Face And Eye Detection In Cv2 Using Haarcascades - With Source Code - Easiest Way - 2024

So in today’s very interesting blog, we will see how we can perform face and eye detection in cv2 using Haarcascades. This is going to be a very easy and fun project. Remember it’s only detection and not recognition.

This is going to be a very interesting blog, so without any further due, Let’s do it…

Checkout the video here – https://youtu.be/x6g-UvkwAzE

Table of Contents

Code for Face and eye detection in cv2…

import cv2

face_detector = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
eye_detector = cv2.CascadeClassifier('haarcascade_eye.xml')

cam = cv2.VideoCapture(0)

ret = True

while ret:
    ret, frame = cam.read()

    if ret == True:
        gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
        face_points = face_detector.detectMultiScale(gray, 1.3, 5)
        for (x, y, w, h) in face_points:
            cv2.rectangle(frame, (x, y), (x+w, y+h), (255, 0, 20), 2)
        
            face = frame[y:y+h,x:x+w]
            eyes = eye_detector.detectMultiScale(face,1.3,5)
            for (x, y, w, h) in eyes:
                cv2.rectangle(face, (x, y), (x+w, y+h), (155, 0, 120), 2)

        cv2.imshow('Live feed', frame)

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

cam.release()
cv2.destroyAllWindows()

Line 1 – Importing required library cv2, for face and eye detection in cv2.
Line 3 – In this line, we are creating a Haarcascade object to detect faces in the frame.
Line 4 – In this line, we are creating a Haarcascade object to detect eyes in the frame.
Line 6 – Creating a VideoCapture object to access the webcam. Argument 0 is passed when we want to use the inbuilt webcam of PC/Laptop, use 1 if you want to use any external camera.
Line 8 – Let’s set ret=True (just a formality to start the infinite loop).
Let’s start the loop…
Line 11 – We are using cam.read() to read the current frame from the webcam.
Line 13 – This if statement says that if we are getting frames from the webcam without any error, then proceed further, because in that case, ret would be True.
Line 14 – Convert the image from BGR to grayscale because Haar Cascades detect faces in grayscale images efficiently.
Line 15 – Let’s detect the faces using detectMultiscale, Now we have our face coordinates as (x,y,w,h) where (x,y) are the coordinates of the top-left of the rectangle around the face, w is the width and h is the height of the rectangle.
Line 16-17 – Let’s traverse through the faces and draw rectangles around them.
Line 19 – Let’s just extract the face.
Line 20 – Detect eyes just in the same way as we did above for faces.
Line 21-22 – Let’s traverse through the eyes and draw rectangles around them.
Line 24 – Showing results.
Line 26-27 – If someone hits the ESC key, break the code.
Line 29-30 – Realease the cam object to close the webcam and destroy all open windows.