Python/OpenCV - Colored Droplets Recognition and Tracking

Question

I'm a semi-noob in Video Analysis. I have a Petri dish with some colored droplets inside and I must detect them, and keep trace of their position,area and color.

I want first to detect my Petri dish (maybe using HoughCircles) and define a ROI on which work later.

The problem is that mi dish detection is very "noisy": the program detects many circles (and I only need the one corresponding to the dish) and it never detects the right one.

Here is my code:

import cv2
import numpy as np

def main():
    cap=cv2.VideoCapture("dropletsS.wmv")
    cv2.namedWindow("prova")
    while(1):
        ret, RGBframe = cap.read()
        grayFrame = cv2.cvtColor(RGBframe,cv2.COLOR_BGR2GRAY)
        grayFrame=cv2.medianBlur(grayFrame,7)
        circles=cv2.HoughCircles(grayFrame,cv2.HOUGH_GRADIENT ,50,50)
        for c in circles[0,:]:
            cv2.circle(RGBframe,(c[0],c[1]),c[2],(0,255,0),2)

        cv2.imshow("prova", RGBframe)
        cv2.imshow("grigio", grayFrame)
        cv2.waitKey(10)

if __name__ == "__main__":
    main()

And here is the result.

Do someone have some suggestions? Suggestions on the way I can later identify and track droplets are welcome too. Thanks in advance!

Answer 1

Its kind of hard to come up with a solution without having much of an idea on how the dish actually looks like, but I'll try helping you anyways.

If the problem is what I think it is, then you can probably open and dilate your image to join all the discontinuous blobs.

Do the following before you apply Hough Transform:

kernel = cv2.getStructuringElement(cv2.MORPH_ELLIPSE, (5,5)) #declare outside while

grayFrame = cv2.morphologyEx(grayFrame, cv2.MORPH_OPEN, kernel)
grayFrame = cv2.dilate(grayFrame, kernel, iterations = 2)

Let me know if the output is output image that you desire. Also play around with the parameters to get the required result. You can change the dimensions of the MORPH_ELLIPSE and also the number of iterations. Increasing any of them would increase the degree of dilation, thus more of the blobs would join up and vice versa.