Preprocess.py

from mtcnn.mtcnn import MTCNN
from PIL import Image
import numpy as np
import os

def extract_face(filename, required_size=(160, 160)):
    # load image from file
    image = Image.open(filename)
    # convert to RGB, if needed
    image = image.convert('RGB')
    # convert to array
    pixels = np.asarray(image)
    # create the detector, using default weights
    detector = MTCNN()
    # detect faces in the image
    results = detector.detect_faces(pixels)
    # extract the bounding box from the first face
    x1, y1, width, height = results[0]['box']
    # deal with negative pixel index
    x1, y1 = abs(x1), abs(y1)
    x2, y2 = x1 + width, y1 + height
    # extract the face
    face = pixels[y1:y2, x1:x2]
    # resize pixels to the model size
    image = Image.fromarray(face)
    image = image.resize(required_size)
    face_array = np.asarray(image)
    return face_array


def load_face(dir):
    faces = list()
    # enumerate files
    for filename in os.listdir(dir):
        path = dir + filename
        face = extract_face(path)
        faces.append(face)
    return faces


def load_dataset(dir):
    # list for faces and labels
    X, y = list(), list()
    for subdir in os.listdir(dir):
        path = dir + subdir + '/'
        faces = load_face(path)
        labels = [subdir for i in range(len(faces))]
        print("loaded %d sample for class: %s" % (len(faces),subdir) ) # print progress
        X.extend(faces)
        y.extend(labels)
    return np.asarray(X), np.asarray(y)


def get_embedding(model, face):
    # scale pixel values
    face = face.astype('float32')
    # standardization
    mean, std = face.mean(), face.std()
    face = (face-mean)/std
    # transfer face into one sample (3 dimension to 4 dimension)
    sample = np.expand_dims(face, axis=0)
    # make prediction to get embedding
    yhat = model.predict(sample)
    return yhat[0]