[image detection] line recognition based on Hough transform (fitting angle bisector) with matlab code

1 brief introduction

Line detection is an important part of digital image processing , In road recognition , Building identification , Medical image analysis and other fields have very important applications . Through the edge detection of the obtained image , And then use Hough Transform edge detection for line detection . The method is simple , It is less affected by the gap and noise in the straight line . stay Matlab The method is simulated in the environment , The linear object in the image is detected , The results show that this method is fast and effective for detecting linear objects in images .​

2 Part of the code

function chengxu()

% The first 1 Step

close all

I=imread('1.jpg');  % Read images

I=rgb2gray(I);    % Color image is converted into gray image

% I=im2bw(I);      % Two valued

I=edge(double(I)); % Detect the edge of the image

figure

imshow(I)          % Display the results of edge detection

% The first 2 Step

[m,n]=size(I);     % Calculate the size of the image

M=3;             % Definition X Number of blocks divided by direction

N=3;             % Definition Y Number of blocks divided by direction

mm=floor(m/M);   % The length of the sub block row

nn=floor(n/N);   % The length of the subblock column

count=1;         % Counter

figure

for i=1:M

    for j=1:N

        A=I((i-1)*mm+1:i*mm,(j-1)*nn+1:j*nn);    % Segment the original image , Get a sub block

        subplot(M,N,count)

        imshow(A)               % Display a sub block

        zuoshangjiao=[(i-1)*mm+1 (j-1)*nn+1];  % Coordinates of the upper left corner of the sub block

        [x,y,k,b]=zikuai(A,zuoshangjiao);      % Get the slope of the straight line fitting the white pixels in the sub block k And intercept b（ call zikuai function ）

        X{count}=x;       % Save all white pixels in the sub block x coordinate

        Y{count}=y;       % Save all white pixels in the sub block y coordinate

        K(count)=k;       % Save the slope of the fitted line in the sub block k

        B(count)=b;       % Save the intercept of the fitted line in the sub block b

        count=count+1;    % Counter plus 1, Calculate the next sub block

    end

end

% The first 3 Step

KK=K(~isnan(K));   % Get rid of K Medium NaN（ White pixels are less than 10 Sub block of ）

BB=B(~isnan(B));   % Get rid of B Medium NaN（ White pixels are less than 10 Sub block of ）

mean_K=mean(KK);   % Find the average of all slopes

mean_B=mean(BB);   % Find the average of all intercepts

figure

subplot(2,1,1)

plot(KK,'-o')

title(' The straight line fitted by each sub block k value ')

subplot(2,1,2)

plot(BB,'-o')

title(' The straight line fitted by each sub block b value ')

% Draw the angle bisector

xx0=[1 m];

yy0=[1 n];

YY1=K01*xx0+B01;  % The angular bisector 1

YY2=K02*xx0+B02;  % The angular bisector 2

plot(xx0,YY1);    % Draw the angle bisector 1

plot(xx0,YY2);    % Draw the angle bisector 2

view([90 90])

end

3 Simulation results

4 reference

[1] Tangjialin , Wangzhenbo , Zhangxinxin . Line detection technology based on Hough transform [J]. Technology Information , 2011(14):2.

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 .