How to count number of objects in the image, compute their areas, and make probability distribution of the areas?

2 次查看（过去 30 天）

显示更早的评论

Jialin Men 2022-12-30

0
链接

此问题的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1886302-how-to-count-number-of-objects-in-the-image-compute-their-areas-and-make-probability-distribution

编辑： Image Analyst 2022-12-31

采纳的回答： Image Analyst

Hello friends,

I just would like to know how to calculate the objects of image and do the area distribution.

Thanks so much in advance.

0 个评论
显示 -2更早的评论隐藏 -2更早的评论

请先登录，再进行评论。

请先登录，再回答此问题。

采纳的回答

Image Analyst 2022-12-30

1
链接

此回答的直接链接

https://ww2.mathworks.cn/matlabcentral/answers/1886302-how-to-count-number-of-objects-in-the-image-compute-their-areas-and-make-probability-distribution#answer_1138577

在 MATLAB Online 中打开

In your other question, I saw that you already have a segmented image. So in that case, you can get an area distribution like this

props = regionprops(mask, 'Area');
histogram([props.Area]);
grid on;
title('Histogram of Areas');
xlabel('Area');
ylabel('Count');

4 个评论
显示 2更早的评论隐藏 2更早的评论

Jialin Men 2022-12-30

Hallo Image Analyst,

I have clicked the Accept this answer.

I have another question.

If I want to know the number of pixels of each particle in this image,

I could also use as below ? right?

props = regionprops(mask, 'PixelValue');

histogram([props.PixelValue]);

Image Analyst 2022-12-31

编辑：Image Analyst 2022-12-31

在 MATLAB Online 中打开

No, that's not right. PixelValue is a list of gray levels of all the pixels in each blob. If you want to know the number of pixels in each blob, you need to ask for 'Area':

props = regionprops(mask, 'Area');
allAreas = [props.Area]

You might use bwmorph and use things like the 'bridge' option to break apart barely touching particles. You might also look at watershed. See these links:

Watershed transform question from tech support » Watershed transform question from tech support

Marker-Controlled Watershed Segmentation - MATLAB & Simulink Example

The Watershed Transformation page

请先登录，再进行评论。