This code captures video from the webcam, detects faces in real-time using the Haar Cascade Classifier, and draws rectangles around the detected faces. The video feed is displayed in a window, and the program can be terminated by pressing the 'Esc' key.

python

import cv2

This imports the OpenCV library, which is widely used for computer vision tasks.

python

alg = "haarcascade_frontalface_default.xml" haar_cascade = cv2.CascadeClassifier(alg)

• alg: Specifies the XML file that contains the Haar Cascade classifier data for detecting frontal faces.
• cv2.CascadeClassifier(alg): Loads the Haar Cascade classifier from the XML file into the haar_cascade object.

python

cam = cv2.VideoCapture(0)

• cv2.VideoCapture(0): Initializes the webcam for video capture. The argument 0 typically refers to the default webcam on the computer.

python

while True: _, img = cam.read()

• cam.read(): Captures a frame from the webcam. The underscore _ is used to ignore the first return value (a boolean indicating if the frame was read correctly), and img stores the captured frame.

python

grayImg = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

• cv2.cvtColor(img, cv2.COLOR_BGR2GRAY): Converts the captured color image to grayscale. This is done because face detection using Haar Cascades works better on grayscale images.

python

face = haar_cascade.detectMultiScale(grayImg, 1.3, 4)

• haar_cascade.detectMultiScale(grayImg, 1.3, 4): Detects faces in the grayscale image. The method returns a list of rectangles where faces are detected.
  • grayImg: The input grayscale image.
  • 1.3: The scale factor for the image pyramid (how much the image size is reduced at each image scale).
  • 4: The minimum number of neighbors each candidate rectangle should have to retain it.

python

 `for (x, y, w, h) in face:
    x1,y1=x+w, y+h

    cv2.line(img, (x,y), (x+30, y),(0, 255, 0), 6)
    cv2.line(img, (x,y), (x, y+30),(0, 255, 0), 6)

    cv2.line(img, (x1,y), (x1-30, y),(0, 255, 0), 6)
    cv2.line(img, (x1,y), (x1, y+30),(0, 255, 0), 6)

    cv2.line(img, (x,y1), (x+30, y1),(0, 255, 0), 6)
    cv2.line(img, (x,y1), (x, y1-30),(0, 255, 0), 6)

    cv2.line(img, (x1,y1), (x1-30, y1),(0, 255, 0), 6)
    cv2.line(img, (x1,y1), (x1, y1-30),(0, 255, 0), 6)` 

• Iterates over the list of detected faces. For each face, a rectangle is drawn on the original image (img):
  • (x, y): The top-left corner of the rectangle.
  • (x, y1): The bottom-left corner of the rectangle.
  • (x1, y): The bottom-right corner of the rectangle.
  • (x1, y1): The bottom-leftcorner of the rectangle.
  • (0, 0, 255): The color of the rectangle (red in BGR format).
  • 2: The thickness of the rectangle's border.

python

cv2.imshow("Face Detection", img)

• cv2.imshow("Face Detection", img): Displays the image with detected faces in a window titled "Face Detection".

python

key = cv2.waitKey(10) if key == 27: break

• cv2.waitKey(10): Waits for 10 milliseconds for a key press.
• if key == 27: Checks if the 'Esc' key (ASCII value 27) is pressed. If so, it breaks the loop and stops the program.

python

cam.release() cv2.destroyAllWindows()

• cam.release(): Releases the webcam resource.
• cv2.destroyAllWindows(): Closes all OpenCV windows.

🤖 AI & ML Developer | Data Science & Analytics Expert
🌐 Web Apps & IoT Skilled | Awesome UI Creator
💻 AI is my main focus! 👾