diff --git a/README.rst b/README.rst
index 16ad8649340b5f35eb0526b2cd65f9a9e04fd281..5b6c578874ce4a0db243906fb5ad6e969d5eaa31 100644
--- a/README.rst
+++ b/README.rst
@@ -20,8 +20,7 @@
====================================================
This package is part of the signal-processing and machine learning toolbox
-Bob_. It implementes several different algorithms that are useful to detect
-presentation attacks.
+Bob_. It implements tools for spoofing or presentation attack detection in face biometrics.
Installation
diff --git a/bob/pad/face/algorithm/VideoSvmPadAlgorithm.py b/bob/pad/face/algorithm/VideoSvmPadAlgorithm.py
index 9cbaeb7d79365420c4cd7646afe5d50f0cd03237..d84b07529f7faf4dffbad287b20137794e275172 100644
--- a/bob/pad/face/algorithm/VideoSvmPadAlgorithm.py
+++ b/bob/pad/face/algorithm/VideoSvmPadAlgorithm.py
@@ -60,6 +60,19 @@ class VideoSvmPadAlgorithm(Algorithm):
``frame_level_scores_flag`` : :py:class:`bool`
Return scores for each frame individually if True. Otherwise, return a
single score per video. Default: False.
+
+ ``save_debug_data_flag`` : :py:class:`bool`
+ Save the data, which might be usefull for debugging if ``True``.
+ Default: ``True``.
+
+ ``reduced_train_data_flag`` : :py:class:`bool`
+ Reduce the amount of final training samples if set to ``True``.
+ Default: ``False``.
+
+ ``n_train_samples`` : :py:class:`int`
+ Number of uniformly selected feature vectors per class defining the
+ sizes of sub-sets used in the final traing of the SVM.
+ Default: 50000.
"""
def __init__(self,
@@ -68,7 +81,10 @@ class VideoSvmPadAlgorithm(Algorithm):
n_samples = 10000,
trainer_grid_search_params = { 'cost': [2**p for p in range(-5, 16, 2)], 'gamma': [2**p for p in range(-15, 4, 2)]},
mean_std_norm_flag = False,
- frame_level_scores_flag = False):
+ frame_level_scores_flag = False,
+ save_debug_data_flag = True,
+ reduced_train_data_flag = False,
+ n_train_samples = 50000):
Algorithm.__init__(self,
@@ -78,6 +94,9 @@ class VideoSvmPadAlgorithm(Algorithm):
trainer_grid_search_params = trainer_grid_search_params,
mean_std_norm_flag = mean_std_norm_flag,
frame_level_scores_flag = frame_level_scores_flag,
+ save_debug_data_flag = save_debug_data_flag,
+ reduced_train_data_flag = reduced_train_data_flag,
+ n_train_samples = n_train_samples,
performs_projection=True,
requires_projector_training=True)
@@ -87,6 +106,9 @@ class VideoSvmPadAlgorithm(Algorithm):
self.trainer_grid_search_params = trainer_grid_search_params
self.mean_std_norm_flag = mean_std_norm_flag
self.frame_level_scores_flag = frame_level_scores_flag
+ self.save_debug_data_flag = save_debug_data_flag
+ self.reduced_train_data_flag = reduced_train_data_flag
+ self.n_train_samples = n_train_samples
self.machine = None
@@ -217,6 +239,44 @@ class VideoSvmPadAlgorithm(Algorithm):
return features_subset
+ #==========================================================================
+ def select_quasi_uniform_data_subset(self, features, n_samples):
+ """
+ Select quasi uniformly N samples/feature vectors from the input array of samples.
+ The rows in the input array are samples. The columns are features.
+ Use this function if n_samples is close to the number of samples.
+
+ **Parameters:**
+
+ ``features`` : 2D :py:class:`numpy.ndarray`
+ Input array with feature vectors. The rows are samples, columns are features.
+
+ ``n_samples`` : :py:class:`int`
+ The number of samples to be selected uniformly from the input array of features.
+
+ **Returns:**
+
+ ``features_subset`` : 2D :py:class:`numpy.ndarray`
+ Selected subset of features.
+ """
+
+ if features.shape[0] <= n_samples:
+
+ features_subset = features
+
+ else:
+
+ uniform_step = (1.0 * features.shape[0]) / n_samples
+
+ element_num_list = range(0,n_samples)
+
+ idx = [np.int(uniform_step*item) for item in element_num_list]
+
+ features_subset = features[idx, :]
+
+ return features_subset
+
+
#==========================================================================
def split_data_to_train_cv(self, features):
"""
@@ -447,7 +507,9 @@ class VideoSvmPadAlgorithm(Algorithm):
trainer_grid_search_params = { 'cost': [2**p for p in range(-5, 16, 2)], 'gamma': [2**p for p in range(-15, 4, 2)]},
mean_std_norm_flag = False,
projector_file = "",
- save_debug_data_flag = True):
+ save_debug_data_flag = True,
+ reduced_train_data_flag = False,
+ n_train_samples = 50000):
"""
First, this function tunes the hyper-parameters of the SVM classifier using
grid search on the sub-sets of training data. Train and cross-validation
@@ -492,6 +554,15 @@ class VideoSvmPadAlgorithm(Algorithm):
Save the data, which might be usefull for debugging if ``True``.
Default: ``True``.
+ ``reduced_train_data_flag`` : :py:class:`bool`
+ Reduce the amount of final training samples if set to ``True``.
+ Default: ``False``.
+
+ ``n_train_samples`` : :py:class:`int`
+ Number of uniformly selected feature vectors per class defining the
+ sizes of sub-sets used in the final traing of the SVM.
+ Default: 50000.
+
**Returns:**
``machine`` : object
@@ -574,6 +645,12 @@ class VideoSvmPadAlgorithm(Algorithm):
real = features_norm[0:real.shape[0], :] # The array is now normalized
attack = features_norm[real.shape[0]:, :] # The array is now normalized
+ if reduced_train_data_flag:
+
+ # uniformly select subsets of features:
+ real = self.select_quasi_uniform_data_subset(real, n_train_samples)
+ attack = self.select_quasi_uniform_data_subset(attack, n_train_samples)
+
data = [np.copy(real), np.copy(attack)] # data for final training
machine = trainer.train(data) # train the machine
@@ -612,7 +689,10 @@ class VideoSvmPadAlgorithm(Algorithm):
kernel_type = self.kernel_type,
trainer_grid_search_params = self.trainer_grid_search_params,
mean_std_norm_flag = self.mean_std_norm_flag,
- projector_file = projector_file)
+ projector_file = projector_file,
+ save_debug_data_flag = self.save_debug_data_flag,
+ reduced_train_data_flag = self.reduced_train_data_flag,
+ n_train_samples = self.n_train_samples)
f = bob.io.base.HDF5File(projector_file, 'w') # open hdf5 file to save to
diff --git a/bob/pad/face/config/database/aggregated_db.py b/bob/pad/face/config/database/aggregated_db.py
new file mode 100644
index 0000000000000000000000000000000000000000..e12abfcd7cc21f9747caebcf9aa6a5e674170b17
--- /dev/null
+++ b/bob/pad/face/config/database/aggregated_db.py
@@ -0,0 +1,50 @@
+#!/usr/bin/env python
+
+"""Aggregated Db is a database for face PAD experiments.
+This database aggregates the data from 3 publicly available data-sets:
+`REPLAYATTACK`_, `REPLAY-MOBILE`_ and `MSU MFSD`_.
+You can download the data for the above databases by following the corresponding
+links.
+
+The reference citation for the `REPLAYATTACK`_ is [CAM12]_.
+The reference citation for the `REPLAY-MOBILE`_ is [CBVM16]_.
+The reference citation for the `MSU MFSD`_ is [WHJ15]_.
+
+.. include:: links.rst
+"""
+
+from bob.pad.face.database import AggregatedDbPadDatabase
+
+# Directory where the data files are stored.
+# This directory is given in the .bob_bio_databases.txt file located in your home directory
+original_directory = "[YOUR_AGGREGATED_DB_DIRECTORIES]"
+"""Value of ``~/.bob_bio_databases.txt`` for this database"""
+
+original_extension = ".mov" # extension of the data files
+
+database = AggregatedDbPadDatabase(
+ protocol='grandtest',
+ original_directory=original_directory,
+ original_extension=original_extension,
+ training_depends_on_protocol=True,
+)
+"""The :py:class:`bob.pad.base.database.PadDatabase` derivative with Aggregated Db
+database settings.
+
+.. warning::
+
+ This class only provides a programmatic interface to load data in an orderly
+ manner, respecting usage protocols. It does **not** contain the raw
+ data files. You should procure those yourself.
+
+Notice that ``original_directory`` is set to ``[YOUR_AGGREGATED_DB_DIRECTORIES]``.
+You must make sure to create ``${HOME}/.bob_bio_databases.txt`` file setting this
+value to the places where you actually installed the Replay-Attack, Replay-Mobile
+and MSU MFSD Databases. In particular, the paths pointing to these 3 databases
+must be separated with a space. See the following note with an example of
+``[YOUR_AGGREGATED_DB_DIRECTORIES]`` entry in the ``${HOME}/.bob_bio_databases.txt`` file.
+
+.. note::
+
+ [YOUR_AGGREGATED_DB_DIRECTORIES] = <PATH_TO_REPLAY_ATTACK> <PATH_TO_REPLAY_MOBILE> <PATH_TO_MSU_MFSD>
+"""
\ No newline at end of file
diff --git a/bob/pad/face/config/frame_diff_svm_aggregated_db.py b/bob/pad/face/config/frame_diff_svm_aggregated_db.py
new file mode 100644
index 0000000000000000000000000000000000000000..0379d88193b9f21eeab0eee8bafb7ebefae067ea
--- /dev/null
+++ b/bob/pad/face/config/frame_diff_svm_aggregated_db.py
@@ -0,0 +1,106 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+"""
+This file contains configurations to run Frame Differences and SVM based face PAD baseline.
+The settings of the preprocessor and extractor are tuned for the Replay-attack database.
+In the SVM algorithm the amount of training data is reduced speeding-up the training for
+large data sets, such as Aggregated PAD database.
+The IQM features used in this algorithm/resource are introduced in the following papers: [WHJ15]_ and [CBVM16]_.
+"""
+
+
+#=======================================================================================
+sub_directory = 'frame_diff_svm'
+"""
+Sub-directory where results will be placed.
+
+You may change this setting using the ``--sub-directory`` command-line option
+or the attribute ``sub_directory`` in a configuration file loaded **after**
+this resource.
+"""
+
+
+#=======================================================================================
+# define preprocessor:
+
+from ..preprocessor import FrameDifference
+
+NUMBER_OF_FRAMES = None # process all frames
+CHECK_FACE_SIZE_FLAG = True # Check size of the face
+MIN_FACE_SIZE = 50 # Minimal size of the face to consider
+
+preprocessor = FrameDifference(number_of_frames = NUMBER_OF_FRAMES,
+ check_face_size_flag = CHECK_FACE_SIZE_FLAG,
+ min_face_size = MIN_FACE_SIZE)
+"""
+In the preprocessing stage the frame differences are computed for both facial and non-facial/background
+regions. In this case all frames of the input video are considered, which is defined by
+``number_of_frames = None``. The frames containing faces of the size below ``min_face_size = 50`` threshold
+are discarded. Both RGB and gray-scale videos are acceptable by the preprocessor.
+The preprocessing idea is introduced in [AM11]_.
+"""
+
+
+#=======================================================================================
+# define extractor:
+
+from ..extractor import FrameDiffFeatures
+
+WINDOW_SIZE=20
+OVERLAP=0
+
+extractor = FrameDiffFeatures(window_size=WINDOW_SIZE,
+ overlap=OVERLAP)
+"""
+In the feature extraction stage 5 features are extracted for all non-overlapping windows in
+the Frame Difference input signals. Five features are computed for each of windows in the
+facial face regions, the same is done for non-facial regions. The non-overlapping option
+is controlled by ``overlap = 0``. The length of the window is defined by ``window_size``
+argument.
+The features are introduced in the following paper: [AM11]_.
+"""
+
+
+#=======================================================================================
+# define algorithm:
+
+from ..algorithm import VideoSvmPadAlgorithm
+
+MACHINE_TYPE = 'C_SVC'
+KERNEL_TYPE = 'RBF'
+N_SAMPLES = 10000
+TRAINER_GRID_SEARCH_PARAMS = {'cost': [2**P for P in range(-3, 14, 2)], 'gamma': [2**P for P in range(-15, 0, 2)]}
+MEAN_STD_NORM_FLAG = True # enable mean-std normalization
+FRAME_LEVEL_SCORES_FLAG = True # one score per frame(!) in this case
+SAVE_DEBUG_DATA_FLAG = True # save the data, which might be useful for debugging
+REDUCED_TRAIN_DATA_FLAG = True # reduce the amount of training data in the final training stage
+N_TRAIN_SAMPLES = 50000 # number of training samples per class in the final SVM training stage
+
+algorithm = VideoSvmPadAlgorithm(machine_type = MACHINE_TYPE,
+ kernel_type = KERNEL_TYPE,
+ n_samples = N_SAMPLES,
+ trainer_grid_search_params = TRAINER_GRID_SEARCH_PARAMS,
+ mean_std_norm_flag = MEAN_STD_NORM_FLAG,
+ frame_level_scores_flag = FRAME_LEVEL_SCORES_FLAG,
+ save_debug_data_flag = SAVE_DEBUG_DATA_FLAG,
+ reduced_train_data_flag = REDUCED_TRAIN_DATA_FLAG,
+ n_train_samples = N_TRAIN_SAMPLES)
+"""
+The SVM algorithm with RBF kernel is used to classify the data into *real* and *attack* classes.
+One score is produced for each frame of the input video, ``frame_level_scores_flag = True``.
+The grid search of SVM parameters is used to select the successful settings.
+The grid search is done on the subset of training data.
+The size of this subset is defined by ``n_samples`` parameter.
+The final training of the SVM is done on the subset of training data ``reduced_train_data_flag = True``.
+The size of the subset for the final training stage is defined by the ``n_train_samples`` argument.
+The data is also mean-std normalized, ``mean_std_norm_flag = True``.
+"""
+
+
+
+
+
+
+
+
diff --git a/bob/pad/face/config/lbp_svm_aggregated_db.py b/bob/pad/face/config/lbp_svm_aggregated_db.py
new file mode 100644
index 0000000000000000000000000000000000000000..5d249a7c83ed3169319e06130096f89a1e725ca7
--- /dev/null
+++ b/bob/pad/face/config/lbp_svm_aggregated_db.py
@@ -0,0 +1,116 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+"""
+This file contains configurations to run LBP and SVM based face PAD baseline.
+The settings of the preprocessor and extractor are tuned for the Replay-attack database.
+In the SVM algorithm the amount of training data is reduced speeding-up the training for
+large data sets, such as Aggregated PAD database.
+The idea of the algorithm is introduced in the following paper: [CAM12]_.
+However some settings are different from the ones introduced in the paper.
+"""
+
+
+#=======================================================================================
+sub_directory = 'lbp_svm_aggregated_db'
+"""
+Sub-directory where results will be placed.
+
+You may change this setting using the ``--sub-directory`` command-line option
+or the attribute ``sub_directory`` in a configuration file loaded **after**
+this resource.
+"""
+
+
+#=======================================================================================
+# define preprocessor:
+
+from ..preprocessor import VideoFaceCrop
+
+CROPPED_IMAGE_SIZE = (64, 64) # The size of the resulting face
+CROPPED_POSITIONS = {'topleft' : (0,0) , 'bottomright' : CROPPED_IMAGE_SIZE}
+FIXED_POSITIONS = None
+MASK_SIGMA = None # The sigma for random values areas outside image
+MASK_NEIGHBORS = 5 # The number of neighbors to consider while extrapolating
+MASK_SEED = None # The seed for generating random values during extrapolation
+CHECK_FACE_SIZE_FLAG = True # Check the size of the face
+MIN_FACE_SIZE = 50 # Minimal possible size of the face
+USE_LOCAL_CROPPER_FLAG = True # Use the local face cropping class (identical to Ivana's paper)
+COLOR_CHANNEL = 'gray' # Convert image to gray-scale format
+
+preprocessor = VideoFaceCrop(cropped_image_size = CROPPED_IMAGE_SIZE,
+ cropped_positions = CROPPED_POSITIONS,
+ fixed_positions = FIXED_POSITIONS,
+ mask_sigma = MASK_SIGMA,
+ mask_neighbors = MASK_NEIGHBORS,
+ mask_seed = None,
+ check_face_size_flag = CHECK_FACE_SIZE_FLAG,
+ min_face_size = MIN_FACE_SIZE,
+ use_local_cropper_flag = USE_LOCAL_CROPPER_FLAG,
+ color_channel = COLOR_CHANNEL)
+"""
+In the preprocessing stage the face is cropped in each frame of the input video given facial annotations.
+The size of the face is normalized to ``cropped_image_size`` dimensions. The faces with the size
+below ``min_face_size`` threshold are discarded. The preprocessor is similar to the one introduced in
+[CAM12]_, which is defined by ``use_local_cropper_flag = True``.
+"""
+
+
+#=======================================================================================
+# define extractor:
+
+from ..extractor import VideoLBPHistogram
+
+LBPTYPE='uniform'
+ELBPTYPE='regular'
+RAD=1
+NEIGHBORS=8
+CIRC=False
+DTYPE=None
+
+extractor = VideoLBPHistogram(lbptype=LBPTYPE,
+ elbptype=ELBPTYPE,
+ rad=RAD,
+ neighbors=NEIGHBORS,
+ circ=CIRC,
+ dtype=DTYPE)
+"""
+In the feature extraction stage the LBP histograms are extracted from each frame of the preprocessed video.
+The parameters are similar to the ones introduced in [CAM12]_.
+"""
+
+
+#=======================================================================================
+# define algorithm:
+
+from ..algorithm import VideoSvmPadAlgorithm
+
+MACHINE_TYPE = 'C_SVC'
+KERNEL_TYPE = 'RBF'
+N_SAMPLES = 10000
+TRAINER_GRID_SEARCH_PARAMS = {'cost': [2**P for P in range(-3, 14, 2)], 'gamma': [2**P for P in range(-15, 0, 2)]}
+MEAN_STD_NORM_FLAG = True # enable mean-std normalization
+FRAME_LEVEL_SCORES_FLAG = True # one score per frame(!) in this case
+SAVE_DEBUG_DATA_FLAG = True # save the data, which might be useful for debugging
+REDUCED_TRAIN_DATA_FLAG = True # reduce the amount of training data in the final training stage
+N_TRAIN_SAMPLES = 50000 # number of training samples per class in the final SVM training stage
+
+algorithm = VideoSvmPadAlgorithm(machine_type = MACHINE_TYPE,
+ kernel_type = KERNEL_TYPE,
+ n_samples = N_SAMPLES,
+ trainer_grid_search_params = TRAINER_GRID_SEARCH_PARAMS,
+ mean_std_norm_flag = MEAN_STD_NORM_FLAG,
+ frame_level_scores_flag = FRAME_LEVEL_SCORES_FLAG,
+ save_debug_data_flag = SAVE_DEBUG_DATA_FLAG,
+ reduced_train_data_flag = REDUCED_TRAIN_DATA_FLAG,
+ n_train_samples = N_TRAIN_SAMPLES)
+"""
+The SVM algorithm with RBF kernel is used to classify the data into *real* and *attack* classes.
+One score is produced for each frame of the input video, ``frame_level_scores_flag = True``.
+The grid search of SVM parameters is used to select the successful settings.
+The grid search is done on the subset of training data.
+The size of this subset is defined by ``n_samples`` parameter.
+The final training of the SVM is done on the subset of training data ``reduced_train_data_flag = True``.
+The size of the subset for the final training stage is defined by the ``n_train_samples`` argument.
+The data is also mean-std normalized, ``mean_std_norm_flag = True``.
+"""
\ No newline at end of file
diff --git a/bob/pad/face/config/qm_svm_aggregated_db.py b/bob/pad/face/config/qm_svm_aggregated_db.py
new file mode 100644
index 0000000000000000000000000000000000000000..4bd54236a09e56ef66fb503daef7baa2ee5a7182
--- /dev/null
+++ b/bob/pad/face/config/qm_svm_aggregated_db.py
@@ -0,0 +1,112 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+"""
+This file contains configurations to run Image Quality Measures (IQM) and SVM based face PAD baseline.
+The settings of the preprocessor and extractor are tuned for the Replay-attack database.
+In the SVM algorithm the amount of training data is reduced speeding-up the training for
+large data sets, such as Aggregated PAD database.
+The IQM features used in this algorithm/resource are introduced in the following papers: [WHJ15]_ and [CBVM16]_.
+"""
+
+
+#=======================================================================================
+sub_directory = 'qm_svm_aggregated_db'
+"""
+Sub-directory where results will be placed.
+
+You may change this setting using the ``--sub-directory`` command-line option
+or the attribute ``sub_directory`` in a configuration file loaded **after**
+this resource.
+"""
+
+
+#=======================================================================================
+# define preprocessor:
+
+from ..preprocessor import VideoFaceCrop
+
+CROPPED_IMAGE_SIZE = (64, 64) # The size of the resulting face
+CROPPED_POSITIONS = {'topleft' : (0,0) , 'bottomright' : CROPPED_IMAGE_SIZE}
+FIXED_POSITIONS = None
+MASK_SIGMA = None # The sigma for random values areas outside image
+MASK_NEIGHBORS = 5 # The number of neighbors to consider while extrapolating
+MASK_SEED = None # The seed for generating random values during extrapolation
+CHECK_FACE_SIZE_FLAG = True # Check the size of the face
+MIN_FACE_SIZE = 50
+USE_LOCAL_CROPPER_FLAG = True # Use the local face cropping class (identical to Ivana's paper)
+RGB_OUTPUT_FLAG = True # Return RGB cropped face using local cropper
+
+preprocessor = VideoFaceCrop(cropped_image_size = CROPPED_IMAGE_SIZE,
+ cropped_positions = CROPPED_POSITIONS,
+ fixed_positions = FIXED_POSITIONS,
+ mask_sigma = MASK_SIGMA,
+ mask_neighbors = MASK_NEIGHBORS,
+ mask_seed = None,
+ check_face_size_flag = CHECK_FACE_SIZE_FLAG,
+ min_face_size = MIN_FACE_SIZE,
+ use_local_cropper_flag = USE_LOCAL_CROPPER_FLAG,
+ rgb_output_flag = RGB_OUTPUT_FLAG)
+"""
+In the preprocessing stage the face is cropped in each frame of the input video given facial annotations.
+The size of the face is normalized to ``cropped_image_size`` dimensions. The faces of the size
+below ``min_face_size`` threshold are discarded. The preprocessor is similar to the one introduced in
+[CAM12]_, which is defined by ``use_local_cropper_flag = True``. The preprocessed frame is the RGB
+facial image, which is defined by ``RGB_OUTPUT_FLAG = True``.
+"""
+
+
+#=======================================================================================
+# define extractor:
+
+from ..extractor import VideoQualityMeasure
+
+GALBALLY=True
+MSU=True
+DTYPE=None
+
+extractor = VideoQualityMeasure(galbally=GALBALLY,
+ msu=MSU,
+ dtype=DTYPE)
+"""
+In the feature extraction stage the Image Quality Measures are extracted from each frame of the preprocessed RGB video.
+The features to be computed are introduced in the following papers: [WHJ15]_ and [CBVM16]_.
+"""
+
+
+#=======================================================================================
+# define algorithm:
+
+from ..algorithm import VideoSvmPadAlgorithm
+
+MACHINE_TYPE = 'C_SVC'
+KERNEL_TYPE = 'RBF'
+N_SAMPLES = 10000
+TRAINER_GRID_SEARCH_PARAMS = {'cost': [2**P for P in range(-3, 14, 2)], 'gamma': [2**P for P in range(-15, 0, 2)]}
+MEAN_STD_NORM_FLAG = True # enable mean-std normalization
+FRAME_LEVEL_SCORES_FLAG = True # one score per frame(!) in this case
+SAVE_DEBUG_DATA_FLAG = True # save the data, which might be useful for debugging
+REDUCED_TRAIN_DATA_FLAG = True # reduce the amount of training data in the final training stage
+N_TRAIN_SAMPLES = 50000 # number of training samples per class in the final SVM training stage
+
+algorithm = VideoSvmPadAlgorithm(machine_type = MACHINE_TYPE,
+ kernel_type = KERNEL_TYPE,
+ n_samples = N_SAMPLES,
+ trainer_grid_search_params = TRAINER_GRID_SEARCH_PARAMS,
+ mean_std_norm_flag = MEAN_STD_NORM_FLAG,
+ frame_level_scores_flag = FRAME_LEVEL_SCORES_FLAG,
+ save_debug_data_flag = SAVE_DEBUG_DATA_FLAG,
+ reduced_train_data_flag = REDUCED_TRAIN_DATA_FLAG,
+ n_train_samples = N_TRAIN_SAMPLES)
+"""
+The SVM algorithm with RBF kernel is used to classify the data into *real* and *attack* classes.
+One score is produced for each frame of the input video, ``frame_level_scores_flag = True``.
+The grid search of SVM parameters is used to select the successful settings.
+The grid search is done on the subset of training data.
+The size of this subset is defined by ``n_samples`` parameter.
+The final training of the SVM is done on the subset of training data ``reduced_train_data_flag = True``.
+The size of the subset for the final training stage is defined by the ``n_train_samples`` argument.
+The data is also mean-std normalized, ``mean_std_norm_flag = True``.
+"""
+
+
diff --git a/bob/pad/face/database/__init__.py b/bob/pad/face/database/__init__.py
index abf2f69122cb549489bf3f043f6c66e8c160ed88..bc586be28417c221340e0bf11297282f5cb4e6d6 100644
--- a/bob/pad/face/database/__init__.py
+++ b/bob/pad/face/database/__init__.py
@@ -1,6 +1,8 @@
from .replay import ReplayPadDatabase
from .replay_mobile import ReplayMobilePadDatabase
from .msu_mfsd import MsuMfsdPadDatabase
+from .aggregated_db import AggregatedDbPadDatabase
+
# gets sphinx autodoc done right - don't remove it
def __appropriate__(*args):
@@ -20,6 +22,7 @@ __appropriate__(
ReplayPadDatabase,
ReplayMobilePadDatabase,
MsuMfsdPadDatabase,
+ AggregatedDbPadDatabase,
)
__all__ = [_ for _ in dir() if not _.startswith('_')]
diff --git a/bob/pad/face/database/aggregated_db.py b/bob/pad/face/database/aggregated_db.py
new file mode 100644
index 0000000000000000000000000000000000000000..353c2d681d6c0f114dd8d1d2a66af383ae2e33e7
--- /dev/null
+++ b/bob/pad/face/database/aggregated_db.py
@@ -0,0 +1,359 @@
+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+#==============================================================================
+from bob.pad.base.database import PadFile # Used in ReplayPadFile class
+
+from bob.pad.base.database import PadDatabase
+
+# Import HLDI for the databases to aggregate:
+from bob.pad.face.database import replay as replay_hldi
+
+from bob.pad.face.database import replay_mobile as replay_mobile_hldi
+
+from bob.pad.face.database import msu_mfsd as msu_mfsd_hldi
+
+import numpy as np
+
+#==============================================================================
+class AggregatedDbPadFile(PadFile):
+ """
+ A high level implementation of the File class for the Aggregated Database
+ uniting 3 databases: REPLAY-ATTACK, REPLAY-MOBILE and MSU MFSD.
+ """
+
+ def __init__(self, f):
+ """
+ **Parameters:**
+
+ ``f`` : :py:class:`object`
+ An instance of the File class defined in the low level db interface
+ of the Replay-Attack or Replay-Mobile or MSU MFSD database, respectively
+ in the bob.db.replay.models.py file or
+ in the bob.db.replaymobile.models.py file or
+ in the bob.db.msu_mfsd_mod.models.py file.
+ """
+
+ self.f = f
+ # this f is actually an instance of the File class that is defined in
+ # bob.db.<database_name>.models and the PadFile class here needs
+ # client_id, path, attack_type, file_id for initialization. We have to
+ # convert information here and provide them to PadFile. attack_type is a
+ # little tricky to get here. Based on the documentation of PadFile:
+ # In cased of a spoofed data, this parameter should indicate what kind of spoofed attack it is.
+ # The default None value is interpreted that the PadFile is a genuine or real sample.
+ if f.is_real():
+ attack_type = None
+ else:
+ attack_type = 'attack'
+ # attack_type is a string and I decided to make it like this for this
+ # particular database. You can do whatever you want for your own database.
+
+ file_path = self.encode_file_path(f)
+
+ file_id = self.encode_file_id(f)
+
+ super(AggregatedDbPadFile, self).__init__(client_id = f.client_id, path = file_path,
+ attack_type = attack_type, file_id = file_id)
+
+
+ #==========================================================================
+ def encode_file_id(self, f, n = 2000):
+ """
+ Return a modified version of the ``f.id`` ensuring uniqueness of the ids
+ across all databases.
+
+ **Parameters:**
+
+ ``f`` : :py:class:`object`
+ An instance of the File class defined in the low level db interface
+ of the Replay-Attack or Replay-Mobile or MSU MFSD database, respectively
+ in the bob.db.replay.models.py file or
+ in the bob.db.replaymobile.models.py file or
+ in the bob.db.msu_mfsd_mod.models.py file.
+
+ ``n`` : :py:class:`int`
+ An offset to be added to the file id for different databases is defined
+ as follows: offset = k*n, where k is the database number,
+ k = 0,1,2 in our case. Default: 2000.
+
+ **Returns:**
+
+ ``file_id`` : :py:class:`int`
+ A modified version of the file id, which is now unigue accross
+ all databases.
+ """
+
+ import bob.db.replay
+ import bob.db.replaymobile
+ import bob.db.msu_mfsd_mod
+
+ if isinstance(f, bob.db.replay.models.File): # check if instance of File class of LLDI of Replay-Attack
+
+ file_id = f.id
+
+ if isinstance(f, bob.db.replaymobile.models.File): # check if instance of File class of LLDI of Replay-Mobile
+
+ file_id = np.int(f.id + n)
+
+ if isinstance(f, bob.db.msu_mfsd_mod.models.File): # check if instance of File class of LLDI of MSU MFSD
+
+ file_id = np.int(f.id + 2*n)
+
+ return file_id
+
+
+ #==========================================================================
+ def encode_file_path(self, f):
+ """
+ Append the name of the database to the end of the file path separated
+ with "_".
+
+ **Parameters:**
+
+ ``f`` : :py:class:`object`
+ An instance of the File class defined in the low level db interface
+ of the Replay-Attack or Replay-Mobile or MSU MFSD database, respectively
+ in the bob.db.replay.models.py file or
+ in the bob.db.replaymobile.models.py file or
+ in the bob.db.msu_mfsd_mod.models.py file.
+
+ **Returns:**
+
+ ``file_path`` : :py:class:`str`
+ Modified path to the file, with database name appended to the end
+ separated with "_".
+ """
+
+ import bob.db.replay
+ import bob.db.replaymobile
+ import bob.db.msu_mfsd_mod
+
+ if isinstance(f, bob.db.replay.models.File): # check if instance of File class of LLDI of Replay-Attack
+
+ file_path = '_'.join([f.path, 'replay'])
+
+ if isinstance(f, bob.db.replaymobile.models.File): # check if instance of File class of LLDI of Replay-Mobile
+
+ file_path = '_'.join([f.path, 'replaymobile'])
+
+ if isinstance(f, bob.db.msu_mfsd_mod.models.File): # check if instance of File class of LLDI of MSU MFSD
+
+ file_path = '_'.join([f.path, 'msu_mfsd_mod'])
+
+ return file_path
+
+
+ #==========================================================================
+ def load(self, directory=None, extension='.mov'):
+ """
+ Overridden version of the load method defined in the ``PadFile``.
+
+ **Parameters:**
+
+ ``directory`` : :py:class:`str`
+ String containing the paths to all databases used in this aggregated
+ database. The paths are separated with a space.
+
+ ``extension`` : :py:class:`str`
+ Extension of the video files in the REPLAY-ATTACK and REPLAY-MOBILE
+ databases. The extension of files in MSU MFSD is not taken into account
+ in the HighLevel DB Interface of MSU MFSD. Default: '.mov'.
+
+ **Returns:**
+
+ ``video_data`` : FrameContainer
+ Video data stored in the FrameContainer, see ``bob.bio.video.utils.FrameContainer``
+ for further details.
+ """
+
+ import bob.db.replay
+ import bob.db.replaymobile
+ import bob.db.msu_mfsd_mod
+
+ directories = directory.split(" ")
+
+ if isinstance(self.f, bob.db.replay.models.File): # check if instance of File class of LLDI of Replay-Attack
+
+ db_pad_file = replay_hldi.ReplayPadFile(self.f) # replay_hldi is HLDI of Replay-Attack
+
+ directory = directories[0]
+
+ if isinstance(self.f, bob.db.replaymobile.models.File): # check if instance of File class of LLDI of Replay-Mobile
+
+ db_pad_file = replay_mobile_hldi.ReplayMobilePadFile(self.f) # replay_mobile_hldi is HLDI of Replay-Mobile
+
+ directory = directories[1]
+
+ if isinstance(self.f, bob.db.msu_mfsd_mod.models.File): # check if instance of File class of LLDI of MSU MFSD
+
+ db_pad_file = msu_mfsd_hldi.MsuMfsdPadFile(self.f) # msu_mfsd_hldi is HLDI of MSU MFSD
+
+ directory = directories[2]
+
+ video_data = db_pad_file.load(directory = directory, extension = extension)
+
+ return video_data # video data
+
+
+#==============================================================================
+class AggregatedDbPadDatabase(PadDatabase):
+ """
+ A high level implementation of the Database class for the Aggregated Database
+ uniting 3 databases: REPLAY-ATTACK, REPLAY-MOBILE and MSU MFSD.
+ """
+
+ def __init__(
+ self,
+ protocol='grandtest', # grandtest is the default protocol for this database
+ original_directory=None,
+ original_extension=None,
+ **kwargs):
+ """
+ **Parameters:**
+
+ ``protocol`` : :py:class:`str` or ``None``
+ The name of the protocol that defines the default experimental setup
+ for this database. Default: 'grandtest'.
+
+ ``original_directory`` : :py:class:`str`
+ String containing the paths to all databases used in this aggregated
+ database. The paths are separated with a space. Default: None.
+
+ ``original_extension`` : :py:class:`str`
+ Extension of the video files in the REPLAY-ATTACK and REPLAY-MOBILE
+ databases. The extension of files in MSU MFSD is not taken into account
+ in the HighLevel DB Interface of MSU MFSD. Default: None.
+
+ ``kwargs``
+ The arguments of the :py:class:`bob.bio.base.database.BioDatabase` base class constructor.
+ """
+
+ # Import LLDI for all databases:
+ import bob.db.replay
+ import bob.db.replaymobile
+ import bob.db.msu_mfsd_mod
+
+ self.replay_db = bob.db.replay.Database()
+ self.replaymobile_db = bob.db.replaymobile.Database()
+ self.msu_mfsd_db = bob.db.msu_mfsd_mod.Database()
+
+ # Since the high level API expects different group names than what the low
+ # level API offers, you need to convert them when necessary
+ self.low_level_group_names = ('train', 'devel', 'test') # group names in the low-level database interface
+ self.high_level_group_names = ('train', 'dev', 'eval') # names are expected to be like that in objects() function
+
+ # Always use super to call parent class methods.
+ super(AggregatedDbPadDatabase, self).__init__(
+ name = 'aggregated_db',
+ protocol = protocol,
+ original_directory = original_directory,
+ original_extension = original_extension,
+ **kwargs)
+
+
+ #==========================================================================
+ def objects(self, groups=None, protocol=None, purposes=None, model_ids=None, **kwargs):
+ """
+ This function returns a list of AggregatedDbPadFile objects, which fulfill the given restrictions.
+
+ Keyword parameters:
+
+ ``groups`` : :py:class:`str`
+ OR a list of strings.
+ The groups of which the clients should be returned.
+ Usually, groups are one or more elements of ('train', 'dev', 'eval')
+
+ ``protocol`` : :py:class:`str`
+ The protocol for which the clients should be retrieved.
+ The protocol is dependent on your database.
+ If you do not have protocols defined, just ignore this field.
+
+ ``purposes`` : :py:class:`str`
+ OR a list of strings.
+ The purposes for which File objects should be retrieved.
+ Usually it is either 'real' or 'attack'.
+
+ ``model_ids``
+ This parameter is not supported in PAD databases yet
+
+ **Returns:**
+
+ ``files`` : [AggregatedDbPadFile]
+ A list of AggregatedDbPadFile objects.
+ """
+
+ # Convert group names to low-level group names here.
+ groups = self.convert_names_to_lowlevel(groups, self.low_level_group_names, self.high_level_group_names)
+ # Since this database was designed for PAD experiments, nothing special
+ # needs to be done here.
+ replay_files = self.replay_db.objects(protocol=protocol, groups=groups, cls=purposes, **kwargs)
+
+ replaymobile_files = self.replaymobile_db.objects(protocol=protocol, groups=groups, cls=purposes, **kwargs)
+
+ msu_mfsd_files = self.msu_mfsd_db.objects(group=groups, cls=purposes, **kwargs)
+
+ files = replay_files + replaymobile_files + msu_mfsd_files # append all files to a single list
+
+ files = [AggregatedDbPadFile(f) for f in files]
+ return files
+
+
+ #==========================================================================
+ def annotations(self, f):
+ """
+ Return annotations for a given file object ``f``, which is an instance
+ of ``AggregatedDbPadFile`` defined in the HLDI of the Aggregated DB.
+ The ``load()`` method of ``AggregatedDbPadFile`` class (see above)
+ returns a video, therefore this method returns bounding-box annotations
+ for each video frame. The annotations are returned as dictionary of dictionaries.
+
+ **Parameters:**
+
+ ``f`` : :py:class:`object`
+ An instance of ``AggregatedDbPadFile`` defined above.
+
+ **Returns:**
+
+ ``annotations`` : :py:class:`dict`
+ A dictionary containing the annotations for each frame in the video.
+ Dictionary structure: ``annotations = {'1': frame1_dict, '2': frame1_dict, ...}``.
+ Where ``frameN_dict = {'topleft': (row, col), 'bottomright': (row, col)}``
+ is the dictionary defining the coordinates of the face bounding box in frame N.
+ """
+
+ import bob.db.replay
+ import bob.db.replaymobile
+ import bob.db.msu_mfsd_mod
+
+ directories = self.original_directory.split(" ")
+
+ if isinstance(f.f, bob.db.replay.models.File): # check if instance of File class of LLDI of Replay-Attack
+
+ hldi_db = replay_hldi.ReplayPadDatabase(original_directory = directories[0])
+
+ if isinstance(f.f, bob.db.replaymobile.models.File): # check if instance of File class of LLDI of Replay-Mobile
+
+ hldi_db = replay_mobile_hldi.ReplayMobilePadDatabase(original_directory = directories[1])
+
+ if isinstance(f.f, bob.db.msu_mfsd_mod.models.File): # check if instance of File class of LLDI of MSU MFSD
+
+ hldi_db = msu_mfsd_hldi.MsuMfsdPadDatabase(original_directory = directories[2])
+
+ annotations = hldi_db.annotations(f)
+
+ return annotations
+
+
+
+
+
+
+
+
+
+
+
+
+
+
diff --git a/bob/pad/face/database/msu_mfsd.py b/bob/pad/face/database/msu_mfsd.py
index 7b183441c2128e222c17725268c6e117328ef8dc..52c7fb8fca9e2ed4594ed465f9d8cba2d353bbd5 100644
--- a/bob/pad/face/database/msu_mfsd.py
+++ b/bob/pad/face/database/msu_mfsd.py
@@ -181,7 +181,7 @@ class MsuMfsdPadDatabase(PadDatabase):
**Returns:**
- ``files`` : :py:class:`str`
+ ``files`` : [MsuMfsdPadFile]
A list of MsuMfsdPadFile objects.
"""
diff --git a/bob/pad/face/database/replay.py b/bob/pad/face/database/replay.py
index 1d1a663548a40e4751f6564e68d55779fd816d41..d9656f3dd0639a73fcf698b1944a2b9687eae252 100644
--- a/bob/pad/face/database/replay.py
+++ b/bob/pad/face/database/replay.py
@@ -148,9 +148,10 @@ class ReplayPadDatabase(PadDatabase):
**Returns:**
- ``files`` : :py:class:`str`
+ ``files`` : [ReplayPadFile]
A list of ReplayPadFile objects.
"""
+
# Convert group names to low-level group names here.
groups = self.convert_names_to_lowlevel(groups, self.low_level_group_names, self.high_level_group_names)
# Since this database was designed for PAD experiments, nothing special
diff --git a/bob/pad/face/database/replay_mobile.py b/bob/pad/face/database/replay_mobile.py
index 773ca43d469e5341500948c12c2837faa61aa0ea..9745e181a9ef6090f0d9c38f0af8d42208bf9bdd 100644
--- a/bob/pad/face/database/replay_mobile.py
+++ b/bob/pad/face/database/replay_mobile.py
@@ -173,7 +173,7 @@ class ReplayMobilePadDatabase(PadDatabase):
**Returns:**
- ``files`` : :py:class:`str`
+ ``files`` : [ReplayMobilePadFile]
A list of ReplayMobilePadFile objects.
"""
diff --git a/doc/api.rst b/doc/api.rst
index 8f94169abe5406ee6bfa772b71ff72ff0c5e9153..3b834a8cd2fc9e468bba8b6c78293837ece98dd3 100644
--- a/doc/api.rst
+++ b/doc/api.rst
@@ -31,6 +31,12 @@ MSU MFSD Database
.. autoclass:: bob.pad.face.database.msu_mfsd.MsuMfsdPadFile
.. autoclass:: bob.pad.face.database.msu_mfsd.MsuMfsdPadDatabase
+Aggregated Database
+========================
+
+.. autoclass:: bob.pad.face.database.aggregated_db.AggregatedDbPadFile
+.. autoclass:: bob.pad.face.database.aggregated_db.AggregatedDbPadDatabase
+
Pre-processors
------------------------------
diff --git a/doc/baselines.rst b/doc/baselines.rst
index 80057a25df0a54a75ddaf3ec93105368fd2acabe..410fc0e4dfa0d775ee0db974be6fb68aea10d4b0 100644
--- a/doc/baselines.rst
+++ b/doc/baselines.rst
@@ -182,7 +182,7 @@ The EER/HTER errors for `replayattack`_ database are summarized in the Table bel
+-------------------+----------+----------+
| Protocol | EER,\% | HTER,\% |
+===================+==========+==========+
-| ``grandtest`` | 4.321 | 4.570 |
+| ``grandtest`` | 3.987 | 4.571 |
+-------------------+----------+----------+
The ROC curves for the particular experiment can be downloaded from here:
@@ -337,7 +337,7 @@ The EER/HTER errors for the `Replay-Mobile`_ database are summarized in the Tabl
+-------------------+----------+----------+
| Protocol | EER,\% | HTER,\% |
+===================+==========+==========+
-| ``grandtest`` | 2.772 | 5.886 |
+| ``grandtest`` | 1.747 | 4.074 |
+-------------------+----------+----------+
The ROC curves for the particular experiment can be downloaded from here:
@@ -493,7 +493,7 @@ The EER/HTER errors for the `MSU MFSD`_ database are summarized in the Table bel
+-------------------+----------+----------+
| Protocol | EER,\% | HTER,\% |
+===================+==========+==========+
-| ``grandtest`` | 4.115 | 5.564 |
+| ``grandtest`` | 3.665 | 4.944 |
+-------------------+----------+----------+
The ROC curves for the particular experiment can be downloaded from here:
@@ -552,5 +552,20 @@ The ROC curves for the particular experiment can be downloaded from here:
------------
+.. _bob.pad.face.baselines.aggregated_db:
+
+Baselines on Aggregated Database
+--------------------------------------
+
+This section summarizes the results of baseline face PAD experiments on the Aggregated Database.
+The description of the database instance, which can be used to run face PAD experiments on the Aggregated Database is given
+here :ref:`bob.pad.face.resources.databases.aggregated_db`.
+To understand the settings of this database instance in more details you can check the
+corresponding configuration file: ``bob/pad/face/config/database/aggregated_db.py``.
+
+------------
+
+
.. include:: links.rst
+
diff --git a/doc/img/ROC_iqm_svm_msu_mfsd.pdf b/doc/img/ROC_iqm_svm_msu_mfsd.pdf
index 740123c376d98fdee99f260e5afa59effe258c36..dd4e80931a21e166f6282bb400eff441fdec9949 100644
Binary files a/doc/img/ROC_iqm_svm_msu_mfsd.pdf and b/doc/img/ROC_iqm_svm_msu_mfsd.pdf differ
diff --git a/doc/img/ROC_iqm_svm_replay_attack.pdf b/doc/img/ROC_iqm_svm_replay_attack.pdf
index a4524065a5d3f1e41e547ae51f63859db6c505d9..9da9c0f5ce51f260a2612c2bc6e60bfb9f7cf1fe 100644
Binary files a/doc/img/ROC_iqm_svm_replay_attack.pdf and b/doc/img/ROC_iqm_svm_replay_attack.pdf differ
diff --git a/doc/img/ROC_iqm_svm_replay_mobile.pdf b/doc/img/ROC_iqm_svm_replay_mobile.pdf
index 57b62a2f8a85ad85301c7ac7b5ce127e0d489e29..b57b3a042c648fc601bf79a9d32bf2143f1c3e07 100644
Binary files a/doc/img/ROC_iqm_svm_replay_mobile.pdf and b/doc/img/ROC_iqm_svm_replay_mobile.pdf differ
diff --git a/doc/installation.rst b/doc/installation.rst
index 504281c7491a85b880760b82dcfd635b4ebe7a9f..52f756617690c0ce2db3b482dcb13f422ef63e72 100644
--- a/doc/installation.rst
+++ b/doc/installation.rst
@@ -57,8 +57,10 @@ to run the baselines.
The current system readily supports the following freely available datasets:
-* ``replay-attack``: `replayattack`_
-
+* `REPLAYATTACK`_
+* `REPLAY-MOBILE`_
+* `MSU MFSD`_
+* ``Aggregated DB``
After downloading the databases, annotate the base directories in which they
are installed. Then, follow the instructions in
diff --git a/doc/resources.rst b/doc/resources.rst
index 9edada2e3441f26eedb7e24e27074caa51cd7715..2407852e7ffe3777d74e71c60e146f8fef74736d 100644
--- a/doc/resources.rst
+++ b/doc/resources.rst
@@ -9,7 +9,6 @@
This section contains a listing of all ready-to-use resources you can find in
this package.
-
---------------------------------
@@ -49,6 +48,14 @@ MSU MFSD Database
:members:
+.. _bob.pad.face.resources.databases.aggregated_db:
+
+Aggregated Database
+================================================================================
+
+.. automodule:: bob.pad.face.config.database.aggregated_db
+ :members:
+
---------------------------------
@@ -91,3 +98,33 @@ Frame differences based features (motion analysis) + SVM for REPLAY-ATTACK
.. automodule:: bob.pad.face.config.frame_diff_svm
:members:
+
+
+.. _bob.pad.face.resources.face_pad.lbp_svm_aggregated_db:
+
+LBP features of facial region + SVM for Aggregated Database
+===================================================================================
+
+.. automodule:: bob.pad.face.config.lbp_svm_aggregated_db
+ :members:
+
+
+.. _bob.pad.face.resources.face_pad.qm_svm_aggregated_db:
+
+Image Quality Measures as features of facial region + SVM for Aggregated Database
+===================================================================================
+
+.. automodule:: bob.pad.face.config.qm_svm_aggregated_db
+ :members:
+
+
+.. _bob.pad.face.resources.face_pad.frame_diff_svm_aggregated_db:
+
+Frame differences based features (motion analysis) + SVM for Aggregated Database
+===================================================================================
+
+.. automodule:: bob.pad.face.config.frame_diff_svm_aggregated_db
+ :members:
+
+
+
diff --git a/setup.py b/setup.py
index eb04789aa236b9abd403cc422ef6a532df15c8d8..e0ac7ee6cbf6fbe56e0b6a9754bded38486ae3db 100644
--- a/setup.py
+++ b/setup.py
@@ -66,6 +66,7 @@ setup(
'replay = bob.pad.face.config.database.replay:database',
'replay-mobile = bob.pad.face.config.database.replay_mobile:database',
'msu-mfsd = bob.pad.face.config.database.msu_mfsd:database',
+ 'aggregated-db = bob.pad.face.config.database.aggregated_db:database',
],
# registered configurations:
@@ -73,8 +74,11 @@ setup(
# baselines:
'lbp-svm = bob.pad.face.config.lbp_svm',
+ 'lbp-svm-aggregated-db = bob.pad.face.config.lbp_svm_aggregated_db',
'qm-svm = bob.pad.face.config.qm_svm',
+ 'qm-svm-aggregated-db = bob.pad.face.config.qm_svm_aggregated_db',
'frame-diff-svm = bob.pad.face.config.frame_diff_svm',
+ 'frame-diff-svm-aggregated-db = bob.pad.face.config.frame_diff_svm_aggregated_db',
],
# registered preprocessors: