import numpy as np
import cv2
from skimage.feature import local_binary_pattern
import os
from joblib import load
import sys

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

# Mendapatkan path lengkap ke file facemodel.joblib
model_path = os.path.join(os.path.dirname(__file__), 'facemodel.joblib')

# Memuat model dari file
knn_model = load(model_path)

# Path ke gambar wajah uji (diteruskan sebagai argumen command line)
test_image_path = sys.argv[1]

# Baca gambar
original_image = cv2.imread(test_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=1.3, minNeighbors=8, minSize=(30, 30))

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

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

    # Resize gambar menjadi 100x100 piksel
    resized_face = cv2.resize(cropped_face, (100, 100))

    # Konversi gambar resized ke grayscale
    gray_resized_face = cv2.cvtColor(resized_face, cv2.COLOR_BGR2GRAY)

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

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

    # 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}')