def minutiae_extract(path, results):
plot = False
# ratio = 0.2
# Extract names
all_images = []
for f in os.listdir(path):
all_images.append(os.path.join(path, f))
# Split train and test data
# train_data, test_data = tl.split_train_test(all_images, ratio)
print("\nAll_images size: {}\n".format(len(all_images)))
all_times = []
for image in all_images:
start = time.time()
name = splitext(basename(image))[0]
print(image)
print("\nProcessing image '{}'".format(name))
cleaned_img = preprocess.blurrImage(image, name, plot)
enhanced_img = img_e.image_enhance(cleaned_img, name, plot)
print(type(enhanced_img))
cleaned_img = preprocess.cleanImage(enhanced_img, name, plot)
skeleton = preprocess.thinImage(cleaned_img, name, plot)
minExtract.process(skeleton, name, plot, results)
all_times.append((time.time() - start))
mean, std = 0, 0
mean = np.mean(all_times)
std = np.std(all_times)
print("\n\nAlgorithm takes {:2.3f} (+/-{:2.3f}) seconds per image".format(
mean, std))
def identify(self):
top = tk.Toplevel(self)
top.geometry('1000x700')
# =============================================================================
#
# =============================================================================
image_ext = '.jpg'
plot = False
path = None
# ratio = 0.2
# Create folders for results
# -r ../Data/Results/fingerprints
# if args.get("results") is not None:
# if not exists(args["results"]):
# tl.makeDir(args["results"])
# path = args["results"]
# Extract names
# all_images = tl.natSort(tl.getSamples(args["path"], image_ext))
# all_images = tl.natSort(tl.getSamples('C:\\Users\\jagdi\\Desktop\\project\\MinutiaeFingerprint-master', image_ext))
all_images = tl.natSort(
tl.getSamples('C:\\Program Files\\PIUF\\images_folder\\temp',
image_ext))
# Split train and test data
# train_data, test_data = tl.split_train_test(all_images, ratio)
print("\nAll_images size: {}\n".format(len(all_images)))
# all_times= []
print("all images\n", all_images)
for image in all_images:
# start = time.time()
name = splitext(basename(image))[0]
print("\nProcessing image '{}'".format(name))
self.pro = 'processing image'
# print("path ={} ".format(args["path"]))
print("image ={}".format(image))
img = cv2.imread(str(image), 0)
equ = cv2.equalizeHist(img)
cv2.imwrite('equalized\\' + str(name) + '.jpg', equ)
all_eqimages = all_images = tl.natSort(
tl.getSamples('equalized', image_ext))
for image in all_eqimages:
name = splitext(basename(image))[0]
print("\nProcessing image '{}'".format(name))
self.pro = 'processing'
cleaned_img = preprocess.blurrImage(image, name, plot)
enhanced_img = img_e.image_enhance(cleaned_img, name, plot)
cleaned_img = preprocess.cleanImage(enhanced_img, name, plot)
skeleton = preprocess.thinImage(cleaned_img, name, plot)
revert = cv2.bitwise_not(skeleton)
cv2.imwrite('thinned\\' + str(name) + '.jpg', revert)
folder = 'equalized'
for the_file in os.listdir(folder):
file_path = os.path.join(folder, the_file)
try:
if os.path.isfile(file_path):
os.unlink(file_path)
except Exception as e:
print(e)
num_channel = 1
test_image = cv2.imread('thinned/temp.jpg')
test_image = cv2.cvtColor(test_image, cv2.COLOR_BGR2GRAY)
test_image = cv2.resize(test_image, (128, 128))
test_image = np.array(test_image)
test_image = test_image.astype('float32')
test_image /= 255
if num_channel == 1:
if K.image_dim_ordering() == 'th':
test_image = np.expand_dims(test_image, axis=0)
test_image = np.expand_dims(test_image, axis=0)
print(test_image.shape)
else:
test_image = np.expand_dims(test_image, axis=3)
test_image = np.expand_dims(test_image, axis=0)
print(test_image.shape)
else:
if K.image_dim_ordering() == 'th':
test_image = np.rollaxis(test_image, 2, 0)
test_image = np.expand_dims(test_image, axis=0)
print(test_image.shape)
else:
test_image = np.expand_dims(test_image, axis=0)
print(test_image.shape)
loaded_model = load_model('model8.h5')
result = int(loaded_model.predict_classes(test_image))
self.v.set(self.switch_demo(result))
b = tk.Button(top,
text="OK",
width=20,
height=2,
bg='brown',
fg='white',
command=lambda win=top: win.destroy())
b.pack(side="bottom")
name1 = self.v.get()
print(name1)
label_2 = tk.Label(top, text="First Name", width=20, font=("bold", 10))
label_2.place(x=70, y=170)
label_3 = tk.Label(top, text="Last Name", width=20, font=("bold", 10))
label_3.place(x=70, y=200)
label_4 = tk.Label(top, text="Gender", width=20, font=("bold", 10))
label_4.place(x=70, y=230)
label_5 = tk.Label(top,
text="Email Address",
width=20,
font=("bold", 10))
label_5.place(x=70, y=260)
label_6 = tk.Label(top,
text="Contact No.",
width=20,
font=("bold", 10))
label_6.place(x=70, y=290)
label_7 = tk.Label(top, text="Address", width=20, font=("bold", 10))
label_7.place(x=70, y=320)
label_8 = tk.Label(top, text="Faculty", width=20, font=("bold", 10))
label_8.place(x=70, y=350)
conn = sqlite3.connect('Form.db')
with conn:
cursor = conn.cursor()
cursor.execute(
'SELECT First_Name FROM Student where First_Name="' + name1 +
'"')
rows = cursor.fetchall()
label_2 = tk.Label(top, text=rows, width=20, font=("bold", 10))
label_2.place(x=240, y=170)
cursor.execute('SELECT Last_Name FROM Student where First_Name="' +
name1 + '"')
rows1 = cursor.fetchall()
label_3 = tk.Label(top, text=rows1, width=20, font=("bold", 10))
label_3.place(x=240, y=200)
cursor.execute('SELECT Gender FROM Student where First_Name="' +
name1 + '"')
rows2 = cursor.fetchall()
label_4 = tk.Label(top, text=rows2, width=20, font=("bold", 10))
label_4.place(x=240, y=230)
cursor.execute('SELECT Email FROM Student where First_Name="' +
name1 + '"')
rows3 = cursor.fetchall()
label_5 = tk.Label(top, text=rows3, width=20, font=("bold", 10))
label_5.place(x=240, y=260)
cursor.execute(
'SELECT Contact_No FROM Student where First_Name="' + name1 +
'"')
rows4 = cursor.fetchall()
label_6 = tk.Label(top, text=rows4, width=20, font=("bold", 10))
label_6.place(x=240, y=290)
cursor.execute('SELECT Address FROM Student where First_Name="' +
name1 + '"')
rows5 = cursor.fetchall()
label_7 = tk.Label(top, text=rows5, width=20, font=("bold", 10))
label_7.place(x=240, y=320)
cursor.execute('SELECT Faculty FROM Student where First_Name="' +
name1 + '"')
rows6 = cursor.fetchall()
label_8 = tk.Label(top, text=rows6, width=20, font=("bold", 10))
label_8.place(x=240, y=350)
cursor.execute('SELECT Photo FROM Student where First_Name="' +
name1 + '"')
rows7 = cursor.fetchall()
print(rows1)
print(rows2)
print(rows3)
print(rows4)
print(rows5)
print(rows6)
print(rows7)
img = ImageLabel(top)
img.pack(side="right")
img.load(str(rows7[0][0]))
image_ext = '.tif'
plot = False
path = None
# ratio = 0.2
# Create folders for results
# -r ../Data/Results/fingerprints
if args.get("results") is not None:
if not exists(args["results"]):
tl.makeDir(args["results"])
path = args["results"]
# Extract names
all_images = tl.natSort(tl.getSamples(args["path"], image_ext))
# Split train and test data
# train_data, test_data = tl.split_train_test(all_images, ratio)
print("\nAll_images size: {}\n".format(len(all_images)))
all_times = []
for image in all_images:
start = time.time()
name = splitext(basename(image))[0]
print("\nProcessing image '{}'".format(name))
cleaned_img = preprocess.blurrImage(image, name, plot)
enhanced_img = img_e.image_enhance(cleaned_img, name, plot)
cleaned_img = preprocess.cleanImage(enhanced_img, name, plot)
# skeleton = preprocess.zhangSuen(cleaned_img, name, plot)
skeleton = preprocess.thinImage(cleaned_img, name, plot)
minExtract.process(skeleton, name, plot, path)
all_times.append((time.time() - start))
mean = mean(all_times)
std = std(all_times)
print("\n\nAlgorithm takes {:2.3f} (+/-{:2.3f}) seconds per image".format(
mean, std))