Created configs for all channels of BATL and lbp_lr

bob/pad/face/config/batl_db.py

@@ -14,8 +14,10 @@ ORIGINAL_EXTENSION = ".h5"  # extension of the data files
 
 ANNOTATIONS_TEMP_DIR = "/idiap/temp/onikisins/project/ODIN/experiment_data/pad_experiments_using_bob_py36/batl_db/annotations/"
 
+PROTOCOL = 'nowig-color-50'
+
 database = BatlPadDatabase(
-    protocol='nowig-color-5',
+    protocol=PROTOCOL,
     original_directory=ORIGINAL_DIRECTORY,
     original_extension=ORIGINAL_EXTENSION,
     annotations_temp_dir=ANNOTATIONS_TEMP_DIR,
@@ -36,7 +38,7 @@ You must make sure to create ``${HOME}/.bob_bio_databases.txt`` file setting thi
 value to the places where you actually installed the BATL database.
 """
 
-protocol = 'nowig-color-5'
+protocol = PROTOCOL
 """
 You may modify this at runtime by specifying the option ``--protocol`` on the
 command-line of ``spoof.py`` or using the keyword ``protocol`` on a

bob/pad/face/config/batl_db_depth.py

+#!/usr/bin/env python
+"""
+BATL Db is a database for face PAD experiments.
+"""
+
+from bob.pad.face.database import BatlPadDatabase
+
+# 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_BATL_DB_DIRECTORY]"
+"""Value of ``~/.bob_bio_databases.txt`` for this database"""
+
+ORIGINAL_EXTENSION = ".h5"  # extension of the data files
+
+ANNOTATIONS_TEMP_DIR = "/idiap/temp/onikisins/project/ODIN/experiment_data/pad_experiments_using_bob_py36/batl_db/annotations/"
+
+PROTOCOL = 'nowig-depth-50'
+
+database = BatlPadDatabase(
+    protocol=PROTOCOL,
+    original_directory=ORIGINAL_DIRECTORY,
+    original_extension=ORIGINAL_EXTENSION,
+    annotations_temp_dir=ANNOTATIONS_TEMP_DIR,
+    landmark_detect_method="mtcnn",
+    training_depends_on_protocol=True,
+)
+"""The :py:class:`bob.pad.base.database.BatlPadDatabase` derivative with BATL 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 ``[BatlPadDatabase]``.
+You must make sure to create ``${HOME}/.bob_bio_databases.txt`` file setting this
+value to the places where you actually installed the BATL database.
+"""
+
+protocol = PROTOCOL
+"""
+You may modify this at runtime by specifying the option ``--protocol`` on the
+command-line of ``spoof.py`` or using the keyword ``protocol`` on a
+configuration file that is loaded **after** this configuration resource.
+"""
+
+groups = ["train", "dev", "eval"]
+"""The default groups to use for reproducing the baselines.
+
+You may modify this at runtime by specifying the option ``--groups`` on the
+command-line of ``spoof.py`` or using the keyword ``groups`` on a
+configuration file that is loaded **after** this configuration resource.
+"""

bob/pad/face/config/batl_db_infrared.py

+#!/usr/bin/env python
+"""
+BATL Db is a database for face PAD experiments.
+"""
+
+from bob.pad.face.database import BatlPadDatabase
+
+# 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_BATL_DB_DIRECTORY]"
+"""Value of ``~/.bob_bio_databases.txt`` for this database"""
+
+ORIGINAL_EXTENSION = ".h5"  # extension of the data files
+
+ANNOTATIONS_TEMP_DIR = "/idiap/temp/onikisins/project/ODIN/experiment_data/pad_experiments_using_bob_py36/batl_db/annotations/"
+
+PROTOCOL = 'nowig-infrared-50'
+
+database = BatlPadDatabase(
+    protocol=PROTOCOL,
+    original_directory=ORIGINAL_DIRECTORY,
+    original_extension=ORIGINAL_EXTENSION,
+    annotations_temp_dir=ANNOTATIONS_TEMP_DIR,
+    landmark_detect_method="mtcnn",
+    training_depends_on_protocol=True,
+)
+"""The :py:class:`bob.pad.base.database.BatlPadDatabase` derivative with BATL 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 ``[BatlPadDatabase]``.
+You must make sure to create ``${HOME}/.bob_bio_databases.txt`` file setting this
+value to the places where you actually installed the BATL database.
+"""
+
+protocol = PROTOCOL
+"""
+You may modify this at runtime by specifying the option ``--protocol`` on the
+command-line of ``spoof.py`` or using the keyword ``protocol`` on a
+configuration file that is loaded **after** this configuration resource.
+"""
+
+groups = ["train", "dev", "eval"]
+"""The default groups to use for reproducing the baselines.
+
+You may modify this at runtime by specifying the option ``--groups`` on the
+command-line of ``spoof.py`` or using the keyword ``groups`` on a
+configuration file that is loaded **after** this configuration resource.
+"""

bob/pad/face/config/batl_db_thermal.py

+#!/usr/bin/env python
+"""
+BATL Db is a database for face PAD experiments.
+"""
+
+from bob.pad.face.database import BatlPadDatabase
+
+# 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_BATL_DB_DIRECTORY]"
+"""Value of ``~/.bob_bio_databases.txt`` for this database"""
+
+ORIGINAL_EXTENSION = ".h5"  # extension of the data files
+
+ANNOTATIONS_TEMP_DIR = "/idiap/temp/onikisins/project/ODIN/experiment_data/pad_experiments_using_bob_py36/batl_db/annotations/"
+
+PROTOCOL = 'nowig-thermal-50'
+
+database = BatlPadDatabase(
+    protocol=PROTOCOL,
+    original_directory=ORIGINAL_DIRECTORY,
+    original_extension=ORIGINAL_EXTENSION,
+    annotations_temp_dir=ANNOTATIONS_TEMP_DIR,
+    landmark_detect_method="mtcnn",
+    training_depends_on_protocol=True,
+)
+"""The :py:class:`bob.pad.base.database.BatlPadDatabase` derivative with BATL 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 ``[BatlPadDatabase]``.
+You must make sure to create ``${HOME}/.bob_bio_databases.txt`` file setting this
+value to the places where you actually installed the BATL database.
+"""
+
+protocol = PROTOCOL
+"""
+You may modify this at runtime by specifying the option ``--protocol`` on the
+command-line of ``spoof.py`` or using the keyword ``protocol`` on a
+configuration file that is loaded **after** this configuration resource.
+"""
+
+groups = ["train", "dev", "eval"]
+"""The default groups to use for reproducing the baselines.
+
+You may modify this at runtime by specifying the option ``--groups`` on the
+command-line of ``spoof.py`` or using the keyword ``groups`` on a
+configuration file that is loaded **after** this configuration resource.
+"""

bob/pad/face/config/lbp_lr_batl_D_T_IR.py

+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+"""
+This file contains configurations to run LBP and SVM based face PAD baseline.
+The settings are tuned for the Replay-attack 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'
+"""
+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 FaceCropAlign
+
+from bob.bio.video.preprocessor import Wrapper
+
+from bob.bio.video.utils import FrameSelector
+
+from ..preprocessor.FaceCropAlign import auto_norm_image as _norm_func
+
+FACE_SIZE = 64 # The size of the resulting face
+RGB_OUTPUT_FLAG = False # Gray-scale output
+USE_FACE_ALIGNMENT = False # use annotations
+MAX_IMAGE_SIZE = None # no limiting here
+FACE_DETECTION_METHOD = None # use annotations
+MIN_FACE_SIZE = 50 # skip small faces
+NORMALIZATION_FUNCTION = _norm_func
+NORMALIZATION_FUNCTION_KWARGS = {}
+NORMALIZATION_FUNCTION_KWARGS = {'n_sigma':3.0, 'norm_method':'MAD'}
+
+_image_preprocessor = FaceCropAlign(face_size = FACE_SIZE,
+                                   rgb_output_flag = RGB_OUTPUT_FLAG,
+                                   use_face_alignment = USE_FACE_ALIGNMENT,
+                                   max_image_size = MAX_IMAGE_SIZE,
+                                   face_detection_method = FACE_DETECTION_METHOD,
+                                   min_face_size = MIN_FACE_SIZE,
+                                   normalization_function = NORMALIZATION_FUNCTION,
+                                   normalization_function_kwargs = NORMALIZATION_FUNCTION_KWARGS)
+
+_frame_selector = FrameSelector(selection_style = "all")
+
+preprocessor = Wrapper(preprocessor = _image_preprocessor,
+                       frame_selector = _frame_selector)
+"""
+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 ``FACE_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 ``FACE_DETECTION_METHOD = None``.
+"""
+
+#=======================================================================================
+# define extractor:
+
+from ..extractor import LBPHistogram
+
+from bob.bio.video.extractor import Wrapper
+
+LBPTYPE = 'uniform'
+ELBPTYPE = 'regular'
+RAD = 1
+NEIGHBORS = 8
+CIRC = False
+DTYPE = None
+
+extractor = Wrapper(LBPHistogram(
+    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 bob.pad.base.algorithm import LogRegr
+
+C = 1.  # The regularization parameter for the LR classifier
+FRAME_LEVEL_SCORES_FLAG = True  # Return one score per frame
+
+algorithm = LogRegr(
+    C=C, frame_level_scores_flag=FRAME_LEVEL_SCORES_FLAG)
+"""
+The Logistic Regression 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 sub-sampling of training data is not used here, sub-sampling flags have default ``False``
+values.
+"""

bob/pad/face/database/batl.py

@@ -64,6 +64,8 @@ class BatlPadFile(PadFile):
 
     def load(self, directory=None, extension='.hdf5', frame_selector=FrameSelector(selection_style='all')):
 
+        print (self.f.path)
+
         data = self.f.load(directory=directory,
                            extension=extension,
                            modality=self.stream_type, # TODO: this parameter is currently missing in bob.db.batl, add it there

bob/pad/face/preprocessor/FaceCropAlign.py

@@ -20,6 +20,63 @@ import bob.ip.base
 import importlib
 
 
+# ==============================================================================
+def auto_norm_image(data, annotations, n_sigma=3.0, norm_method='MAD'):
+    """
+    Normalizes a single channel image to range 0-255, using the data distribution
+    Expects single channel images
+
+    **method: Gaussian , MAD, MINMAX
+    **n_sigma: The range which is normalized
+
+    """
+
+    face = data[annotations['topleft'][0]:annotations['bottomright'][0],
+                 annotations['topleft'][1]:annotations['bottomright'][1]]
+
+    face = face.astype('float')
+    data = data.astype('float')
+
+    assert(len(data.shape)==2)
+
+    face_c = np.ma.array(face).compressed()
+    # Avoiding zeros from flat field in thermal and holes in depth
+
+    face_c=face_c[face_c>1.0]
+
+    if norm_method=='STD':
+
+        mu = np.mean(face_c)
+        std = np.std(face_c)
+
+        data_n=((data-mu+n_sigma*std)/(2.0*n_sigma*std))*255.0
+
+
+    if norm_method=='MAD':
+
+        med = np.median(face_c)
+        mad = np.median(np.abs(face_c - med))
+
+        data_n = ((data-med+n_sigma*mad)/(2.0*n_sigma*mad))*255.0
+
+
+    if norm_method=='MINMAX':
+
+        t_min = np.min(face_c)
+        t_max = np.max(face_c)
+
+        data_n = ((data-t_min)/(t_max-t_min))*255.0
+
+
+    # Clamping to 0-255
+    data_n=np.maximum(data_n,0)
+    data_n=np.minimum(data_n,255)
+
+    data_n = data_n.astype('uint8')
+
+    return data_n
+
+
 # ==============================================================================
 def get_eye_pos(lm):
     """
@@ -355,14 +412,18 @@ class FaceCropAlign(Preprocessor):
                  use_face_alignment,
                  max_image_size=None,
                  face_detection_method=None,
-                 min_face_size=None):
+                 min_face_size=None,
+                 normalization_function=None,
+                 normalization_function_kwargs = None):
 
         Preprocessor.__init__(self, face_size=face_size,
                               rgb_output_flag=rgb_output_flag,
                               use_face_alignment=use_face_alignment,
                               max_image_size=max_image_size,
                               face_detection_method=face_detection_method,
-                              min_face_size=min_face_size)
+                              min_face_size=min_face_size,
+                              normalization_function=normalization_function,
+                              normalization_function_kwargs = normalization_function_kwargs)
 
         self.face_size = face_size
         self.rgb_output_flag = rgb_output_flag
@@ -371,6 +432,8 @@ class FaceCropAlign(Preprocessor):
         self.max_image_size = max_image_size
         self.face_detection_method = face_detection_method
         self.min_face_size = min_face_size
+        self.normalization_function = normalization_function
+        self.normalization_function_kwargs = normalization_function_kwargs
 
         self.supported_face_detection_method = ["dlib", "mtcnn"]
 
@@ -465,6 +528,10 @@ class FaceCropAlign(Preprocessor):
 
                 return None
 
+        if self.normalization_function is not None:
+
+            image = self.normalization_function(image, annotations, **self.normalization_function_kwargs)
+
         norm_face_image = normalize_image_size(image=image,
                                                annotations=annotations,
                                                face_size=self.face_size,

setup.py

@@ -64,6 +64,9 @@ setup(
             'aggregated-db = bob.pad.face.config.aggregated_db:database',
             'mifs = bob.pad.face.config.mifs:database',
             'batl-db = bob.pad.face.config.batl_db:database',
+            'batl-db-infrared = bob.pad.face.config.batl_db_infrared:database',
+            'batl-db-depth = bob.pad.face.config.batl_db_depth:database',
+            'batl-db-thermal = bob.pad.face.config.batl_db_thermal:database',
         ],
 
         # registered configurations:
@@ -75,6 +78,9 @@ setup(
             'aggregated-db = bob.pad.face.config.aggregated_db',
             'mifs = bob.pad.face.config.mifs',
             'batl-db = bob.pad.face.config.batl_db',
+            'batl-db-infrared = bob.pad.face.config.batl_db_infrared',
+            'batl-db-depth = bob.pad.face.config.batl_db_depth',
+            'batl-db-thermal = bob.pad.face.config.batl_db_thermal',
 
             # baselines using SVM:
             'lbp-svm = bob.pad.face.config.lbp_svm',
@@ -90,6 +96,7 @@ setup(
 
             # baselines using LR:
             'qm-lr = bob.pad.face.config.qm_lr',  # this pipe-line can be used both for individual and Aggregated databases.
+            'lbp-lr-batl-D-T-IR = bob.pad.face.config.lbp_lr_batl_D_T_IR',  # this pipe-line can be used both for BATL databases, Depth, Thermal and Infrared channels.
 
             # baselines using GMM:
             'qm-one-class-gmm = bob.pad.face.config.qm_one_class_gmm',  # this pipe-line can be used both for individual and Aggregated databases.