how can i follow canny output?

Question

nadia 2016-10-26

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/309208-how-can-i-follow-canny-output

评论： nadia 2016-10-27

I segment a mammography breast image but the border of it is not accurate. I also have canny output of the image. now, I want to expand breast region to outer border of canny, but I do not know how to do it? I insert the output of breast segmentation and canny output below. I want to expand segmentation to outer border of canny. can you help me?

1 个评论
显示 -1更早的评论隐藏 -1更早的评论

nadia 2016-10-26

no one has any suggestion?

请先登录，再进行评论。

请先登录，再回答此问题。

Answer 1

Image Analyst 2016-10-26

0
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/309208-how-can-i-follow-canny-output#answer_240837

activecontour_demo.m

Why did you use canny anyway? Why not just threshold? Or maybe you can use activecontour() for a smoother outline.

8 个评论
显示 6更早的评论隐藏 6更早的评论

Image Analyst 2016-10-26

在 MATLAB Online 中打开

triangle_threshold.m

Why do you need to "remove" the background anyway? The signal is very low. If you need to mask it off, I'd probably just use a triangle threshold (attached) and erase it.

clc;    % Clear the command window.
close all;  % Close all figures (except those of imtool.)
clear;  % Erase all existing variables. Or clearvars if you want.
workspace;  % Make sure the workspace panel is showing.
format long g;
format compact;
fontSize = 20;
filename = 'D:\Matlab\work\Tests\mdb00.png';
grayImage = imread(filename);
subplot(2, 2, 1);
imshow(grayImage);
title('Original Image', 'FontSize', fontSize);
% Set up figure properties:
% Enlarge figure to full screen.
set(gcf, 'Units', 'Normalized', 'OuterPosition', [0 0 1 1]);
% Get rid of tool bar and pulldown menus that are along top of figure.
set(gcf, 'Toolbar', 'none', 'Menu', 'none');
% Give a name to the title bar.
set(gcf, 'Name', 'Demo by ImageAnalyst', 'NumberTitle', 'Off') 
pixelCounts = imhist(grayImage);
thresholdLevel = triangle_threshold(pixelCounts, 'R', true)
mask = grayImage > thresholdLevel;
subplot(2, 2, 2);
imshow(mask);
title('Initial Mask', 'FontSize', fontSize);
mask = bwareafilt(mask, 1); % Take largest blob only
mask = ~imfill(mask, 'holes');
subplot(2, 2, 3);
imshow(mask);
title('Final Mask', 'FontSize', fontSize);
grayImage(mask) = 0;
subplot(2, 2, 4);
imshow(grayImage);
title('Final, Masked Image', 'FontSize', fontSize);

Image Analyst 2016-10-26

Zero out the pixelCount(1). There's something weird about the histogram so it's not finding the right threshold. It's because the second bin is zero and the first bin is real high. Zeroing out the first bin will fix that.

nadia 2016-10-27

no, this solution dose not work. because in some other images by zero out the pixelCount(1),threshold become very big and only some white part remain.

请先登录，再进行评论。