Image processing and Segmentation

Hello, I have applied the "sobel" edge detection function. However, I am not sure how to segment and single out only the cells that contain the " cross" shape inside of them. These are the cells infected by Babesisos, while the rest are not infected.

Thanks !

Answer 1

[Shubham]

Hey @Alessio,

I understand that you have applied “Sobel” edge detection and now you want to segment out the cells which have “cross” shape in them.

For segmenting the cells, you can refer to “SEG-SELF Method” available on the file exchange: https://www.mathworks.com/matlabcentral/fileexchange/67313-cell-segmentation-seg-self-method

This method helps in detection and segmentation of touching cells.

A newer method RFOVE is also provided for the cell segmentation: https://www.mathworks.com/matlabcentral/fileexchange/74200-cell-segmentation-rfove-method

You may also try having a look at a previous case of MATLAB answer involving infected white cell detection in an image: https://www.mathworks.com/matlabcentral/answers/128701-infected-white-cell-detection-in-image

In the proposed answer, there was a discussion on Marker-Controlled Watershed Segmentation. You can refer to the documentation here: https://www.mathworks.com/help/images/marker-controlled-watershed-segmentation.html

I hope this helps!

Answer 2

[Image Analyst]

Not sure what cells you are talking about. And do you want cells if they are not fully contained in the image?

If you have any more questions, then attach your original gray scale image, and code with the paperclip icon after you read this:

TUTORIAL: How to ask a question (on Answers) and get a fast answer

In the meantime, see Steve's image processing blog:

https://blogs.mathworks.com/steve/2006/06/02/cell-segmentation/

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