Detecting Contours in an Image: A Step-by-Step Guide
Have you ever wondered how computers can detect the edges of an object in a picture? This is called contour detection, and it is a fundamental technique in computer vision.
It is useful in various applications, such as object recognition, shape analysis, and image segmentation. In this article, we will take you through the steps of detecting contours in an image using OpenCV, a popular computer vision library developed by Intel.
We will explain each step in detail and provide example code to help you implement it on your own. If youre ready, lets get started!
Importing Modules
Before we start, we need to import the necessary modules. OpenCV provides several functions for image processing and analysis, while matplotlib can be used to display the image and its contours.
Heres how we can import them:
“`
import cv2
from matplotlib import pyplot as plt
“`
Loading Image into the Program
The next step is to load the image into our program. We can use the `imread` function of OpenCV to read the image in RGB format.
Heres an example:
“`
image = cv2.imread(‘example.jpg’, cv2.IMREAD_COLOR)
“`
Converting Image to Grayscale
The contour detection algorithm works on grayscale images. Therefore, we need to convert our image to grayscale before applying the algorithm.
We can use the `cvtColor` function of OpenCV to do this. Heres an example:
“`
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
“`
Getting Binary Image
The contour detection algorithm requires a binary image as input. Therefore, we need to convert our grayscale image into a binary image.
We can use the `threshold` function of OpenCV to do this. Heres an example:
“`
ret, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
“`
The `threshold` function returns two values: the threshold value and the binary image.
We set the threshold value to 127, which means that all pixel values below 127 will be set to 0, and all pixel values above 127 will be set to 255.
Detecting Contours
Finally, we are ready to detect contours in our binary image. We can use the `findContours` function of OpenCV to do this.
Heres an example:
“`
contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
“`
The `findContours` function returns two values: the contours themselves and a hierarchy of the contours. We set the retrieval mode to `cv2.RETR_EXTERNAL`, which means that we only want to retrieve the external contours.
We also set the contour approximation mode to `cv2.CHAIN_APPROX_SIMPLE`, which means that we want to approximate the contours as simple polygons. Final Code for
Detecting Contours
Heres the final code for detecting contours in an image:
“`
import cv2
from matplotlib import pyplot as plt
# Load the image
image = cv2.imread(‘example.jpg’, cv2.IMREAD_COLOR)
# Convert the image to grayscale
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)
# Convert the grayscale image to binary
ret, binary = cv2.threshold(gray, 127, 255, cv2.THRESH_BINARY)
# Detect contours in the binary image
contours, hierarchy = cv2.findContours(binary, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)
# Draw the contours on the original image
cv2.drawContours(image, contours, -1, (0, 255, 0), 2)
# Display the image with contours
plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
plt.show()
“`
In this code, we first load the image, convert it to grayscale, and then convert it to binary. We then use the `findContours` function to detect the contours in the binary image.
Finally, we use the `drawContours` function to draw the contours on the original image, and we display the image with contours using Matplotlib.
Results on a Different Image
To demonstrate the accuracy of contour detection, we applied the same method to a different image. Heres the original image:

And heres the result:

As you can see, the contour detection algorithm accurately detected the edges of the object in the image.
Conclusion
Contour detection is a fundamental technique in computer vision that can be useful in various applications. By following the steps outlined in this article, you can detect contours in an image using OpenCV and Python.
We hope you found this article informative and helpful. Happy coding!
Contour detection is a fundamental technique in computer vision that can be useful in various applications like object recognition, shape analysis, and image segmentation.
In this article, we took you through the steps of detecting contours in an image using OpenCV and explained each step in detail with example code for the readers to implement it themselves. By following these steps, the readers can detect contours in their images accurately and apply them in various applications.
Contour detection is an essential technique in computer vision, and mastering these techniques is highly recommended for a budding computer vision engineer.