Quantifying Weka Output with equation and obtaining RGB values

Hi! I am new to image processing and am having some difficulty obtaining the necessary outputs.

I have pictures of algae which I need to quantify growth in a non-destructive manner. My endpoints would be obtaining min, mean, max intensity RGB values, and then use color threshold to estimate photosynthetic pixels for the algae selection in each image.

I have been able to use Trainable Weka Segmentation to delineate what is algae and what is not, but I am having difficulty taking the output from the Segmentation processing and applying the calculations to the values about the 90% certainty threshold. Do I need to write a macro? Has anyone had experience in this?


Let’s see if I am understanding you correctly. You have already used Trainable Weka Segmentation to identify which pixels to consider as algae. Now you want to find the stats on the RGB values of those pixels but not the others. Is that correct? In that case, I think you might be able to get your stats this way:

  1. Use Split Channels to separate the RGB values into their own gray-scale images.
  2. Use the output of Trainable Weka Segmentation with Create Selection to select the pixels you want.
  3. Use Measure to get the min, max, and mean. You may need to use Set Measurements to adjust which values are determined.
1 Like