is this the right code ?

i'm trying to get features from my thinned of finger vein images by using lbp. i found this code, is this right code to extract features lbp from my images ?

I2 = imread(thisismythinnedimage);
figure, imshow(I2)%
w=size(I2,1);
h=size(I2,2);
%%LBP
for i=2:w-1
    for j=2:h-1
        J0=I2(i,j);
        I3(i-1,j-1)=I2(i-1,j-1)>J0;
        I3(i-1,j)=I2(i-1,j)>J0;
        I3(i-1,j+1)=I2(i-1,j+1)>J0; 
        I3(i,j+1)=I2(i,j+1)>J0;
        I3(i+1,j+1)=I2(i+1,j+1)>J0; 
        I3(i+1,j)=I2(i+1,j)>J0; 
        I3(i+1,j-1)=I2(i+1,j-1)>J0; 
        I3(i,j-1)=I2(i,j-1)>J0;
        LBP(i,j)=I3(i-1,j-1)*2^8+I3(i-1,j)*2^7+I3(i-1,j+1)*2^6+I3(i,j+1)*2^5+I3(i+1,j+1)*2^4+I3(i+1,j)*2^3+I3(i+1,j-1)*2^2+I3(i,j-1)*2^1;
    end
end
figure,imshow(I3)
figure,imhist(LBP)

i have tried this code but not understand enough how the codes works to get lbp from my images i intended to get bins of lbp for classification. from this code i cannot get decimal value of bins .

[Stephen23]

@azkya novia: today I formatted your code correctly for you. In future you can do it yourself: first select the code text, then click the {} Code button.

[azkya novia]

i did it, i asked and put my code in the code button. i dont know if the code changed appeare to be unformated

Answer 1

[Image Analyst]

If it does what you want and expect, then it's the right code for you, though there is no need for I3 to be a 2-D array, and the program is lacking in comments.

As an alternative, I attach my LBP demo program.

[azkya novia]

I just saw this answer. thank you ImageAnalyst :)

Answer 2

[Guillaume]

The code may or may not be correct. I've not wasted the time checking every single line is correct as it's so horribly written. I suggest you do a search on the FileExchange for some better code.

An example of how bad the code is: you can replace all the I3(.., ..) = ... lines by just this one line:

I3(i-1:i+1, j-1:j+1) = I2(i-1:i+1, j-1:j+1) > J0;

There are a lot more problems with it (I3 gets resized at each step of the loop, the loop is not even needed, no vectorisation of the LBP computation, etc.). As said, find a better implementation.

[azkya novia]

Ok thank you for the answer :)