Face Detection is a technology to identify faces from the image. We use Python’s OpenCV for this. We can also use Face Detection in the case of Animals too. If one can take a close look at the OpenCV repository, the haar cascades directory to be specific (where the OpenCV stores all its pre-trained haar classifiers to detect various objects, body parts, etc.), there are two files:
- haarcascade_frontalcatface.xml
- haarcascade_frontalcatface_extended.xml
The objective of the program given is to detect the object of interest(cat face) in real-time and to keep tracking the same object. This is a simple example of how to detect the cat face in Python. You can try to use training samples of any other object of your choice to be detected by training the classifier on required objects.
Below is the implementation.
# OpenCV program to detect cat face in real time # import libraries of python OpenCV # where its functionality resides import cv2 # load the required trained XML classifiers # data/haarcascades/haarcascade_frontalcatface.xml # Trained XML classifiers describes some features of some # object we want to detect a cascade function is trained # from a lot of positive(faces) and negative(non-faces) # images. face_cascade = cv2.CascadeClassifier('haarcascade_frontalcatface.xml') # capture frames from a camera cap = cv2.VideoCapture(0) # loop runs if capturing has been initialized. while 1: # reads frames from a camera ret, img = cap.read() # convert to gray scale of each frames gray = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY) # Detects faces of different sizes in the input image faces = face_cascade.detectMultiScale(gray, 1.3, 5) for (x,y,w,h) in faces: # To draw a rectangle in a face cv2.rectangle(img,(x,y),(x+w,y+h),(255,255,0),2) roi_gray = gray[y:y+h, x:x+w] roi_color = img[y:y+h, x:x+w] # Display an image in a window cv2.imshow('img',img) # Wait for Esc key to stop k = cv2.waitKey(30) & 0xff if k == 27: break # Close the window cap.release() # De-allocate any associated memory usage cv2.destroyAllWindows() |
Output:
