Added a local face detection option to the VideoFaceCrop class

bob/pad/face/config/preprocessor/video_face_crop.py

+#!/usr/bin/env python2
+# -*- coding: utf-8 -*-
+
+from bob.pad.face.preprocessor import VideoFaceCrop
+
+#=======================================================================================
+# Define instances here:
+
+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
+
+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)

bob/pad/face/preprocessor/VideoFaceCrop.py

@@ -18,6 +18,8 @@ import numpy as np
 
 from bob.pad.face.preprocessor.ImageFaceCrop import ImageFaceCrop
 
+from ..utils.face_detection_utils import detect_faces_in_video
+
 #==============================================================================
 # Main body:
 
@@ -76,6 +78,12 @@ class VideoFaceCrop(Preprocessor, object):
         returned. This flag is only valid when ``use_local_cropper_flag = True``.
         Default: ``False``.
 
+    ``detect_faces_flag`` : :py:class:`bool`
+        If set to ``True`` the facial annotations will be generated using
+        face detection. Otherwise, annotations of the database are used for
+        cropping.
+        Default: ``False``.
+
     ``kwargs``
         Remaining keyword parameters passed to the Base constructor, such as ``color_channel`` or ``dtype``.
     """
@@ -92,6 +100,7 @@ class VideoFaceCrop(Preprocessor, object):
                  min_face_size = 50,
                  use_local_cropper_flag = False,
                  rgb_output_flag = False,
+                 detect_faces_flag = False,
                  **kwargs):
 
         super(VideoFaceCrop, self).__init__(cropped_image_size = cropped_image_size,
@@ -104,6 +113,7 @@ class VideoFaceCrop(Preprocessor, object):
                                             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,
                                             **kwargs)
 
         self.cropped_image_size = cropped_image_size
@@ -116,6 +126,7 @@ class VideoFaceCrop(Preprocessor, object):
         self.min_face_size = min_face_size
         self.use_local_cropper_flag = use_local_cropper_flag
         self.rgb_output_flag = rgb_output_flag
+        self.detect_faces_flag = detect_faces_flag
 
         # Save also the data stored in the kwargs:
         for (k, v) in kwargs.items():
@@ -263,6 +274,10 @@ class VideoFaceCrop(Preprocessor, object):
             Cropped faces stored in the FrameContainer.
         """
 
+        if self.detect_faces_flag:
+
+            annotations = detect_faces_in_video(frames)
+
         if len(frames) != len(annotations): # if some annotations are missing
 
             ## Select only annotated frames:

bob/pad/face/utils/face_detection_utils.py

+#!/usr/bin/env python
+# vim: set fileencoding=utf-8 :
+
+"""
+This file contains face detection utils.
+"""
+#==============================================================================
+# Import here:
+
+import bob.ip.dlib # for face detection functionality
+
+
+#==============================================================================
+def detect_face_in_image(image):
+    """
+    This function detects a face in the input image.
+
+    **Parameters:**
+
+    ``image`` : 3D :py:class:`numpy.ndarray`
+        A color image to detect the face in.
+
+    **Returns:**
+
+    ``annotations`` : :py:class:`dict`
+        A dictionary containing annotations of the face bounding box.
+        Dictionary must be as follows ``{'topleft': (row, col), 'bottomright': (row, col)}``.
+    """
+
+    bounding_box, _ = bob.ip.dlib.FaceDetector().detect_single_face(image)
+
+    annotations = {}
+
+    if bounding_box is not None:
+
+        annotations['topleft'] = bounding_box.topleft
+
+        annotations['bottomright'] = bounding_box.bottomright
+
+    else:
+
+        annotations['topleft'] = (0, 0)
+
+        annotations['bottomright'] = (0, 0)
+
+    return annotations
+
+
+#==============================================================================
+def detect_faces_in_video(frame_container):
+    """
+    This function detects a face in each farme of the input video.
+
+    **Parameters:**
+
+    ``frame_container`` : FrameContainer
+        FrameContainer containing the frames data.
+
+    **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.
+    """
+
+    annotations = {}
+
+    for idx, frame in enumerate(frame_container):
+
+        image = frame[1]
+
+        frame_annotations = detect_face_in_image(image)
+
+        annotations[str(idx)] = frame_annotations
+
+    return annotations
+
+
+
+
+
+
+
+
+

setup.py

@@ -103,6 +103,7 @@ 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
             ],
 
         # registered extractors: