1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
| im=imread('G:\matlab\fichie oxiliaires\parkinson coronale.png'); im=double(im);X=hist(im);
% [W,M,V,L] = EM_GM_fast(X,3,[],[],1,[])
function [W,M,V,L] = EM_GM_fast(X,3,[],[],1,[])
% [W,M,V,L] = EM_GM_fast(X,k,ltol,maxiter,pflag,Init)
%
% EM algorithm for k multidimensional Gaussian mixture estimation
% (EM_GM_fast is the modified version of EM_GM for speed enchancement.
% The functionalities of EM_GM_fast and EM_GM are identical.)
%
% Note: EM_GM_fast requires more memory than EM_GM to execute.
% If EM_GM_fast does not provide any speed gain or is slower than EM_GM,
% more memory is needed or EM_GM should be used instead.
%
% Inputs:
% X(n,d) - input data, n=number of observations, d=dimension of variable
% k - maximum number of Gaussian components allowed
% ltol - percentage of the log likelihood difference between 2 iterations ([] for none)
% maxiter - maximum number of iteration allowed ([] for none)
% pflag - 1 for plotting GM for 1D or 2D cases only, 0 otherwise ([] for none)
% Init - structure of initial W, M, V: Init.W, Init.M, Init.V ([] for none)
%
% Ouputs:
% W(1,k) - estimated weights of GM
% M(d,k) - estimated mean vectors of GM
% V(d,d,k) - estimated covariance matrices of GM
% L - log likelihood of estimates
%
% Written by
% Patrick P. C. Tsui,
% PAMI research group
% Department of Electrical and Computer Engineering
% University of Waterloo,
% March, 2006
%
% Michael Boedigheimer
% Amgen
% Dept of Computational Biology
% Thousand Oaks CA, 91320
% Dec, 2005
%
%%%% Validate inputs %%%%
if nargin <= 1,
disp('EM_GM must have at least 2 inputs: X,k!/n')
return
elseif nargin == 2,
ltol = 0.1; maxiter = 1000; pflag = 0; Init = [];
err_X = Verify_X(X);
err_k = Verify_k(k);
if err_X | err_k, return; end
elseif nargin == 3,
maxiter = 1000; pflag = 0; Init = [];
err_X = Verify_X(X);
err_k = Verify_k(k);
[ltol,err_ltol] = Verify_ltol(ltol);
if err_X | err_k | err_ltol, return; end
elseif nargin == 4,
pflag = 0; Init = [];
err_X = Verify_X(X);
err_k = Verify_k(k);
[ltol,err_ltol] = Verify_ltol(ltol);
[maxiter,err_maxiter] = Verify_maxiter(maxiter);
if err_X | err_k | err_ltol | err_maxiter, return; end
elseif nargin == 5,
Init = [];
err_X = Verify_X(X);
err_k = Verify_k(k);
[ltol,err_ltol] = Verify_ltol(ltol);
[maxiter,err_maxiter] = Verify_maxiter(maxiter);
[pflag,err_pflag] = Verify_pflag(pflag);
if err_X | err_k | err_ltol | err_maxiter | err_pflag, return; end
elseif nargin == 6,
err_X = Verify_X(X);
err_k = Verify_k(k);
[ltol,err_ltol] = Verify_ltol(ltol);
[maxiter,err_maxiter] = Verify_maxiter(maxiter);
[pflag,err_pflag] = Verify_pflag(pflag);
[Init,err_Init]=Verify_Init(Init);
if err_X | err_k | err_ltol | err_maxiter | err_pflag | err_Init, return; end
else
disp('EM_GM must have 2 to 6 inputs!');
return
end
%%%% Initialize W, M, V,L %%%%
t = cputime;
if isempty(Init),
[W,M,V] = Init_EM(X,k); L = 0;
else
W = Init.W;
M = Init.M;
V = Init.V;
end
Ln = Likelihood(X,k,W,M,V); % Initialize log likelihood
Lo = 2*Ln;
%%%% EM algorithm %%%%
niter = 0;
while (abs(100*(Ln-Lo)/Lo)>ltol) & (niter<=maxiter),
E = Expectation(X,k,W,M,V); % E-step
[W,M,V] = Maximization(X,k,E); % M-step
Lo = Ln;
Ln = Likelihood(X,k,W,M,V);
niter = niter + 1;
end
L = Ln;
%%%% Plot 1D or 2D %%%%
if pflag==1,
[n,d] = size(X);
if d>2,
disp('Can only plot 1 or 2 dimensional applications!/n');
else
Plot_GM(X,k,W,M,V);
end
elapsed_time = sprintf('CPU time used for EM_GM: %5.2fs',cputime-t);
disp(elapsed_time);
disp(sprintf('Number of iterations: %d',niter-1));
end
%%%%%%%%%%%%%%%%%%%%%%
%%%% End of EM_GM %%%%
%%%%%%%%%%%%%%%%%%%%%%
function E = Expectation(X,k,W,M,V)
% This function is the modification of 'Expectation' in EM_GM made by
% Mr. Michael Boedigheimer to enchance computational speed.
% Note: this modification requires more memory to execute.
% If EM_GM_fast does not provide any speed gain or is slower than EM_GM,
% more memory is needed or EM_GM should be used instead.
[n,d] = size(X);
E = zeros(n,k);
for j = 1:k,
if V(:,:,j)==zeros(d,d), V(:,:,j)=ones(d,d)*eps; end
E(:,j) = W(j).*mvnpdf( X, M(:,j)', V(:,:,j) );
end
total = repmat(sum(E,2),1,j);
E = E./total;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Expectation %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [W,M,V] = Maximization(X,k,E)
% This function is the modification of 'Maximization' in EM_GM made by
% Mr. Michael Boedigheimer to enchance computational speed.
% Note: this modification requires more memory to execute.
% If EM_GM_fast does not provide any speed gain or is slower than EM_GM,
% more memory is needed or EM_GM should be used instead.
[n,d] = size(X);
W = sum(E);
M = X'*E./repmat(W,d,1);
for i=1:k,
dXM = X - repmat(M(:,i)',n,1);
Wsp = spdiags(E(:,i),0,n,n);
V(:,:,i) = dXM'*Wsp*dXM/W(i);
end
W = W/n;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Maximization %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function L = Likelihood(X,k,W,M,V)
% Compute L based on K. V. Mardia, "Multivariate Analysis", Academic Press, 1979, PP. 96-97
% to enchance computational speed
[n,d] = size(X);
U = mean(X)';
S = cov(X);
L = 0;
for i=1:k,
iV = inv(V(:,:,i));
L = L + W(i)*(-0.5*n*log(det(2*pi*V(:,:,i))) ...
-0.5*(n-1)*(trace(iV*S)+(U-M(:,i))'*iV*(U-M(:,i))));
end
%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Likelihood %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%
function err_X = Verify_X(X)
err_X = 1;
[n,d] = size(X);
if n<d,
disp('Input data must be n x d!/n');
return
end
err_X = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_X %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%
function err_k = Verify_k(k)
err_k = 1;
if ~isnumeric(k) | ~isreal(k) | k<1,
disp('k must be a real integer >= 1!/n');
return
end
err_k = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_k %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%
function [ltol,err_ltol] = Verify_ltol(ltol)
err_ltol = 1;
if isempty(ltol),
ltol = 0.1;
elseif ~isreal(ltol) | ltol<=0,
disp('ltol must be a positive real number!');
return
end
err_ltol = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_ltol %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [maxiter,err_maxiter] = Verify_maxiter(maxiter)
err_maxiter = 1;
if isempty(maxiter),
maxiter = 1000;
elseif ~isreal(maxiter) | maxiter<=0,
disp('ltol must be a positive real number!');
return
end
err_maxiter = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_maxiter %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [pflag,err_pflag] = Verify_pflag(pflag)
err_pflag = 1;
if isempty(pflag),
pflag = 0;
elseif pflag~=0 & pflag~=1,
disp('Plot flag must be either 0 or 1!/n');
return
end
err_pflag = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_pflag %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [Init,err_Init] = Verify_Init(Init)
err_Init = 1;
if isempty(Init),
% Do nothing;
elseif isstruct(Init),
[Wd,Wk] = size(Init.W);
[Md,Mk] = size(Init.M);
[Vd1,Vd2,Vk] = size(Init.V);
if Wk~=Mk | Wk~=Vk | Mk~=Vk,
disp('k in Init.W(1,k), Init.M(d,k) and Init.V(d,d,k) must equal!/n')
return
end
if Md~=Vd1 | Md~=Vd2 | Vd1~=Vd2,
disp('d in Init.W(1,k), Init.M(d,k) and Init.V(d,d,k) must equal!/n')
return
end
else
disp('Init must be a structure: W(1,k), M(d,k), V(d,d,k) or []!');
return
end
err_Init = 0;
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Verify_Init %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%
function [W,M,V] = Init_EM(X,k)
[n,d] = size(X);
[Ci,C] = kmeans(X,k,'Start','cluster', ...
'Maxiter',100, ...
'EmptyAction','drop', ...
'Display','off'); % Ci(nx1) - cluster indeices; C(k,d) - cluster centroid (i.e. mean)
while sum(isnan(C))>0,
[Ci,C] = kmeans(X,k,'Start','cluster', ...
'Maxiter',100, ...
'EmptyAction','drop', ...
'Display','off');
end
M = C';
Vp = repmat(struct('count',0,'X',zeros(n,d)),1,k);
for i=1:n, % Separate cluster points
Vp(Ci(i)).count = Vp(Ci(i)).count + 1;
Vp(Ci(i)).X(Vp(Ci(i)).count,:) = X(i,:);
end
V = zeros(d,d,k);
for i=1:k,
W(i) = Vp(i).count/n;
V(:,:,i) = cov(Vp(i).X(1:Vp(i).count,:));
end
%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Init_EM %%%%
%%%%%%%%%%%%%%%%%%%%%%%%
function Plot_GM(X,k,W,M,V)
[n,d] = size(X);
if d>2,
disp('Can only plot 1 or 2 dimensional applications!/n');
return
end
S = zeros(d,k);
R1 = zeros(d,k);
R2 = zeros(d,k);
for i=1:k, % Determine plot range as 4 x standard deviations
S(:,i) = sqrt(diag(V(:,:,i)));
R1(:,i) = M(:,i)-4*S(:,i);
R2(:,i) = M(:,i)+4*S(:,i);
end
Rmin = min(min(R1));
Rmax = max(max(R2));
R = [Rmin:0.001*(Rmax-Rmin):Rmax];
clf, hold on
if d==1,
Q = zeros(size(R));
for i=1:k,
P = W(i)*normpdf(R,M(:,i),sqrt(V(:,:,i)));
Q = Q + P;
plot(R,P,'r-'); grid on,
end
plot(R,Q,'k-');
xlabel('X');
ylabel('Probability density');
else % d==2
plot(X(:,1),X(:,2),'r.');
for i=1:k,
Plot_Std_Ellipse(M(:,i),V(:,:,i));
end
xlabel('1^{st} dimension');
ylabel('2^{nd} dimension');
axis([Rmin Rmax Rmin Rmax])
end
title('Gaussian Mixture estimated by EM');
%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Plot_GM %%%%
%%%%%%%%%%%%%%%%%%%%%%%%
function Plot_Std_Ellipse(M,V)
[Ev,D] = eig(V);
d = length(M);
if V(:,:)==zeros(d,d),
V(:,:) = ones(d,d)*eps;
end
iV = inv(V);
% Find the larger projection
P = [1,0;0,0]; % X-axis projection operator
P1 = P * 2*sqrt(D(1,1)) * Ev(:,1);
P2 = P * 2*sqrt(D(2,2)) * Ev(:,2);
if abs(P1(1)) >= abs(P2(1)),
Plen = P1(1);
else
Plen = P2(1);
end
count = 1;
step = 0.001*Plen;
Contour1 = zeros(2001,2);
Contour2 = zeros(2001,2);
for x = -Plen:step:Plen,
a = iV(2,2);
b = x * (iV(1,2)+iV(2,1));
c = (x^2) * iV(1,1) - 1;
Root1 = (-b + sqrt(b^2 - 4*a*c))/(2*a);
Root2 = (-b - sqrt(b^2 - 4*a*c))/(2*a);
if isreal(Root1),
Contour1(count,:) = [x,Root1] + M';
Contour2(count,:) = [x,Root2] + M';
count = count + 1;
end
end
Contour1 = Contour1(1:count-1,:);
Contour2 = [Contour1(1,:);Contour2(1:count-1,:);Contour1(count-1,:)];
plot(M(1),M(2),'k+');
plot(Contour1(:,1),Contour1(:,2),'k-');
plot(Contour2(:,1),Contour2(:,2),'k-');
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%
%%%% End of Plot_Std_Ellipse %%%%
%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%%% |
Algorithme EM et segmentation
Répondre avec citation
Partager