app.py

# command
# streamlit run app.py

# importing necessary packages
import streamlit as st
from PIL import Image, ImageEnhance
import numpy as np
import cv2
import os
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

# Setting custom Page Title and Icon with changed layout and sidebar state
st.set_page_config(page_title='Face Mask Detector', page_icon='😷', layout='centered', initial_sidebar_state='expanded')


def local_css(file_name):
    # Method for reading styles.css
    with open(file_name) as f:
        st.markdown(f'<style>{f.read()}</style>', unsafe_allow_html=True)


def mask_image():
    global RGB_img
    # load our serialized face detector model from disk
    print("[INFO] loading face detector model...")
    prototxtPath = os.path.sep.join(["face_detector", "deploy.prototxt"])
    weightsPath = os.path.sep.join(["face_detector",
                                    "res10_300x300_ssd_iter_140000.caffemodel"])
    net = cv2.dnn.readNet(prototxtPath, weightsPath)

    # load the face mask detector model from disk
    print("[INFO] loading face mask detector model...")
    model = load_model("mask_detector.model")

    # load the input image from disk and grab the image spatial
    # dimensions
    image = cv2.imread("./images/out.jpg")
    (h, w) = image.shape[:2]

    # construct a blob from the image
    blob = cv2.dnn.blobFromImage(image, 1.0, (300, 300),
                                 (104.0, 177.0, 123.0))

    # pass the blob through the network and obtain the face detections
    print("[INFO] computing face detections...")
    net.setInput(blob)
    detections = net.forward()

    # loop over the detections
    for i in range(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the detection
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the confidence is
        # greater than the minimum confidence
        if confidence > 0.5:
            # compute the (x, y)-coordinates of the bounding box for
            # the object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # ensure the bounding boxes fall within the dimensions of
            # the frame
            (startX, startY) = (max(0, startX), max(0, startY))
            (endX, endY) = (min(w - 1, endX), min(h - 1, endY))

            # extract the face ROI, convert it from BGR to RGB channel
            # ordering, resize it to 224x224, and preprocess it
            face = image[startY:endY, startX:endX]
            face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
            face = cv2.resize(face, (224, 224))
            face = img_to_array(face)
            face = preprocess_input(face)
            face = np.expand_dims(face, axis=0)

            # pass the face through the model to determine if the face
            # has a mask or not
            (mask, withoutMask) = model.predict(face)[0]

            # determine the class label and color we'll use to draw
            # the bounding box and text
            label = "Mask" if mask > withoutMask else "No Mask"
            color = (0, 255, 0) if label == "Mask" else (255, 0, 0)

            # include the probability in the label
            label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)

            # display the label and bounding box rectangle on the output
            # frame
            cv2.putText(image, label, (startX, startY - 10),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.45, color, 2)
            cv2.rectangle(image, (startX, startY), (endX, endY), color, 2)
            RGB_img = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)


mask_image()

global frame, faceNet, maskNet


def detect_and_predict_mask(frame, faceNet, maskNet):
    # grab the dimensions of the frame and then construct a blob
    # from it
    # global frame, faceNet, maskNet

    (h, w) = frame.shape[:2]
    blob = cv2.dnn.blobFromImage(frame, 1.0, (300, 300),
                                 (104.0, 177.0, 123.0))

    # pass the blob through the network and obtain the face detections
    faceNet.setInput(blob)
    detections = faceNet.forward()

    # initialize our list of faces, their corresponding locations,
    # and the list of predictions from our face mask network
    faces = []
    locs = []
    preds = []

    # loop over the detections
    for i in range(0, detections.shape[2]):
        # extract the confidence (i.e., probability) associated with
        # the detection
        confidence = detections[0, 0, i, 2]

        # filter out weak detections by ensuring the confidence is
        # greater than the minimum confidence
        if confidence > 0.5:
            # compute the (x, y)-coordinates of the bounding box for
            # the object
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            # ensure the bounding boxes fall within the dimensions of
            # the frame
            (startX, startY) = (max(0, startX), max(0, startY))
            (endX, endY) = (min(w - 1, endX), min(h - 1, endY))

            # extract the face ROI, convert it from BGR to RGB channel
            # ordering, resize it to 224x224, and preprocess it
            face = frame[startY:endY, startX:endX]
            if face.any():
                face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
                face = cv2.resize(face, (224, 224))
                face = img_to_array(face)
                face = preprocess_input(face)

                # add the face and bounding boxes to their respective
                # lists
                faces.append(face)
                locs.append((startX, startY, endX, endY))

    # only make a predictions if at least one face was detected
    if len(faces) > 0:
        # for faster inference we'll make batch predictions on *all*
        # faces at the same time rather than one-by-one predictions
        # in the above `for` loop
        faces = np.array(faces, dtype="float32")
        preds = maskNet.predict(faces, batch_size=32)

    # return a 2-tuple of the face locations and their corresponding
    # locations
    return (locs, preds)

# detect_and_predict_mask(frame, faceNet, maskNet)


def mask_detection():
    local_css("css/styles.css")
    st.markdown('<h1 align="center">Face-Mask Detector</h1>', unsafe_allow_html=True)
    activities = ["Image", "LiveCam"]
    st.set_option('deprecation.showfileUploaderEncoding', False)
    st.sidebar.markdown("# Mask Detector !")
    choice = st.sidebar.selectbox("Choose among the given options:", activities)

    if choice == 'Image':
        st.markdown('<h2 align="center">Image Detector</h2>', unsafe_allow_html=True)
        st.markdown("### Upload the image to detect mask here ⬇")
        image_file = st.file_uploader("", type=['jpg'])  # upload image
        if image_file is not None:
            our_image = Image.open(image_file)  # making compatible to PIL
            im = our_image.save('./images/out.jpg')
            saved_image = st.image(image_file, caption='', use_column_width=True)
            st.markdown('<h3 align="center">Image successfully uploaded!</h3>', unsafe_allow_html=True)
            if st.button('Process'):
                st.image(RGB_img, use_column_width=True)

    if choice == 'LiveCam':
        st.markdown('<h2 align="center">Webcam Detector</h2>', unsafe_allow_html=True)
        st.title("Live WebCam Testing Application")
        run = st.checkbox('Start')
        print("[INFO] loading face detector model...")
        prototxtPath = os.path.sep.join(["face_detector", "deploy.prototxt"])
        weightsPath = os.path.sep.join(["face_detector", "res10_300x300_ssd_iter_140000.caffemodel"])
        faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)

        print("[INFO] loading face mask detector model...")
        maskNet = load_model("mask_detector.model")

        print("[INFO] starting video stream...")
        FRAME_WINDOW = st.image([])
        cam = cv2.VideoCapture(1)

        while run:
            ret, frame = cam.read()
            frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
            frame = cv2.flip(frame, 1)

            (locs, preds) = detect_and_predict_mask(frame, faceNet, maskNet)
            for (box, pred) in zip(locs, preds):
                # unpack the bounding box and predictions
                (startX, startY, endX, endY) = box
                (mask, withoutMask) = pred

                # determine the class label and color we'll use to draw
                # the bounding box and text
                label = "Mask" if mask > withoutMask else "No Mask"
                color = (0, 255, 0) if label == "Mask" else (255, 0, 0)

                # include the probability in the label
                label = "{}: {:.2f}%".format(label, max(mask, withoutMask) * 100)

                # display the label and bounding box rectangle on the output
                # frame
                cv2.putText(frame, label, (startX, startY - 10),
                            cv2.FONT_HERSHEY_SIMPLEX, 0.7, color, 2)
                cv2.rectangle(frame, (startX, startY), (endX, endY), color, 2)

            FRAME_WINDOW.image(frame)
        else:
            st.write('Stopped')


mask_detection()