These are my notes based on Jason Dsouza’s excellent OpenCV video course.
python3 -m pip install opencv-contrib-python
Finding a Classifier
OpenCV’s face detection loads a cascade classifier which is then used to detect faces.
Running the classifier
Using an image with a face (or many faces); we can detect them with:
import cv2 as cv img = cv.imread('Photos/people.jpg') cascade_file = 'haarcascade_frontalface_default.xml' haar_cascade = cv.CascadeClassifier(cascade_file) faces_rect = haar_cascade.detectMultiScale( cv.cvtColor(img, cv.COLOR_BGR2GRAY), scaleFactor=1.1, minNeighbors=5) for (x,y,w,h) in faces_rect: cv.rectangle(img, (x,y), (x+w, y+h), (0,255,255), 2) cv.imshow('Detected faces', img) cv.waitKey(0)
For the Super Mario Movie cast, I got these results.
There were a few false positives and negatives.
This could be further tuned by adjusting the
minNeighbours parameters; however, this isn’t the best idea since we would only be tuning the face detection to work with a specific type of image.