Shape Detection in OpenCV | Detect Circles, Rectangles, and Polygons with Python

Chapter 3.2: Shape Detection (Circle, Rectangle, Polygon)

Detecting shapes like circles, rectangles, and polygons is an important task in computer vision. OpenCV provides powerful tools such as cv2.findContours(), cv2.approxPolyDP(), and cv2.HoughCircles() to identify and draw different shapes.

🟨 Detecting Rectangles & Polygons

Using contours and cv2.approxPolyDP(), we can approximate the number of sides and classify the shape (triangle, rectangle, polygon).

import cv2

img = cv2.imread("shapes.jpg")
gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
_, thresh = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)

contours, _ = cv2.findContours(thresh, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

for cnt in contours:
    approx = cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt, True), True)
    if len(approx) == 3:
        shape = "Triangle"
    elif len(approx) == 4:
        shape = "Rectangle"
    elif len(approx) > 4:
        shape = "Polygon"
    else:
        shape = "Unknown"
    
    cv2.drawContours(img, [approx], 0, (0,255,0), 2)
    x, y = approx.ravel()[0], approx.ravel()[1] - 10
    cv2.putText(img, shape, (x, y), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,255,255), 2)

cv2.imshow("Shape Detection", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

⚪ Detecting Circles

Circles can be detected using the Hough Circle Transform method with cv2.HoughCircles().

circles = cv2.HoughCircles(gray, cv2.HOUGH_GRADIENT, dp=1.2, minDist=50,
                           param1=100, param2=30, minRadius=20, maxRadius=100)

if circles is not None:
    circles = circles[0, :]
    for (x, y, r) in circles:
        cv2.circle(img, (x, y), r, (255, 0, 0), 2)
        cv2.putText(img, "Circle", (x-10, y-10),
                    cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,255,255), 2)

cv2.imshow("Circle Detection", img)
cv2.waitKey(0)
cv2.destroyAllWindows()

✅ In this lesson, you learned how to detect rectangles, polygons, and circles in OpenCV. These techniques are widely used in object recognition, robotics, document analysis, and pattern detection.
👉 Next, we will explore color detection and masking in OpenCV.