img(i,j) = 1;
end
end
end
figure,imshow(mat2gray(img))
3 仿真结果
4 参考文献
[1]霍凤财等. "基于人工蜂群算法的图像阈值分割." 自动化技术与应用 035.002(2016):112-116.
部分理论引用网络文献，若有侵权联系博主删除。
5 MATLAB代码与数据下载地址
见博客主页
