import numpy as np
import cv2
from skimage.feature import local_binary_pattern
import joblib

# Load the trained model from file
knn_model = joblib.load('facemodel.joblib')

def extract_lbp_features(image, radius=1, n_points=8, method='uniform'):
    lbp = local_binary_pattern(image, n_points, radius, method)
    (hist, _) = np.histogram(lbp.ravel(), bins=np.arange(0, n_points + 3), range=(0, n_points + 2))
    # Normalize the histogram
    hist = hist.astype("float")
    hist /= (hist.sum() + 1e-7)
    return hist

# Fungsi untuk deteksi wajah dan cropping
def detect_and_crop_faces(image_path):
    # Baca gambar
    original_image = cv2.imread(image_path)
    gray_image = cv2.cvtColor(original_image, cv2.COLOR_BGR2GRAY)

    # Peningkatan kontras
    gray_image = cv2.equalizeHist(gray_image)

    # Muat pre-trained Haar Cascade untuk deteksi wajah
    face_cascade = cv2.CascadeClassifier(cv2.data.haarcascades + 'haarcascade_frontalface_default.xml')

    # Deteksi wajah pada gambar dengan parameter yang disesuaikan
    faces = face_cascade.detectMultiScale(gray_image, scaleFactor=1.4, minNeighbors=6, minSize=(50, 50))

    # Cek jumlah wajah yang terdeteksi
    print(f'{image_path}: {len(faces)} face(s) detected')

    # Loop melalui setiap wajah yang terdeteksi, potong, dan tampilkan
    for i, (x, y, w, h) in enumerate(faces, 1):
        # Pemotongan (Cropping) wajah
        cropped_face = original_image[y:y + h, x:x + w]

        # # Tampilkan gambar wajah yang terpotong
        # cv2.imshow(f'Cropped Face {i}', cropped_face)
        #
        # # Tunggu 1 detik sebelum menampilkan gambar berikutnya
        # cv2.waitKey(1000)

    return faces

# Path ke gambar wajah uji
test_image_path = 'images/testface/Alia Bhatt/Alia Bhatt_77.jpg'

# Deteksi wajah dan cropping pada gambar uji
test_faces = detect_and_crop_faces(test_image_path)

# Loop melalui setiap wajah yang terdeteksi di gambar uji
for i, (x, y, w, h) in enumerate(test_faces, 1):
    # Pemotongan (Cropping) wajah
    cropped_test_face = cv2.imread(test_image_path)[y:y + h, x:x + w]

    # Resize gambar menjadi 100x100 piksel
    resized_test_face = cv2.resize(cropped_test_face, (100, 100))

    # Konversi gambar resized ke grayscale
    gray_resized_test_face = cv2.cvtColor(resized_test_face, cv2.COLOR_BGR2GRAY)

    # Normalisasi intensitas
    normalized_test_face = cv2.normalize(gray_resized_test_face, None, alpha=0, beta=255, norm_type=cv2.NORM_MINMAX)

    # Ekstraksi fitur LBP untuk gambar uji
    test_lbp_features = extract_lbp_features(normalized_test_face, radius=1, n_points=8, method='uniform')

    # Tampilkan nilai ekstraksi LBP ke konsol
    print(f'LBP Features for face: {test_lbp_features}')

    # Prediksi kelas menggunakan model K-NN
    predicted_class = knn_model.predict([test_lbp_features])[0]

    # Tampilkan hasil prediksi
    print(f'Predicted class for face {i}: {predicted_class}')

# Tunggu sampai tombol ditekan dan tutup jendela
cv2.waitKey(0)
cv2.destroyAllWindows()