Message Boards Message Boards


Get cell boundaries in a noisy image?

Posted 5 years ago
2 Replies
4 Total Likes

I have a microscope image of some animal tissue and wish to get the contours for all the cells that are present in the image. the cells are connected to the neighbouring cells via these contours. At the bottom of the image the signal intensity is faint but the human eye can still detect some contours.

I have tried a bunch of techniques including the use of ClusteringComponents and MorphologicalBinarize, LaplacianGaussianFilter and GradientFilter but have been unsuccessful in my approaches. The particular problem I am facing is the inability to get rid of the noisy signal (grains/granules whatever you may wish to call them) inside the contours during segmentation.

Can anyone kindly help me for my research problem. Thanks in advance.

enter image description here

2 Replies

I encounter similar noise with astrophotography. I'm not sure about the origin of your image's noise, or if astro techniques will properly address the issue you are seeing but you might try a combination of:

1) Subtracting a dark frame (or an averaged set of dark frames). These are exposures of the same length as the 'light' frame, but with the camera blocked so that no light enters. It is probably irrelevant for your work, but your camera should be at the same temperature during the dark frames as the light frames. This will remove thermal noise associated with the CCD.

2) Subtract a 'bias' frame, which is like a dark frame but of extremely short duration. This frame removes noise intrinsic to the readout of the CCD's data.

3) Take a series of light frames and combine them using Mean or Median statistical function. This will average out the noise and improve the SNR.

Detailed answer to this question was posted here:

Segment noisy microscope image into cell boundaries via valleys

Reply to this discussion
Community posts can be styled and formatted using the Markdown syntax.
Reply Preview
or Discard

Group Abstract Group Abstract