Discover MakerZone

MATLAB and Simulink resources for Arduino, LEGO, and Raspberry Pi

Learn more

Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply Today

Thread Subject:
Plot 2-Variables ...strange output

Subject: Plot 2-Variables ...strange output

From: Twilighter

Date: 12 Jun, 2011 13:34:02

Message: 1 of 5


i'm having 2 variables Y1 & Y2 which i need to plot them against X

but as i plot everyone separately it works fine

only when i plot them together, i get wierd output

see the picture here ....
https://picasaweb.google.com/105826940471714630965/Jun122011?authkey=Gv1sRgCMyR_4KKnpmzXg#5617322740234476466

the two figures are plotted using the same data table shown in the figure, no change

the red line which is the Threshold (Y2), becomes a straight line which its + points are exactly the same values of X .... see the table in the image

here is my Code

Y = [Y1 Y2]; % size 4x2

  
  X =AttacksValue.Value;
  X=X'; % size 4x1
  
% plotting Y1 & Y2 Against X

plot(X,Y(:,1),'k:o',X,Y(:,2),'r:+','Linewidth',2);
title ('Gaussain Attack');
xlabel ('Gaussian Noise Variance');
ylabel ('Response Detector');
legend('Image Response','Threshold');

% that for plotting only the Threshold Against X

plot(X,Y(:,2),'r:+','Linewidth',2);
title ('Gaussain Attack');
xlabel ('Gaussian Noise Variance');
ylabel ('Response Detector');
legend('Threshold');


why do i get this weird plot ?

thanx for your responses

Subject: Plot 2-Variables ...strange output

From: ImageAnalyst

Date: 12 Jun, 2011 13:39:22

Message: 2 of 5

Because they're different scales. Y1 goes up to 2*10^13 and Y2 is
like .003 so of course it shows up as a flat line when you plot them
both with the same vertical axis scale.

You want to use plotyy() instead so that the two curves are plotted
each with their own Y scale.

Subject: Plot 2-Variables ...strange output

From: Twilighter

Date: 12 Jun, 2011 19:07:02

Message: 3 of 5

Thank you so much yes i got it ... i appreciate it

but can you help me in this too ... it's regarding the Y1 & Y2 values ....
it seems the that Image response value isn't supposed to be that big

here is my Code ... in how i get Y1 & Y2

i have a watermarked image, and i add additive gaussian noise with zero mean & variance value is the X value & on it ...
so i get Y1 & Y2 which are the Image Response & the threshold respectively

side info is the Watermark image

sideinfo_h=reshape(sideinfo_h,1,256*256);
sideinfo_v=reshape(sideinfo_v,1,256*256);

% initalize message to all ones
message_vector=ones(1,256*256);

[cA1,cH1,cV1,cD1] = dwt2(watermarked_image,'haar');

cH1 = reshape(cH1,1,256*256);
cV1 = reshape(cV1,1,256*256);

% The computed detection value ( Correlation between the watermark image & the subbands which i actually embedded the watermark in them )

ccH1= zeros(1,256*256);
ccV1= zeros(1,256*256);

for (KK=1:length(message_vector))
    
        ccH1(KK)=cH1(KK)*sideinfo_h(KK);
        ccV1=ccV1+cV1(KK)*sideinfo_v(KK);
end

P= (1/3*256*256)*(ccH1+ccV1);
Ptotal =abs(sum(P));
P_img = reshape(P,256,256);
imshow(P_img,[])
title('Image Correlation')


% Other Method to perform correlation between Watermark & watermarked Image
% nearly the same value as Ptotal
cross_correlation_h = xcorr(cH1,sideinfo_h)
cross_correlation_v = xcorr(cV1,sideinfo_v)
cross_correlation = (1/3*256*256)*((cross_correlation_h+cross_correlation_h)/2);
cross_correlation = sum(cross_correlation);


so now that's how i calculate the threshold too

% The computed Threshold value value
ccHThr= zeros(1,256*256);
ccVThr= zeros(1,256*256);
for (KK=1:length(message_vector))
    
        ccHThr(KK)=ccHThr(KK)+(cH1(KK))^2;
        ccVThr(KK)=ccVThr(KK)+(cV1(KK))^2;
end


T1=(1/(3*256*256)^2) *sum(ccHThr+ccVThr)
T = 3.97*sqrt(2*T1)

here is a link to the equations implement here ....

https://picasaweb.google.com/105826940471714630965/Jun12201103?authkey=Gv1sRgCLju152JiJCwZg#5617410448109831986

what i need to know is it normal to have way far values between threshold & the Image Response ??

am i correctly interpreting those equations ?
they are simple but i'm just beginner i may have not put them correct

i appreciate your guidance through this

Subject: Plot 2-Variables ...strange output

From: ImageAnalyst

Date: 12 Jun, 2011 19:40:22

Message: 4 of 5

Sorry, no. I see dwt2 being called and I don't have the wavelet
toolbox, so I know I shouldn't even try. It shouldn't be difficult to
figure out, assuming you know how to use the debugger.

Subject: Plot 2-Variables ...strange output

From: Twilighter

Date: 12 Jun, 2011 20:00:21

Message: 5 of 5

thank you

i dont have an error

i'm just asking about the output of those two equations ... are they correctly implemented ... or i mis-understood implementing them

you could consider the Wavelet coefficient is another image not decomposed image

but anyway thanx :)

Tags for this Thread

What are tags?

A tag is like a keyword or category label associated with each thread. Tags make it easier for you to find threads of interest.

Anyone can tag a thread. Tags are public and visible to everyone.

Contact us