3

I am working on a shape detection algorithm with opencv in python. I am using Contours from the library and I have had some shapes being detected successfully: Circle, Rectangle and Triangle. The only problem is that I only need to detect circles rectangles and octagons. Also, the circle was working, but inconsistently. So, this is my code: 

import cv2
import numpy as np

def nothing(x):
    # any operation
    pass

cap = cv2.VideoCapture(1)

cv2.namedWindow("Trackbars")
cv2.createTrackbar("L-H", "Trackbars", 0, 180, nothing)
cv2.createTrackbar("L-S", "Trackbars", 66, 255, nothing)
cv2.createTrackbar("L-V", "Trackbars", 134, 255, nothing)
cv2.createTrackbar("U-H", "Trackbars", 180, 180, nothing)
cv2.createTrackbar("U-S", "Trackbars", 255, 255, nothing)
cv2.createTrackbar("U-V", "Trackbars", 243, 255, nothing)

font = cv2.FONT_HERSHEY_COMPLEX

while True:
    _, frame = cap.read()
    hsv = cv2.cvtColor(frame, cv2.COLOR_BGR2HSV)

    l_h = cv2.getTrackbarPos("L-H", "Trackbars")
    l_s = cv2.getTrackbarPos("L-S", "Trackbars")
    l_v = cv2.getTrackbarPos("L-V", "Trackbars")
    u_h = cv2.getTrackbarPos("U-H", "Trackbars")
    u_s = cv2.getTrackbarPos("U-S", "Trackbars")
    u_v = cv2.getTrackbarPos("U-V", "Trackbars")

    lower_yellow = np.array([l_h,l_s, l_v])
    upper_yellow = np.array([u_h, u_s, u_v])

    mask = cv2.inRange(hsv, lower_yellow, upper_yellow)
    kernel = np.ones((5, 5), np.uint8)
    mask = cv2.erode(mask, kernel)

    # Contours detection
    if int(cv2.__version__[0]) > 3:
        # Opencv 4.x.x
        contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)
    else:
        # Opencv 3.x.x
        _, contours, _ = cv2.findContours(mask, cv2.RETR_TREE, cv2.CHAIN_APPROX_SIMPLE)

    for cnt in contours:
        area = cv2.contourArea(cnt)
        approx = cv2.approxPolyDP(cnt, 0.02*cv2.arcLength(cnt, True), True)
        x = approx.ravel()[0]
        y = approx.ravel()[1]

        if area > 400:
            cv2.drawContours(frame, [approx], 0, (0, 0, 0), 5)

            if len(approx) == 3:
                cv2.putText(frame, "Triangle", (x, y), font, 1, (0, 0, 0))
            elif len(approx) == 4:
                cv2.putText(frame, "Rectangle", (x, y), font, 1, (0, 0, 0))
            elif 10 < len(approx) < 20:
                cv2.putText(frame, "Circle", (x, y), font, 1, (0, 0, 0))

    cv2.imshow("Frame", frame)
    cv2.imshow("Mask", mask)

    key = cv2.waitKey(1)
    if key == 27:
        break

cap.release()
cv2.destroyAllWindows()

What I would like to have is to detect octagons and circles more accurately.

Improve this question

1 Answer 1

Reset to default
4

To perform shape detection, we can use contour approximation. With the assumption that the objects are simple shapes, here's an approach using thresholding + contour approximation. Contour approximation is based on the assumption that a curve can be approximated by a series of short line segments which can be used to determine the shape of a contour. For instance, a triangle has three vertices, a square/rectangle has four vertices, a pentagon has five vertices, and so on.

  1. Obtain binary image. We load the image, convert to grayscale, then Otsu's threshold to obtain a binary image.

  2. Detect shapes. Find contours and identify the shape of each contour using contour approximation filtering. This can be done using arcLength to compute the perimeter of the contour and approxPolyDP to obtain the actual contour approximation.

Input image

Labeled shapes

Code

import cv2

def detect_shape(c):
    # Compute perimeter of contour and perform contour approximation
    shape = ""
    peri = cv2.arcLength(c, True)
    approx = cv2.approxPolyDP(c, 0.04 * peri, True)

    # Triangle
    if len(approx) == 3:
        shape = "triangle"

    # Square or rectangle
    elif len(approx) == 4:
        (x, y, w, h) = cv2.boundingRect(approx)
        ar = w / float(h)

        # A square will have an aspect ratio that is approximately
        # equal to one, otherwise, the shape is a rectangle
        shape = "square" if ar >= 0.95 and ar <= 1.05 else "rectangle"

    # Pentagon
    elif len(approx) == 5:
        shape = "pentagon"

    # Hexagon
    elif len(approx) == 6:
        shape = "hexagon"

    # Octagon 
    elif len(approx) == 8:
        shape = "octagon"

    # Star
    elif len(approx) == 10:
        shape = "star"

    # Otherwise assume as circle or oval
    else:
        shape = "circle"

    return shape

# Load image, grayscale, Otsu's threshold
image = cv2.imread('1.png')
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
thresh = cv2.threshold(gray, 0, 255, cv2.THRESH_BINARY_INV + cv2.THRESH_OTSU)[1]

# Find contours and detect shape
cnts = cv2.findContours(thresh, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
cnts = cnts[0] if len(cnts) == 2 else cnts[1]
for c in cnts:
    # Identify shape
    shape = detect_shape(c)

    # Find centroid and label shape name
    M = cv2.moments(c)
    cX = int(M["m10"] / M["m00"])
    cY = int(M["m01"] / M["m00"])
    cv2.putText(image, shape, (cX - 20, cY), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (36,255,12), 2)

cv2.imshow('thresh', thresh)
cv2.imshow('image', image)
cv2.waitKey()
Improve this answer
Sign up to request clarification or add additional context in comments.

3 Comments

Thanks, for answering. This is so helpful. I just want to say that I am using real time image processing(reading from a camera), but yours work for only a picture on your computer which is cool, but doesn't match my need.
This example was to demonstrate how to perform shape detection on an image, you can adapt the answer to process on each frame read from the camera. Its the same concept just applying the detection onto every frame
Okay, thanks a lot for demonstrating this for me. If any problem comes up I am going to inform you about it.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Start asking to get answers

Find the answer to your question by asking.

Ask question

Explore related questions

See similar questions with these tags.