Autonomize count and identification of particles in RGB image



Hi all,

New the forum. I did quite a bit of searching and exploration for my answer with no success. I have several thousand photos of urchin guts taken using a stereoscope and I need to count and identify particles >0.5mm as red, brown, or green algae. Needless to say, this takes forever to do manually. To my understanding, ImageJ can automatically segment and count particles, but can it count particles based on a defined RGB threshold? For example, some urchin diets are a mixture of red, brown, and green algae. Each particles can assume multiple shades of their associated color (i.e., RGB), but nonetheless are visually distinct from one another. So, using imageJ, is there a useful method for segmenting/counting and identifying particles based on an RGB color threshold? I’ve attached an image for reference.



Welcome to the Forum!

Here are a few plugins you can take a look at to help you segment your algae:

  • Trainable Weka Segmentation (TWS) plugin - a great tool for segmentation that comes directly with Fiji. NOTE: Fiji is Just ImageJ - it is simply a distribution of ImageJ that comes with a bunch of plugins bundled - ready for you to use out-of-the-box. If you are just getting started, we recommend downloading/using Fiji.
  • Color Counter plugin - counts the number of unique colors in an RGB image or stack
  • Color Pixel Counter plugin - counts the number of pixels on an image (or selection) of a specified color

This should give you a couple of options to get started. You can also check out this other forum thread that is somewhat similar to what you need:

Hope this helps!

eta :slight_smile: