Finding the particular path using image processing

Hi,

I need to find the path from the attached displacement field attached as .MAT file. My code was working on other data sets that I was analyzing but is not working for the new data set I have.

Currently I am using following code:

 Igray = mat2gray(dispfield);
th = multithresh(Igray,2);
Iseg = imquantize(Igray,th);
se = strel('disk',1);
BW1 = bwperim(Iseg == 1);
BW1 = imdilate(BW1,se);
BW2 = bwperim(Iseg == 2);
BW2 = imdilate(BW2,se);
 BWedge = BW1 & BW2;
BWedge = bwmorph(BWedge,'skel',Inf);
bwedge = BWedge;
[Y,X] = find(bwedge);
 cracklinefit = fit(X,Y,'poly3','Normalize','on');
% cracklinefit = fit(X,Y,'poly3','Normalize','on','Robust','Bisquare');
outputArg3 = [1:size(bwedge,2)]';
outputArg2 = round(cracklinefit(outputArg3));

Answer 1

[Madhav Thakker]

Hi Waqas,

I understand that you want to calculate path from the given .MAT file. I see that your code was not working for this example due to some distortions.

One useful function to use here is bwareaopen() which removes all connected components (objects) that have fewer than P pixels from the binary image.

I am attaching a code snippet for better understanding.

Igray = mat2gray(dispfield);
th = multithresh(Igray,1);
Iseg = imquantize(Igray,th);
%imshow(Iseg,[])
se = strel('disk',1);
BW1 = bwperim(Iseg == 1);
BW1 = imdilate(BW1,se);
bwedge = bwareaopen(BW1, 100); % removes all connected components (objects) that have fewer than P pixels
[Y,X] = find(bwedge);
cracklinefit = fit(X,Y,'poly3','Normalize','on');
% cracklinefit = fit(X,Y,'poly3','Normalize','on','Robust','Bisquare');
outputArg3 = [1:size(bwedge,2)]';
outputArg2 = round(cracklinefit(outputArg3));

Hope this helps.

[waqas]

it ended up helping me in another implementation. Thank you.