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
import numpy as np
import cv2

labels = {0: 'mask_incorrectly_worn', 1: 'with_mask', 2: 'without_mask'}


def most_common(lst):
    return max(set(lst), key=lst.count)


def detect_mask(img, face_detector, face_mask_detector):
    (h, w) = img.shape[:2]
    blob = cv2.dnn.blobFromImage(img, 1.0, (128, 128), (104.0, 177.0, 123.0))

    face_detector.setInput(blob)
    detections = face_detector.forward()

    faces = []
    locs = []
    preds = []

    for i in range(0, detections.shape[2]):
        confidence = detections[0, 0, i, 2]

        if confidence > 0.5:
            box = detections[0, 0, i, 3:7] * np.array([w, h, w, h])
            (startX, startY, endX, endY) = box.astype("int")

            (startX, startY) = (max(0, startX), max(0, startY))
            (endX, endY) = (min(w - 1, endX), min(h - 1, endY))

            face = img[startY:endY, startX:endX]
            face = cv2.cvtColor(face, cv2.COLOR_BGR2RGB)
            face = cv2.resize(face, (128, 128))
            face = img_to_array(face)
            face = preprocess_input(face)

            faces.append(face)
            locs.append((startX, startY, endX, endY))

    if len(faces) > 0:
        faces = np.array(faces, dtype="float32")
        preds = face_mask_detector.predict(faces, batch_size=32)

    return locs, preds


prototxtPath = r"face_detector\deploy.prototxt"
weightsPath = r"face_detector\res10_300x300_ssd_iter_140000.caffemodel"
faceNet = cv2.dnn.readNet(prototxtPath, weightsPath)

mask_detection_model = load_model("face_mask_detection2.h5")

states = []
current_label = ''
current_color = (0, 0, 0)

cam = cv2.VideoCapture(0)

while True:
    ret, frame = cam.read()
    if not ret:
        print("failed to grab frame")
        break

    (locs, preds) = detect_mask(frame, faceNet, mask_detection_model)

    for (box, pred) in zip(locs, preds):
        (startX, startY, endX, endY) = box

        label_index = np.argmax(pred)

        states.append(label_index)

        if len(states) == 10:
            index = most_common(states)
            current_label = labels[index]
            if index == 2:
                current_color = (0, 0, 255)
            elif index == 1:
                current_color = (0, 255, 0)
            else:
                current_color = (0, 127, 255)
            states.clear()

        if current_label != '':
            cv2.putText(frame, current_label, (startX, startY - 10),
                        cv2.FONT_HERSHEY_SIMPLEX, 0.45, current_color, 2)
            cv2.rectangle(frame, (startX, startY), (endX, endY), current_color, 2)

    cv2.imshow("Face Mask Detection", frame)
    key = cv2.waitKey(1) & 0xFF

    if key == ord("q"):
        break

cv2.destroyAllWindows()
cam.release()