In this project we are going to implement Coin Detection algorithm in OpenCV Python. We are going to use real time webcam feed for detecting the coins. We created a simulated lab bench environment where we tested our algorithm. Similar code could be used in Raspberry PI as well. So if you installed the OpenCV in Raspberry Pi you can use same code to implement a coin detection code in the raspberry pi as well.
Coin Detection Code
Here is the complete code for the coin detection in Python using OpenCV library. We used the Hough Circle algorithm for circle identification later we created some threshold value for detecting the circle of the size of our coin. We then segment the image and fetch those circle using contour analysis in OpenCV Python. If you want to learn more about the contour detection you can check one of my previous post about contour detection in OpenCV Python where I discussed this in detail.
Here is the code
import cv2 import numpy as np cap = cv2.VideoCapture(1) cap.set(3,320) cap.set(4,240) while(True): # Capture frame-by-frame ret, frame = cap.read() if ret: gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) circles = cv2.HoughCircles(gray, 3, 1.2, 100) # ensure at least some circles were found if circles is not None: # convert the (x, y) coordinates and radius of the circles to integers circles = np.round(circles[0, :]).astype("int") # loop over the (x, y) coordinates and radius of the circles for (x, y, r) in circles: # draw the circle in the output image, then draw a rectangle # corresponding to the center of the circle cv2.circle(frame, (x, y), r, (0, 255, 0), 4) cv2.rectangle(frame, (x - 5, y - 5), (x + 5, y + 5), (0, 128, 255), -1) # show the output image #cv2.imshow("output", np.hstack([image, output])) cv2.imshow('frame',frame) if cv2.waitKey(1) & 0xFF == ord('q'): break else: print('no frame') break; # When everything done, release the capture cap.release() cv2.destroyAllWindows()Code language: Python (python)