diff --git a/bob/pad/face/config/preprocessor/video_face_crop.py b/bob/pad/face/config/preprocessor/video_face_crop.py
index ad7f963b0fdb8f92319c02ad8210c899a44dbccc..72156454a24fed51f8bce0102511f49d5e3f2175 100644
--- a/bob/pad/face/config/preprocessor/video_face_crop.py
+++ b/bob/pad/face/config/preprocessor/video_face_crop.py
@@ -17,15 +17,50 @@ 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
DETECT_FACES_FLAG = True # find annotations locally replacing the database annotations
+FACE_DETECTION_METHOD = "dlib"
+
+rgb_face_detector_dlib = 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,
+ detect_faces_flag = DETECT_FACES_FLAG,
+ face_detection_method = FACE_DETECTION_METHOD)
+
+
+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
+DETECT_FACES_FLAG = True # find annotations locally replacing the database annotations
+FACE_DETECTION_METHOD = "mtcnn"
+
+rgb_face_detector_mtcnn = 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,
+ detect_faces_flag = DETECT_FACES_FLAG,
+ face_detection_method = FACE_DETECTION_METHOD)
+
+
+
+
+
-preprocessor_rgb_face_detect = 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,
- detect_faces_flag = DETECT_FACES_FLAG)
diff --git a/bob/pad/face/preprocessor/VideoFaceCrop.py b/bob/pad/face/preprocessor/VideoFaceCrop.py
index 756bac3ef01fadee56feb89939c1689f6d44ab2d..7689fed94073c15cece1e6c8f7614c12ba86117f 100644
--- a/bob/pad/face/preprocessor/VideoFaceCrop.py
+++ b/bob/pad/face/preprocessor/VideoFaceCrop.py
@@ -84,6 +84,10 @@ class VideoFaceCrop(Preprocessor, object):
cropping.
Default: ``False``.
+ ``face_detection_method`` : :py:class:`str`
+ A package to be used for face detection. Available options: "dlib" and
+ "mtcnn".
+
``kwargs``
Remaining keyword parameters passed to the Base constructor, such as ``color_channel`` or ``dtype``.
"""
@@ -101,6 +105,7 @@ class VideoFaceCrop(Preprocessor, object):
use_local_cropper_flag = False,
rgb_output_flag = False,
detect_faces_flag = False,
+ face_detection_method = "dlib",
**kwargs):
super(VideoFaceCrop, self).__init__(cropped_image_size = cropped_image_size,
@@ -114,6 +119,7 @@ class VideoFaceCrop(Preprocessor, object):
use_local_cropper_flag = use_local_cropper_flag,
rgb_output_flag = rgb_output_flag,
detect_faces_flag = detect_faces_flag,
+ face_detection_method = face_detection_method,
**kwargs)
self.cropped_image_size = cropped_image_size
@@ -127,6 +133,7 @@ class VideoFaceCrop(Preprocessor, object):
self.use_local_cropper_flag = use_local_cropper_flag
self.rgb_output_flag = rgb_output_flag
self.detect_faces_flag = detect_faces_flag
+ self.face_detection_method = face_detection_method
# Save also the data stored in the kwargs:
for (k, v) in kwargs.items():
@@ -276,15 +283,7 @@ class VideoFaceCrop(Preprocessor, object):
if self.detect_faces_flag:
- annotations_detected = detect_faces_in_video(frames)
-
- if not annotations_detected:
-
- annotations = annotations # if now annotations detected use DB annotations
-
- else:
-
- annotations = annotations_detected # if face was detected overwrite DB annotations
+ annotations = detect_faces_in_video(frames, self.face_detection_method)
if len(frames) != len(annotations): # if some annotations are missing
@@ -315,7 +314,9 @@ class VideoFaceCrop(Preprocessor, object):
name of the file.
"""
- self.video_preprocessor.write_data(frames, file_name)
+ if frames: # save file if FrameContainer is not empty, otherwise do nothing.
+
+ self.video_preprocessor.write_data(frames, file_name)
#==========================================================================
diff --git a/bob/pad/face/utils/face_detection_utils.py b/bob/pad/face/utils/face_detection_utils.py
index c088f3ba391a5a885e453f8d5ee727b14569d1e3..37eeac609441d6bc4863db42d66d6a4815cde1ab 100644
--- a/bob/pad/face/utils/face_detection_utils.py
+++ b/bob/pad/face/utils/face_detection_utils.py
@@ -9,9 +9,10 @@ This file contains face detection utils.
import bob.ip.dlib # for face detection functionality
+import bob.ip.mtcnn
#==============================================================================
-def detect_face_in_image(image):
+def detect_face_in_image(image, method):
"""
This function detects a face in the input image.
@@ -20,6 +21,10 @@ def detect_face_in_image(image):
``image`` : 3D :py:class:`numpy.ndarray`
A color image to detect the face in.
+ ``method`` : :py:class:`str`
+ A package to be used for face detection. Available options: "dlib" and
+ "mtcnn".
+
**Returns:**
``annotations`` : :py:class:`dict`
@@ -28,11 +33,17 @@ def detect_face_in_image(image):
If no annotations found an empty dictionary is returned.
"""
- data = bob.ip.dlib.FaceDetector().detect_single_face(image)
+ if method == "dlib":
+
+ data = bob.ip.dlib.FaceDetector().detect_single_face(image)
+
+ if method == "mtcnn":
+
+ data = bob.ip.mtcnn.FaceDetector().detect_single_face(image)
annotations = {}
- if data is not None:
+ if ( data is not None ) and ( not all([x is None for x in data]) ):
bounding_box = data[0]
@@ -44,7 +55,7 @@ def detect_face_in_image(image):
#==============================================================================
-def detect_faces_in_video(frame_container):
+def detect_faces_in_video(frame_container, method):
"""
This function detects a face in each farme of the input video.
@@ -53,6 +64,10 @@ def detect_faces_in_video(frame_container):
``frame_container`` : FrameContainer
FrameContainer containing the frames data.
+ ``method`` : :py:class:`str`
+ A package to be used for face detection. Available options: "dlib" and
+ "mtcnn".
+
**Returns:**
``annotations`` : :py:class:`dict`
@@ -69,7 +84,7 @@ def detect_faces_in_video(frame_container):
image = frame[1]
- frame_annotations = detect_face_in_image(image)
+ frame_annotations = detect_face_in_image(image, method)
if frame_annotations:
diff --git a/setup.py b/setup.py
index 0a0578e9d4355fcdc12bd181768fb43c0c237ffe..5994338a00da26f58f9e9dc5cafaca19978ba57e 100644
--- a/setup.py
+++ b/setup.py
@@ -103,7 +103,8 @@ setup(
# registered preprocessors:
'bob.pad.preprocessor': [
'empty-preprocessor = bob.pad.face.config.preprocessor.filename:empty_preprocessor', # no preprocessing
- 'preprocessor-rgb-face-detect = bob.pad.face.config.preprocessor.video_face_crop:preprocessor_rgb_face_detect', # detect faces locally replacing database annotations
+ 'rgb-face-detect-dlib = bob.pad.face.config.preprocessor.video_face_crop:rgb_face_detector_dlib', # detect faces locally replacing database annotations
+ 'rgb-face-detect-mtcnn = bob.pad.face.config.preprocessor.video_face_crop:rgb_face_detector_mtcnn', # detect faces locally replacing database annotations
],
# registered extractors: