How to find region of interest using region props for multiple skin dermoscopic images

I need to use region props to find region of interest in multiple skin lesion images. I am using Otsus segmentation method. Kindly help me use region props to find region of interest for multiple images. The lesion can be anywhere in the image thus the code should be able to identify which region has the lesion

.

Answer 1

[Image Analyst]

A full demo is given here in my Image Segmentation Tutorial:

Image Analyst's File Exchange

Just convert your image to gray scale and it should work. In short

% Make sure the image is gray scale.
if ndims(rgbImage) == 3
    % Is color.  Need to convert it to gray scale.
    grayImage = rgb2gray(rgbImage);
else
    grayImage = rgbImage; % Was not really RGB after all.
end
% Binarize using Otsu's method to find the dark blob.
mask = imbinarize(grayImage);
% Take largest blob only.
mask = bwareafilt(mask, 1);
% Make measurements.
props = regionprops(mask, grayImage, 'Area', 'Perimeter', 'MeanIntensity'); % List whatever measurements you want.
area = props.Area
perimeter = props.Perimeter
meanGrayLevel = props.MeanIntensity

[Aashir Ahmed]

%% Otsu Thresholding

close all;

clear all;

clc

%%================================================================================================

location = 'demo.jpg'; % folder in which your images exists

ds = imageDatastore(location) % Creates a datastore for all images in your folder

while hasdata(ds)

img = read(ds) ; % read image from datastore

figure, imshow(img); % creates a new window for each image

%%=================================================================================================

n=imhist(img); % Compute the histogram

N=sum(n); % sum the values of all the histogram values

max=0; %initialize maximum to zero

%%================================================================================================

for i=1:256

P(i)=n(i)/N; %Computing the probability of each intensity level

end

%%================================================================================================

for T=2:255 % step through all thresholds from 2 to 255

w0=sum(P(1:T)); % Probability of class 1 (separated by threshold)

w1=sum(P(T+1:256)); %probability of class2 (separated by threshold)

u0=dot([0:T-1],P(1:T))/w0; % class mean u0

u1=dot([T:255],P(T+1:256))/w1; % class mean u1

sigma=w0*w1*((u1-u0)^2); % compute sigma i.e variance(between class)

if sigma>max % compare sigma with maximum

max=sigma; % update the value of max i.e max=sigma

threshold=T-1; % desired threshold corresponds to maximum variance of between class

end

end

%%====================================================================================================

bw=im2bw(img,threshold/255); % Convert to Binary Image

bw= imclearborder(~bw);

figure ,imshow(bw); % Display the Binary Image

%%====================================================================================================

end

[Aashir Ahmed]

Heres my otsus code. I am still insure how will I be able to use region props to accurately find the region of lesion. I have used your code but it gives values. I just need some guidance on how will I use the values to get the region of the lesion. Thank you