13

I have the following image: img1

enter image description here

I'm trying to count al these colored cells and draw a circle around them. I really don't now how I can use SelectComponents for this image. And EdgeDetect has the following result: img2

enter image description here

Maybe some tips or examples.

Greetings

kglr
  • 394,356
  • 18
  • 477
  • 896
Glenn
  • 131
  • 1
  • 3
  • If you just want information about the components (centroid, caliper length), ComponentMeasurements should be more useful than SelectComponents – Niki Estner Dec 07 '12 at 13:59
  • No, I want to know how you can use these functions to count the cell (examples) – Glenn Dec 07 '12 at 14:04
  • 3
    Have you looked at MorphologicalComponents ? – image_doctor Dec 07 '12 at 14:11
  • I have an impression that this is not the original image. What is the very original image you start from? – Vitaliy Kaurov Dec 07 '12 at 17:13
  • Welcome to Mathematica.SE! I suggest the following: 1) As you receive help, try to give it too, by answering questions in your area of expertise. 2) Read the FAQs! 3) When you see good Q&A, vote them up by clicking the gray triangles, because the credibility of the system is based on the reputation gained by users sharing their knowledge. ALSO, remember to accept the answer, if any, that solves your problem, by clicking the checkmark sign` – Vitaliy Kaurov Dec 09 '12 at 09:03
  • If you are able to use colorize it seems like you already have all the components isolated and don't need to do image processing. If you post your code to get to this point I think it would be very simple to count the number of components. – s0rce Dec 09 '12 at 16:42

1 Answers1

17

I will follow algorithm described in the following blog, but will have to modify some parameters for your case. You can also drop FillingTransform from the blog code because you don't have holes in your regions.

rbc = ImageCrop[   Import["https://i.stack.imgur.com/wOJps.png"], {300, 340}];

b = DeleteSmallComponents[ColorNegate[Binarize[rbc, .81]], 50];
distT = DistanceTransform[b, Padding -> 0];
marker = MaxDetect[ImageAdjust[distT], 0.02];
w = WatershedComponents[GradientFilter[b, 3], marker, 
   Method -> "Rainfall"];

cells = SelectComponents[w, "Count", 500 < # < 3000 &];
measures = 
  ComponentMeasurements[
   cells, {"Centroid", "EquivalentDiskRadius", "Label"}];
Show[rbc, 
 Graphics[{Blue, Circle @@ # & /@ (measures[[All, 2, 1 ;; 2]]), 
   MapThread[Text, {measures[[All, 2, 3]], measures[[All, 2, 1]]}]}]]

enter image description here

Then bare number of circled cells can be computed with 

measures // Length

16

Vitaliy Kaurov
  • 73,078
  • 9
  • 204
  • 355