Commited minutiae

This commit is contained in:
2026-02-13 13:17:41 +01:00
parent 0ee74cbcb8
commit 9595675cdb
40 changed files with 4125 additions and 0 deletions
@@ -0,0 +1,244 @@
"""Code for FineNet in paper "Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge" at ICB 2018
https://arxiv.org/pdf/1712.09401.pdf
If you use whole or partial function in this code, please cite paper:
@inproceedings{Nguyen_MinutiaeNet,
author = {Dinh-Luan Nguyen and Kai Cao and Anil K. Jain},
title = {Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge},
booktitle = {The 11th International Conference on Biometrics, 2018},
year = {2018},
}
"""
from __future__ import absolute_import
from __future__ import division
from keras.models import Model
from keras.layers import Activation, AveragePooling2D, BatchNormalization, Concatenate, Conv2D, Dense, GlobalAveragePooling2D
from keras.layers import Input, Lambda, MaxPooling2D
from keras.applications.imagenet_utils import _obtain_input_shape
from keras import backend as K
import matplotlib.pyplot as plt
import numpy as np
import itertools
def preprocess_input(x):
"""Preprocesses a numpy array encoding a batch of images.
"""
return keras.applications.imagenet_utils.preprocess_input(x, mode='tf')
def conv2d_bn(x,
filters,
kernel_size,
strides=1,
padding='same',
activation='relu',
use_bias=False,
name=None):
"""Utility function to apply conv + BN.
"""
x = Conv2D(filters,
kernel_size,
strides=strides,
padding=padding,
use_bias=use_bias,
name=name)(x)
if not use_bias:
bn_axis = 1 if K.image_data_format() == 'channels_first' else 3
bn_name = None if name is None else name + '_bn'
x = BatchNormalization(axis=bn_axis, scale=False, name=bn_name)(x)
if activation is not None:
ac_name = None if name is None else name + '_ac'
x = Activation(activation, name=ac_name)(x)
return x
def inception_resnet_block(x, scale, block_type, block_idx, activation='relu'):
"""Inception-ResNet block.
"""
if block_type == 'block35':
branch_0 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(x, 32, 1)
branch_1 = conv2d_bn(branch_1, 32, 3)
branch_2 = conv2d_bn(x, 32, 1)
branch_2 = conv2d_bn(branch_2, 48, 3)
branch_2 = conv2d_bn(branch_2, 64, 3)
branches = [branch_0, branch_1, branch_2]
elif block_type == 'block17':
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 128, 1)
branch_1 = conv2d_bn(branch_1, 160, [1, 7])
branch_1 = conv2d_bn(branch_1, 192, [7, 1])
branches = [branch_0, branch_1]
elif block_type == 'block8':
branch_0 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(x, 192, 1)
branch_1 = conv2d_bn(branch_1, 224, [1, 3])
branch_1 = conv2d_bn(branch_1, 256, [3, 1])
branches = [branch_0, branch_1]
else:
raise ValueError('Unknown Inception-ResNet block type. '
'Expects "block35", "block17" or "block8", '
'but got: ' + str(block_type))
block_name = block_type + '_' + str(block_idx)
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
mixed = Concatenate(axis=channel_axis, name=block_name + '_mixed')(branches)
up = conv2d_bn(mixed,
K.int_shape(x)[channel_axis],
1,
activation=None,
use_bias=True,
name=block_name + '_conv')
x = Lambda(lambda inputs, scale: inputs[0] + inputs[1] * scale,
output_shape=K.int_shape(x)[1:],
arguments={'scale': scale},
name=block_name)([x, up])
if activation is not None:
x = Activation(activation, name=block_name + '_ac')(x)
return x
def FineNetmodel(num_classes = 2, pretrained_path = None, input_shape = None):
"""Create FineNet architecture.
"""
# Determine proper input shape
input_shape = _obtain_input_shape(
input_shape,
default_size=299,
min_size=139,
data_format=K.image_data_format(),
require_flatten=False,
weights=pretrained_path)
img_input = Input(shape=input_shape)
# Stem block: 35 x 35 x 192
x = conv2d_bn(img_input, 32, 3, strides=2, padding='valid')
x = conv2d_bn(x, 32, 3, padding='valid')
x = conv2d_bn(x, 64, 3)
x = MaxPooling2D(3, strides=2)(x)
x = conv2d_bn(x, 80, 1, padding='valid')
x = conv2d_bn(x, 192, 3, padding='valid')
x = MaxPooling2D(3, strides=2)(x)
# Mixed 5b (Inception-A block): 35 x 35 x 320
branch_0 = conv2d_bn(x, 96, 1)
branch_1 = conv2d_bn(x, 48, 1)
branch_1 = conv2d_bn(branch_1, 64, 5)
branch_2 = conv2d_bn(x, 64, 1)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_2 = conv2d_bn(branch_2, 96, 3)
branch_pool = AveragePooling2D(3, strides=1, padding='same')(x)
branch_pool = conv2d_bn(branch_pool, 64, 1)
branches = [branch_0, branch_1, branch_2, branch_pool]
channel_axis = 1 if K.image_data_format() == 'channels_first' else 3
x = Concatenate(axis=channel_axis, name='mixed_5b')(branches)
# 10x block35 (Inception-ResNet-A block): 35 x 35 x 320
for block_idx in range(1, 11):
x = inception_resnet_block(x,
scale=0.17,
block_type='block35',
block_idx=block_idx)
# Mixed 6a (Reduction-A block): 17 x 17 x 1088
branch_0 = conv2d_bn(x, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 256, 3)
branch_1 = conv2d_bn(branch_1, 384, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_6a')(branches)
# 20x block17 (Inception-ResNet-B block): 17 x 17 x 1088
for block_idx in range(1, 21):
x = inception_resnet_block(x,
scale=0.1,
block_type='block17',
block_idx=block_idx)
# Mixed 7a (Reduction-B block): 8 x 8 x 2080
branch_0 = conv2d_bn(x, 256, 1)
branch_0 = conv2d_bn(branch_0, 384, 3, strides=2, padding='valid')
branch_1 = conv2d_bn(x, 256, 1)
branch_1 = conv2d_bn(branch_1, 288, 3, strides=2, padding='valid')
branch_2 = conv2d_bn(x, 256, 1)
branch_2 = conv2d_bn(branch_2, 288, 3)
branch_2 = conv2d_bn(branch_2, 320, 3, strides=2, padding='valid')
branch_pool = MaxPooling2D(3, strides=2, padding='valid')(x)
branches = [branch_0, branch_1, branch_2, branch_pool]
x = Concatenate(axis=channel_axis, name='mixed_7a')(branches)
# 10x block8 (Inception-ResNet-C block): 8 x 8 x 2080
for block_idx in range(1, 10):
x = inception_resnet_block(x,
scale=0.2,
block_type='block8',
block_idx=block_idx)
x = inception_resnet_block(x,
scale=1.,
activation=None,
block_type='block8',
block_idx=10)
# Final convolution block: 8 x 8 x 1536
x = conv2d_bn(x, 1536, 1, name='conv_7b')
# Classification block
x = GlobalAveragePooling2D(name='avg_pool')(x)
x = Dense(num_classes, activation='softmax', name='predictions')(x)
inputs = img_input
# Create model
model = Model(inputs, x, name='FineNet')
# Load weights
if pretrained_path != None:
print 'Loading FineNet weights from %s'%(pretrained_path)
model.load_weights(pretrained_path)
return model
def plot_confusion_matrix(cm, classes,
normalize=False,
title='Confusion matrix',
cmap=plt.cm.Blues):
"""
This function prints and plots the confusion matrix.
Normalization can be applied by setting `normalize=True`.
"""
plt.imshow(cm, interpolation='nearest', cmap=cmap)
plt.title(title)
plt.colorbar()
tick_marks = np.arange(len(classes))
plt.xticks(tick_marks, classes, rotation=45)
plt.yticks(tick_marks, classes)
if normalize:
cm = cm.astype('float') / cm.sum(axis=1)[:, np.newaxis]
print("Normalized confusion matrix")
else:
print('Confusion matrix, without normalization')
print(cm)
thresh = cm.max() / 2.
for i, j in itertools.product(range(cm.shape[0]), range(cm.shape[1])):
plt.text(j, i, cm[i, j],
horizontalalignment="center",
color="white" if cm[i, j] > thresh else "black")
plt.tight_layout()
plt.ylabel('True label')
plt.xlabel('Predicted label')
plt.show()
@@ -0,0 +1,172 @@
"""Code for FineNet in paper "Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge" at ICB 2018
https://arxiv.org/pdf/1712.09401.pdf
If you use whole or partial function in this code, please cite paper:
@inproceedings{Nguyen_MinutiaeNet,
author = {Dinh-Luan Nguyen and Kai Cao and Anil K. Jain},
title = {Robust Minutiae Extractor: Integrating Deep Networks and Fingerprint Domain Knowledge},
booktitle = {The 11th International Conference on Biometrics, 2018},
year = {2018},
}
"""
import sys,os
sys.path.append(os.path.realpath('../FineNet'))
from keras.optimizers import Adam
from keras.callbacks import ModelCheckpoint, LearningRateScheduler, TensorBoard
from keras.callbacks import ReduceLROnPlateau
from keras.preprocessing.image import ImageDataGenerator
from FineNet_model import FineNetmodel, plot_confusion_matrix
import numpy as np
import os
from sklearn.metrics import confusion_matrix
from datetime import datetime
os.environ["CUDA_VISIBLE_DEVICES"] = '2'
os.environ['KERAS_BACKEND'] = 'tensorflow'
output_dir = '../output_FineNet/'+datetime.now().strftime('%Y%m%d-%H%M%S')
# Prepare model model saving directory.
save_dir = os.path.join(os.getcwd(), output_dir)
log_dir = os.path.join(os.getcwd(), output_dir + '/logs')
# Training parameters
batch_size = 32
epochs = 200
num_classes = 2
# Subtracting pixel mean improves accuracy
subtract_pixel_mean = True
# Model size, patch
model_type = 'patch224batch32'
# =============== DATA loading ========================
train_path = '../Dataset/train/'
test_path = '../Dataset/validate/'
input_shape = (224, 224, 3)
# Using data augmentation technique for training
datagen = ImageDataGenerator(
# set input mean to 0 over the dataset
featurewise_center=False,
# set each sample mean to 0
samplewise_center=False,
# divide inputs by std of dataset
featurewise_std_normalization=False,
# divide each input by its std
samplewise_std_normalization=False,
# apply ZCA whitening
zca_whitening=False,
# randomly rotate images in the range (deg 0 to 180)
rotation_range=180,
# randomly shift images horizontally
width_shift_range=0.5,
# randomly shift images vertically
height_shift_range=0.5,
# randomly flip images
horizontal_flip=True,
# randomly flip images
vertical_flip=True)
train_batches = datagen.flow_from_directory(train_path, target_size=(input_shape[0], input_shape[1]), classes=['minu', 'non_minu'], batch_size=batch_size)
# Feed data from directory into batches
test_gen = ImageDataGenerator()
test_batches = test_gen.flow_from_directory(test_path, target_size=(input_shape[0], input_shape[1]), classes=['minu', 'non_minu'], batch_size=batch_size)
# =============== end DATA loading ========================
def lr_schedule(epoch):
"""Learning Rate Schedule
"""
lr = 0.5e-2
if epoch > 180:
lr *= 0.5e-3
elif epoch > 150:
lr *= 1e-3
elif epoch > 60:
lr *= 5e-2
elif epoch > 30:
lr *= 5e-1
print('Learning rate: ', lr)
return lr
#============== Define model ==================
model = FineNetmodel(num_classes = num_classes,
pretrained_path = '../Models/FineNet.h5',
input_shape=input_shape)
# Save model architecture
#plot_model(model, to_file='./modelFineNet.pdf',show_shapes=True)
model.compile(loss='categorical_crossentropy',
optimizer=Adam(lr=lr_schedule(0)),
metrics=['accuracy'])
#model.summary()
#============== End define model ==============
#============== Other stuffs for loging and parameters ==================
model_name = 'FineNet_%s_model.{epoch:03d}.h5' % model_type
if not os.path.isdir(save_dir):
os.makedirs(save_dir)
if not os.path.isdir(log_dir):
os.makedirs(log_dir)
filepath = os.path.join(save_dir, model_name)
# Show in tensorboard
tensorboard = TensorBoard(log_dir=log_dir, histogram_freq=0, write_graph=True, write_images=False)
# Prepare callbacks for model saving and for learning rate adjustment.
checkpoint = ModelCheckpoint(filepath=filepath,
monitor='val_acc',
verbose=1,
save_best_only=True)
lr_scheduler = LearningRateScheduler(lr_schedule)
lr_reducer = ReduceLROnPlateau(factor=np.sqrt(0.1),
cooldown=0,
patience=5,
min_lr=0.5e-6)
callbacks = [checkpoint, lr_reducer, lr_scheduler, tensorboard]
#============== End other stuffs ==================
# Begin training
model.fit_generator(train_batches,
validation_data=test_batches,
epochs=epochs, verbose=1,
callbacks=callbacks)
# Plot confusion matrix
score = model.evaluate_generator(test_batches)
print 'Test accuracy:', score[1]
predictions = model.predict_generator(test_batches)
test_labels = test_batches.classes[test_batches.index_array]
cm = confusion_matrix(test_labels, np.argmax(predictions,axis=1))
cm_plot_labels = ['minu','non_minu']
plot_confusion_matrix(cm, cm_plot_labels, title='Confusion Matrix')