[image processing] image skeleton extraction based on central axis transformation with matlab code

1 Content introduction

This paper introduces a central axis transformation algorithm . This algorithm corrects the shortcomings of existing algorithms , It can quickly remove redundant information in binary images , Accurately extract the single pixel skeleton of the image , Retain basic features , In particular, slash and circular pad features . A lot of experiments show that , This method reduces the complexity of the image , Only the topology information of the image shape is preserved , Provide an ideal image for subsequent processing , Improve the performance of the whole system .​

2 Complete code

%  Axis Algorithm  Medial Axis Transfrom%% by HPC_ZY 20190802clear; close all; clc​load data​%% matlab%  Find skeleton ticskeleton = bwmorph(im,'skeleton',Inf);t1 = toc;%  Deburring ticskeleton1 = bwmorph(skeleton,'spur',16); t2 = toc;​figureshowres(im,skeleton,t1,1,2,1,'matlab library ')showres(im,skeleton1,t2,1,2,2,'matlab library （ Deburring ）')​%%  Iteratively delete %  Iterative deletion ticskeleton1 = method1(im);t1 = toc;​%  Iterative deletion （ Lookup table ）ticskeleton2 = method2(im);t2 = toc;​%  Iterative deletion （ simplify ）ticskeleton3 = method3(im);t3 = toc;​figureshowres(im,skeleton1,t1,1,3,1,' Iterative deletion ')showres(im,skeleton2,t2,1,3,2,' Iterative deletion （ Lookup table ）')showres(im,skeleton3,t3,1,3,3,' Iterative deletion （ simplify ）')​​%% ------------function--------------​%  Iterative deletion function skeleton = method1(bw)​bw = double(bw); %  To non logical type , It is convenient to sum later [M,N] = size(bw);skeleton = bw;deleCount = 1; %  Used to record the number of pixels deleted in an iteration while deleCount>0    %  Delete （ Right , Next ）    deleCount = 0;    label = zeros(M,N,'logical');    for i = 2:M-1        for j = 2:N-1            if skeleton(i,j) %  If the point is 1, Judge the surrounding pixels                 p = [skeleton(i-1,j),skeleton(i-1,j+1),skeleton(i,j+1),skeleton(i+1,j+1),...                    skeleton(i+1,j),skeleton(i+1,j-1),skeleton(i,j-1),skeleton(i-1,j-1)];                Np = sum(p);                Tp = length(find(([p(2:end),p(1)]-p) == 1));                if Np>1 && Np<7 && Tp==1 && p(1)*p(3)*p(5)==0 && p(7)*p(3)*p(5)==0                    deleCount = deleCount+1;                    label(i,j) = 1;                end            end        end    end    skeleton(label) = 0;    %  Delete （ Left , On ）    label = zeros(M,N,'logical');    for i = 2:M-1        for j = 2:N-1            if skeleton(i,j) %  If the point is 1, Judge the surrounding pixels                 p = [skeleton(i-1,j),skeleton(i-1,j+1),skeleton(i,j+1),skeleton(i+1,j+1),...                    skeleton(i+1,j),skeleton(i+1,j-1),skeleton(i,j-1),skeleton(i-1,j-1)];                Np = sum(p);                Tp = length(find(([p(2:end),p(1)]-p) == 1));                if Np>1 && Np<7 && Tp==1 && p(1)*p(3)*p(7)==0 && p(1)*p(5)*p(7)==0                    deleCount = deleCount+1;                    label(i,j) = 1;                end            end        end    end    skeleton(label) = 0;   end​​end​%  Iterative deletion （ Lookup table ）function skeleton = method2(bw)​bw = double(bw);[M,N] = size(bw);skeleton = bw;​%  Generate lookup table [List1,List2] = getList1();​[x,y] = find(bw);a = min(x);b = max(x);c = min(y);d = max(y);​deleCount = 1;mat = [1,2,4,8,16,32,64,128];while deleCount>0        deleCount = 0;    %  Delete （ Right , Next ）    label1 = zeros(M,N,'logical');    for i = a:b        for j = c:d            if skeleton(i,j)                p = [skeleton(i-1,j),skeleton(i-1,j+1),skeleton(i,j+1),skeleton(i+1,j+1),...                    skeleton(i+1,j),skeleton(i+1,j-1),skeleton(i,j-1),skeleton(i-1,j-1)];                idx = sum(p.*mat)+1;                if List1(idx)                    label1(i,j) = true;                    deleCount = deleCount+1;                end            end        end    end    skeleton(label1) = 0;        %  Delete （ Left , On ）    label2 = zeros(M,N,'logical');    for i = a:b        for j = c:d            if skeleton(i,j)                p = [skeleton(i-1,j),skeleton(i-1,j+1),skeleton(i,j+1),skeleton(i+1,j+1),...                    skeleton(i+1,j),skeleton(i+1,j-1),skeleton(i,j-1),skeleton(i-1,j-1)];                idx = sum(p.*mat)+1;                if List2(idx)                    label2(i,j) = true;                    deleCount = deleCount+1;                end            end        end    end        skeleton(label2) = 0;end​end​%  Iterative deletion （ simplify ）function skeleton = method3(bw)​bw = double(bw);[M,N] = size(bw);skeleton = bw;%  Generate lookup table List = getList2();%  Narrow your search [x,y] = find(bw);a = min(x);b = max(x);c = min(y);d = max(y);%  Start the iteration deleCount = 1;mat = [1,2,4,8,16,32,64,128];while deleCount>0     deleCount = 0;    label = zeros(M,N,'logical');    for i = a:b        for j = c:d            if skeleton(i,j)                p = [skeleton(i-1,j),skeleton(i-1,j+1),skeleton(i,j+1),skeleton(i+1,j+1),...                    skeleton(i+1,j),skeleton(i+1,j-1),skeleton(i,j-1),skeleton(i-1,j-1)];                idx = sum(p.*mat)+1;                if List(idx)                    label(i,j) = true;                    deleCount = deleCount+1;                end            end        end    end    skeleton(label) = 0;end​​end​%  Generate lookup table function [List1,List2] = getList1()​List1 = zeros(256,1,'logical');List2 = zeros(256,1,'logical');for n = 0:255    p = bitget(n,1:8);    Np = sum(p);    Tp = length(find(([p(2:end),p(1)]-p) == 1));    if Np>1 && Np<7 && Tp==1        %  Right , Next         if p(1)*p(3)*p(5)==0 && p(7)*p(3)*p(5)==0            List1(n+1) = true;        end        %  Left , On         if p(1)*p(3)*p(7)==0 && p(1)*p(5)*p(7)==0            List2(n+1) = true;        end    end end​end​%  Generate lookup table （ simplify ）function List = getList2()​List = zeros(256,1,'logical');for n = 0:255    p = bitget(n,1:8);    Np = sum(p);    Tp = length(find(([p(2:end),p(1)]-p) == 1));    if Np>1 && Np<7 && Tp==1        if (p(1)*p(3)*p(5)==0 && p(7)*p(3)*p(5)==0)||...                (p(1)*p(3)*p(7)==0 && p(1)*p(5)*p(7)==0)            List(n+1) = true;        end    end end​end​%  Show results function showres(im,skeleton,t,i,j,k,titlename)​subplot(i,j,k),imshow(im)hold on[x,y] = find(skeleton);plot(y,x,'r.')​title(['\fontsize{16}',titlename])xlabel(['\fontsize{16} Time consuming ( second )：',num2str(t)])end​

3 Running results

4 reference

[1] Shi Congwei , Zhao Jieyu , Chang Junsheng . Skeleton feature extraction algorithm based on axis transformation [J]. Computer engineering , 2019, 45(7):9.

About bloggers ： Good at intelligent optimization algorithms 、 Neural networks predict 、 signal processing 、 Cellular automata 、 The image processing 、 Path planning 、 UAV and other fields Matlab Simulation , relevant matlab Code problems can be exchanged by private letter .

Some theories cite network literature , If there is infringement, contact the blogger to delete .