Keras/VGGFace

face-recognition.py

import sys
import numpy as np
from PIL import Image
from scipy import misc, ndimage
from keras import Model
from keras import Sequential
from keras.layers import Activation
from keras.layers import Dropout
from keras.layers import Flatten
from keras.layers import ZeroPadding2D
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.models import model_from_json
from keras.preprocessing.image import load_img
from keras.preprocessing.image import img_to_array
from keras.applications.imagenet_utils import preprocess_input

def preprocess_image(image_path):
    img = load_img(image_path, target_size=(224, 224))
    img = img_to_array(img)
    img = np.expand_dims(img, axis=0)
    img = preprocess_input(img)
    return img
 
def prepare_model():
    model = Sequential()
    model.add(ZeroPadding2D((1,1),input_shape=(224,224, 3)))
    model.add(Convolution2D(64, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(64, (3, 3), activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
     
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(128, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(128, (3, 3), activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
     
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(256, (3, 3), activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
     
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
     
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(ZeroPadding2D((1,1)))
    model.add(Convolution2D(512, (3, 3), activation='relu'))
    model.add(MaxPooling2D((2,2), strides=(2,2)))
     
    model.add(Convolution2D(4096, (7, 7), activation='relu'))
    model.add(Dropout(0.5))
    model.add(Convolution2D(4096, (1, 1), activation='relu'))
    model.add(Dropout(0.5))
    model.add(Convolution2D(2622, (1, 1)))
    model.add(Flatten())
    model.add(Activation('softmax'))

    model.load_weights('vgg_face_weights.h5')

    vgg_face_descriptor = Model(inputs=model.layers[0].input, outputs=model.layers[-2].output)
    return vgg_face_descriptor

def same_person(model, img1, img2):
    img1_representation = model.predict(preprocess_image(img1))[0,:]
    img2_representation = model.predict(preprocess_image(img2))[0,:]

    a = np.matmul(np.transpose(img1_representation), img2_representation)
    b = np.sum(np.multiply(img1_representation, img1_representation))
    c = np.sum(np.multiply(img2_representation, img2_representation))
    cosine_similarity = 1 - (a / (np.sqrt(b) * np.sqrt(c)))
    print(cosine_similarity)

    if cosine_similarity < 0.4:
        return True
    return False

model = prepare_model()

if same_person(model, 'bengio1.jpg', 'bengio2.jpg'):
    print("Same person!")
else:
    print(":(")