matlab - How Local binary pattern's feature vector can be used for classification? -
i working on project classification of skin cancer.i used built in matlab function extractlbpfeatures() texture analysis. used 'false' in parameters.i got vector of 10 elements.but failed differentiate cancerous image non-cancerous images.because saw values similar both of case if region of interest closed (means same area).for small region got small value ,for big region got bigger value.what should classify?
clc; close all; imtool close all; clear; fontsize=10; %input image current directory... [file path]=uigetfile('.jpg','select image folder'); temp=[path file]; a=imread(temp); a=imresize(a,[300 300]); mkr=a; %convert gray scale image... im=rgb2gray(a); %a = imresize(a,[200 200]) m1 = im2double(a); %im= imadjust(im); %dullrazor technique hair removal se = strel('disk',5); hairs = imbothat(im,se); bw = hairs > 15; bw2 = imdilate(bw,strel('disk',2)); replacedimage = roifill(im,bw2); %filtering removing artifacts.. replacedimage=medfilt2(replacedimage); grayimage=replacedimage; %applying otsu thresholding method.... level=graythresh(replacedimage); a=im2bw(replacedimage,level); %hole fills... a=imfill(~a,'holes'); %labeling image a=bwlabel(a); %selecting biggest region .. s = regionprops(a,'area'); [maxvalue,index] = max([s.area]); i=bwareaopen(a,maxvalue); %morphological closing operation.. se = strel('disk',5); i= imclose(i,se); figure,imshow(i); grayimage(~i)=nan; figure, imshow(grayimage); lbp= extractlbpfeatures(grayimage,'upright',false); disp(lbp);
Comments
Post a Comment