Welcome to EDAboard.com

Welcome to our site! EDAboard.com is an international Electronic Discussion Forum focused on EDA software, circuits, schematics, books, theory, papers, asic, pld, 8051, DSP, Network, RF, Analog Design, PCB, Service Manuals... and a whole lot more! To participate you need to register. Registration is free. Click here to register now.

Register Log in

wavelet based hidden markov model

Status
Not open for further replies.

jothiseetha

Newbie level 1
Joined
Feb 11, 2010
Messages
1
Helped
0
Reputation
0
Reaction score
0
Trophy points
1,281
Activity points
1,289
hi,
i m trying the project edge detection using hidden markov chain(HMC) model based on wavelets.The HMC needs transition matrix(TM), initial state probability (PI)distribution,observation sequence(O),and observation pobability distribution(b).
for my case the observation(O) is wavelet coefficients.
TM=[.95 .05;.2 .8];
PI[.5 .5];
b= can be achieved through gaussion and laplacian pdf;

while executing my program i am receiving the following error.
??? Attempted to access b(1,0.5); index must be a positive integer or logical.

Error in ==> pr_hmm at 13
m(1,i)=b(i,o(1))*pi(i);
[/size][/b][/color][/size]

Code:
clc;
clear all;
close all;
X=imread('cameraman.tif');
 
%SWT
[a1,h1,v1,d1] = swt2(X,1,'haar');
[a2,h2,v2,d2] = swt2(a1,1,'haar');
[a3,h3,v3,d3] = swt2(a2,1,'haar');
w=[a3,h3;v3,d3];
 w=w(:)'; 
k=1;
    for i=1:256
        for j=1:256
            seq1(k,1:3)=[h1(i,j),v1(i,j),d1(i,j)];
            k=k+1;
        end
    end
k=1;
    for i=1:256
        for j=1:256
            seq2(k,1:3)=[h2(i,j),v2(i,j),d2(i,j)];
            k=k+1;
        end
    end
    k=1;
    for i=1:256
        for j=1:256
            seq3(k,1:3)=[h3(i,j),v3(i,j),d3(i,j)];
            k=k+1;
        end
    end
e=1;
  for k=1:65536
      o(e,1:3)=seq1(k,1:3);
      e=e+1;
  end
 w=w(:)';
 data1=w;
 var1=var(data1);
 std1=sqrt(var1);
 for k=1:262144
 y1(k)=(2*pi*var1).^(-1/2)*exp(-(data1(k).^2)/2*var1.^2);
 x1(k)=(2).^(-1/2)*(std1).^(-1)*exp(-(sqrt(2)*data1(k))/std1);
 b(k,1:2)=[x1(k),y1(k)];
 end
  pi=[.5 .5];
  a=[.95 .05;.2 .8];
  s=pr_hmm(o,a,b,pi);


%%pr_hmm

function p=pr_hmm(o,a,b,pi)
%INPUTS:
%O=Given observation sequence labellebd in numerics
%A(N,N)=transition probability matrix
%B(N,M)=Emission matrix
%pi=initial probability matrix
%Output
%P=probability of given sequence in the given model
n=length(a(1,:));
T=length(o);
%it uses forward algorith to compute the probability
for i=1:n        %it is initilization
    m(1,i)=b(i,o(1))*pi(i);
end
for t=1:(T-1)      %recurssion
    for j=1:n
        z=0;
        for i=1:n
            z=z+a(i,j)*m(t,i);
        end
        m(t+1,j)=z*b(j,o(t+1));
    end
end
p=0;
for i=1:n         %termination
    p=p+m(T,i);        
end
 

Status
Not open for further replies.

Part and Inventory Search

Welcome to EDABoard.com

Sponsor

Top