Face Mask Detection Using MobileNetV2 Transfer Learning

5 min readMay 28, 2020

In this article, we will learn the role of computer vision in detecting people who wear the mask or not, especially as we are going through a global crisis from the outbreak of the Corona virus.

Note

The training of the model will be on Google Colab because it was previously prepared for all training libraries deep learning and away from the problems of installation troublesome libraries

Photo by Anastasiia Chepinska on Unsplash

Dataset for face mask

#download dataset 
!wget https://s3-us-west-2.amazonaws.com/static.pyimagesearch.com/face-mask-detection/face-mask-detector.zip

unzip dataset in the google colab root

!unzip /content/face-mask-detector.zip

import the necessary packages

from tensorflow.keras.preprocessing.image import ImageDataGenerator
from tensorflow.keras.applications import MobileNetV2
from tensorflow.keras.layers import AveragePooling2D
from tensorflow.keras.layers import Dropout
from tensorflow.keras.layers import Flatten
from tensorflow.keras.layers import Dense
from tensorflow.keras.layers import Input
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.preprocessing.image import load_img
from tensorflow.keras.utils import to_categorical
from sklearn.preprocessing import LabelBinarizer
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report
from imutils import paths
import matplotlib.pyplot as plt
import numpy as np
import os

initialize the initial learning rate, number of epochs,batch size

INIT_LR = 1e-4
EPOCHS = 10
BS = 32

grab the list of images in our dataset directory, then initialize the list of data and class images

print("[INFO] loading images...")
imagePaths = list(paths.list_images(dataset))
data = []
labels = []
# loop over the image paths
for imagePath in imagePaths:
 # extract the class label from the filename
 label = imagePath.split(os.path.sep)[-2]
 # load the input image (224x224) and preprocess it
 image = load_img(imagePath, target_size=(224, 224))
 image = img_to_array(image)
 image = preprocess_input(image)
 # update the data and labels lists, respectively
 data.append(image)
 labels.append(label)

convert the data and labels to arrays

data = np.array(data, dtype="float32")
labels = np.array(labels)

perform one-hot encoding on the labels

lb = LabelBinarizer()
labels = lb.fit_transform(labels)
labels = to_categorical(labels)

partition the data into training and testing splits using 80% of the data for training and the remaining 20% for testing

(trainX, testX, trainY, testY) = train_test_split(data, labels,
 test_size=0.20, stratify=labels, random_state=42)

construct the training image generator for data augmentation

aug = ImageDataGenerator(
 rotation_range=20,
 zoom_range=0.15,
 width_shift_range=0.2,
 height_shift_range=0.2,
 shear_range=0.15,
 horizontal_flip=True,
 fill_mode="nearest")

load the MobileNetV2 network, ensuring the head FC layer sets are

baseModel = MobileNetV2(weights="imagenet", include_top=False,
 input_tensor=Input(shape=(224, 224, 3)))

construct the head of the model that will be placed on top of the the base model

headModel = baseModel.output
headModel = AveragePooling2D(pool_size=(7, 7))(headModel)
headModel = Flatten(name="flatten")(headModel)
headModel = Dense(128, activation="relu")(headModel)
headModel = Dropout(0.5)(headModel)
headModel = Dense(2, activation="softmax")(headModel)

place the head FC model on top of the base model

model = Model(inputs=baseModel.input, outputs=headModel)

loop over all layers in the base model and freeze them

for layer in baseModel.layers:
 layer.trainable = False

compile our model

print("[INFO] compiling model...")
opt = Adam(lr=INIT_LR, decay=INIT_LR / EPOCHS)
model.compile(loss="binary_crossentropy", optimizer=opt, metrics=["accuracy"])

train the head of the network

print("[INFO] training head...")
H = model.fit(
 aug.flow(trainX, trainY, batch_size=BS),
 steps_per_epoch=len(trainX) // BS,
 validation_data=(testX, testY),
 validation_steps=len(testX) // BS,
 epochs=EPOCHS)

make predictions on the testing set and show a nicely formatted classification report

print("[INFO] evaluating network...")
predIdxs = model.predict(testX, batch_size=BS)
# for each image in the testing set we need to find the index of the
# label with corresponding largest predicted probability
predIdxs = np.argmax(predIdxs, axis=1)
print(classification_report(testY.argmax(axis=1), predIdxs,
 target_names=lb.classes_))

plot the training loss and accuracy

N = EPOCHS
plt.style.use("ggplot")
plt.figure()
plt.plot(np.arange(0, N), H.history["loss"], label="train_loss")
plt.plot(np.arange(0, N), H.history["val_loss"], label="val_loss")
plt.plot(np.arange(0, N), H.history["accuracy"], label="train_acc")
plt.plot(np.arange(0, N), H.history["val_accuracy"], label="val_acc")
plt.title("Training Loss and Accuracy")
plt.xlabel("Epoch #")
plt.ylabel("Loss/Accuracy")
plt.legend(loc="lower left")
plt.savefig(plot)

save model

print("[INFO] saving mask detector model...")
model.save('mask-no-mask.h5')

convert model to tensorflowjs

# install tensorflowjs 
!pip install tensorflowjs

and import module

import tensorflowjs as tfjs
from tensorflow.keras.models import load_model

create function to convert keras model to tensorflowjs

def keras2tfjs(model_path,dir_out):
 #import tensorflowjs as tfjs
 MODEL_PATH = model_path
 print('Model loading...')
 model=load_model(MODEL_PATH)
 #print('Model loaded. Started serving...')
 tfjs.converters.save_keras_model(model, dir_out)

and implementation this function

model_path='/content/mask-no-mask.h5'
dir_out='/content/keras2js'
keras2tfjs(model_path,dir_out)

and this code implementation in pc or laptop detection in real time with camera

# import the necessary packages
from datetime import datetime
from mtcnn.mtcnn import MTCNN
detector = MTCNN()
import numpy as np
from tensorflow.keras.applications.mobilenet_v2 import preprocess_input
from tensorflow.keras.preprocessing.image import img_to_array
from tensorflow.keras.models import load_model
from keras.preprocessing.image import load_img
import cv2
import os
from resizeimage import resizeimage

load the model

model = load_model("./models/mask_no_mask.h5")

load and run camera by opencv2 module

font = cv2.FONT_HERSHEY_TRIPLEX
font2 = cv2.FONT_HERSHEY_COMPLEX_SMALL
font3 = cv2.FONT_HERSHEY_SCRIPT_COMPLEX
font4 = cv2.FONT_HERSHEY_SIMPLEX
cap = cv2.VideoCapture(0)
while True: 
 #Capture frame-by-frame
 __, frame = cap.read()
 cv2.putText(frame,str(datetime.now()),(10,30), font3, 1,(255,255,255),2,cv2.LINE_AA)
 # cv2.putText(frame,(10,450), font2, 1,(255,255,255),2,cv2.LINE_AA)
 cv2.putText(frame,'ARR-AB\'s CAM',(480,450), font2, 0.9,(255,255,255),2,cv2.LINE_AA)
 #Use MTCNN to detect faces
 result = detector.detect_faces(frame)
 if result != []:
  for person in result:
   bounding_box = person['box']
   keypoints = person['keypoints']
   #cv2.putText(frame,"The Face",(200,100), font, 1,(255,255,255),2,cv2.LINE_AA)
   cv2.imwrite('opencv.png', frame)
   image_file = load_img('opencv.png')
   cover = resizeimage.resize_cover(image_file, [224, 224], validate=False)
   x = []
   x = img_to_array(cover)
   face = preprocess_input(x)
   face = np.expand_dims(face, axis=0)
   #x = np.expand_dims(x, axis=0)
   (mask, withoutMask) = model.predict(face)[0]
   #print(pred[0][0])
   label = "Mask" if mask > withoutMask else "No Mask"
   color = (0, 255, 0) if label == "Mask" else (0, 0, 255)
      # include the probability in the label
   label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)
      #if pred[0][0]==0.0:
   cv2.putText(frame,label,(100,100), font4, 0.8,(0,255,0),2,cv2.LINE_AA)
   #cv2.putText(frame, label, (startX, startY - 10),
    #cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
   #cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)
        # elif pred[0][0]==1.0:
       # cv2.putText(frame,"ACCESS DENIED, No FACE-MASK",(100,100), font4, 0.8,(0,0,255),2,cv2.LINE_AA)
   cv2.rectangle(frame,
       (bounding_box[0], bounding_box[1]),
       (bounding_box[0]+bounding_box[2], bounding_box[1] + bounding_box[3]),
       (0,155,255),2)     
  #display resulting frame
 out.write(frame)#display resulting frame
 cv2.imshow('frame',frame)
 if cv2.waitKey(10) &0xFF == ord('q'):
  break