def autenticacao(request):
if request.method == "POST":
try:
uploaded_file = request.FILES['biometry']
fs = FileSystemStorage()
fs.save("fingerprint.png", uploaded_file)
except:
return redirect('home/')
global username
username = request.POST['username']
try:
Users.objects.filter(username=username).first().username
print("Username cadastrado no BD")
try:
print('Analisando o fingerprint recebido')
img = cv2.imread('./upload/fingerprint.png',
0) # read input image
out = fingerprint_enhancer.enhance_Fingerprint(
img) # enhance the fingerprint image
print('Analisando o fingerprint cadastrado no BD')
img2 = cv2.imread('./upload/' + Users.objects.filter(
username=username).first().biometry.name, 0) # read input image
out2 = fingerprint_enhancer.enhance_Fingerprint(
img2) # enhance the fingerprint image
result = out == out2
try:
global autenticado
if result.all() == True:
autenticado = True
print("Autenticado!")
fs.delete("fingerprint.png")
return redirect('home/')
except:
if result == False:
autenticado = False
print("Falha na autenticação!")
fs.delete("fingerprint.png")
return redirect('home/')
except:
print("Obtivemos um erro ao analisarmos a fingerprint recebida. Por favor, verifique se a fingerprint está no formato JPEG, JPG ou PNG.")
fs.delete("fingerprint.png")
return redirect('home/')
except:
print("Usuario não cadastrado no BD")
fs.delete("fingerprint.png")
return redirect('home/')
return render(request, 'auth/src/auth.html')
def get_descriptors(img):
clahe = cv2.createCLAHE(clipLimit=2.0, tileGridSize=(8, 8))
img = clahe.apply(img)
img = fingerprint_enhancer.enhance_Fingerprint(img)
img = numpy.array(img, dtype=numpy.uint8)
# Threshold (identify the white black pixel by near method and convert in white or black absolute)
ret, img = cv2.threshold(
img, 127, 255, cv2.THRESH_BINARY_INV | cv2.THRESH_OTSU)
# Normalize to 0 and 1 range
img[img == 255] = 1
# Harris corners
harris_corners = cv2.cornerHarris(img, 3, 3, 0.04)
harris_normalized = cv2.normalize(
harris_corners, 0, 255, norm_type=cv2.NORM_MINMAX, dtype=cv2.CV_32FC1)
threshold_harris = _FRONTIER
# Extract keypoints
keypoints = []
for x in range(0, harris_normalized.shape[0]):
for y in range(0, harris_normalized.shape[1]):
if harris_normalized[x][y] > threshold_harris:
keypoints.append(cv2.KeyPoint(y, x, 1))
# Define descriptor
orb = cv2.ORB_create()
# Compute descriptors
_, des = orb.compute(img, keypoints)
return (keypoints, des)
def T_generator(img):
X = []
Y = []
R = []
T = []
enhanced_img = enh.enhance_Fingerprint(img)
features_terminations, features_bifurcations = ext.extract_minutiae_features(
enhanced_img, showResult=False)
for termination in features_terminations:
X.append(termination.locX)
Y.append(termination.locY)
for bifurcation in features_bifurcations:
X.append(bifurcation.locX)
Y.append(bifurcation.locY)
n = len(Y)
for i in range(0, 64):
R.append(randint(0, 2 * (n - 1)))
for r in R:
if r < n:
T.append((X[r] % 256) - 128)
else:
T.append((Y[r - n] % 256) - 128)
return T
import cv2
import fingerprint_enhancer
import os
import tqdm
images = os.listdir('./data/light_data/dataset/train_data')
i = False
for image_name in tqdm.tqdm(images):
img = cv2.imread('./data/light_data/dataset/train_data/' + image_name, 0)
try:
out = fingerprint_enhancer.enhance_Fingerprint(img)
cv2.imwrite('./data/enhanced/light_data_enhanced/' + image_name, out)
except:
pass
def enhance_and_binarize(img):
enhanced_img = fingerprint_enhancer.enhance_Fingerprint(img)
_, binarized_enhanced_img = cv2.threshold(
enhanced_img, 0, 255, cv2.THRESH_BINARY + cv2.THRESH_OTSU)
return binarized_enhanced_img