Python Image Processing Cookbook

How to do it...

Run the following steps to implement facial alignment using the imutil library (from PyImagesearch):

1. First, initialize the face detector from dlib. Load the pre-trained model as a facial landmark predictor and, finally, instantiate a FaceAligner object from imutils:

detector = dlib.get_frontal_face_detector()predictor = dlib.shape_predictor('models/shape_predictor_68_face_landmarks.dat')face_aligner = FaceAligner(predictor, desiredFaceWidth=256)

2. Read the input image from disk, resize the image, and convert it into grayscale:

image = cv2.imread('images/scientists.png')image = imutils.resize(image, width=800)gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)

Now, if you plot the original image, you will get an output like the ...