def align_face(img,pnet, rnet, onet):
minsize = 20 # minimum size of face
threshold = [ 0.6, 0.7, 0.7 ] # three steps's threshold
factor = 0.709 # scale factor
print("before img.size == 0")
if img.size == 0:
print("empty array")
return False,img,[0,0,0,0]
if img.ndim<2:
print('Unable to align')
if img.ndim == 2:
img = to_rgb(img)
img = img[:,:,0:3]
bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces==0:
return False,img,[0,0,0,0]
else:
det = bounding_boxes[:,0:4]
det_arr = []
img_size = np.asarray(img.shape)[0:2]
if nrof_faces>1:
if args.detect_multiple_faces:
for i in range(nrof_faces):
det_arr.append(np.squeeze(det[i]))
else:
bounding_box_size = (det[:,2]-det[:,0])*(det[:,3]-det[:,1])
img_center = img_size / 2
offsets = np.vstack([ (det[:,0]+det[:,2])/2-img_center[1], (det[:,1]+det[:,3])/2-img_center[0] ])
offset_dist_squared = np.sum(np.power(offsets,2.0),0)
index = np.argmax(bounding_box_size-offset_dist_squared*2.0) # some extra weight on the centering
det_arr.append(det[index,:])
else:
det_arr.append(np.squeeze(det))
if len(det_arr)>0:
faces = []
bboxes = []
for i, det in enumerate(det_arr):
det = np.squeeze(det)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0]-args.margin/2, 0)
bb[1] = np.maximum(det[1]-args.margin/2, 0)
bb[2] = np.minimum(det[2]+args.margin/2, img_size[1])
bb[3] = np.minimum(det[3]+args.margin/2, img_size[0])
cropped = img[bb[1]:bb[3],bb[0]:bb[2],:]
scaled = misc.imresize(cropped, (args.image_size, args.image_size), interp='bilinear')
misc.imsave("cropped.png", scaled)
faces.append(scaled)
bboxes.append(bb)
print("leaving align face")
return True,faces,bboxes
def get_faces_live(img, pnet, rnet, onet, image_size):
"""Detects multiple human faces live from web camera frame.
Args:
img: web camera frame.
pnet: proposal net, first stage of the MTCNN face detection.
rnet: refinement net, second stage of the MTCNN face detection.
onet: output net, third stage of the MTCNN face detection.
image_size: (int) required square image size.
Returns:
faces: List containing the cropped human faces.
rects: List containing the rectangle coordinates to be drawn around each human face.
"""
# Default constants from the FaceNet repository implementation of the MTCNN
minsize = 20
threshold = [0.6, 0.7, 0.7]
factor = 0.709
margin = 44
input_image_size = image_size
faces = []
rects = []
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face(img=img,
minsize=minsize,
pnet=pnet,
rnet=rnet,
onet=onet,
threshold=threshold,
factor=factor)
# If human face(s) is/are detected:
if not len(bounding_boxes) == 0:
for face in bounding_boxes:
if face[4] > 0.50:
det = np.squeeze(face[0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
resized = imresize(arr=cropped,
size=(input_image_size, input_image_size),
mode='RGB')
faces.append(resized)
rects.append([bb[0], bb[1], bb[2], bb[3]])
return faces, rects
def get_face(img, pnet, rnet, onet, image_size):
"""Crops an image containing a single human face from the input image if it exists; using a Multi-Task Cascading
Convolutional neural network, then resizes the image to the required image size: default = (160 x 160 x 3).
If no face is detected, it returns a null value.
Args:
img: (numpy array) image file
pnet: proposal net, first stage of the MTCNN face detection
rnet: refinement net, second stage of the MTCNN face detection
onet: output net, third stage of the MTCNN face detection
image_size: (int) required square image size
Returns:
face_img: an image containing a face of image_size: default = (160 x 160 x 3)
if no human face is detected a None value is returned instead.
"""
# Default constants from the FaceNet repository implementation of the MTCNN
minsize = 20
threshold = [0.6, 0.7, 0.7]
factor = 0.709
margin = 44
input_image_size = image_size
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face(img=img,
minsize=minsize,
pnet=pnet,
rnet=rnet,
onet=onet,
threshold=threshold,
factor=factor)
if not len(bounding_boxes) == 0:
for face in bounding_boxes:
det = np.squeeze(face[0:4])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
face_img = imresize(arr=cropped,
size=(input_image_size, input_image_size),
mode='RGB')
return face_img
else:
return None
def main(input_dir, output_dir, image_size, margin, random_order,
gpu_memory_fraction, detect_multiple_faces):
sleep(random.random())
output_dir = os.path.expanduser(output_dir)
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# Store some git revision info in a text file in the log directory
#src_path,_ = os.path.split(os.path.realpath(__file__))
src_path = input_dir
facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv))
dataset = facenet.get_dataset(input_dir)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(
per_process_gpu_memory_fraction=gpu_memory_fraction)
sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options,
log_device_placement=False))
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
#bounding_boxes_filename = os.path.join(output_dir, 'bounding_boxes_%05d.txt' % random_key)
if 1:
nrof_images_total = 0
nrof_successfully_aligned = 0
if random_order:
random.shuffle(dataset)
for cls in dataset:
print("cls.name", cls.name)
output_class_dir = os.path.join(output_dir, cls.name)
if not os.path.exists(output_class_dir):
os.makedirs(output_class_dir)
if random_order:
random.shuffle(cls.image_paths)
for image_path in cls.image_paths:
nrof_images_total += 1
filename = os.path.splitext(os.path.split(image_path)[1])[0]
output_filename = os.path.join(output_class_dir,
filename + '.png')
print(image_path)
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
print(errorMessage)
else:
if img.ndim < 2:
print('Unable to align "%s"' % image_path)
#text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2:
img = facenet.to_rgb(img)
img = img[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
det_arr = []
img_size = np.asarray(img.shape)[0:2]
if nrof_faces > 1:
if detect_multiple_faces:
for i in range(nrof_faces):
det_arr.append(np.squeeze(det[i]))
else:
bounding_box_size = (
det[:, 2] - det[:, 0]) * (det[:, 3] -
det[:, 1])
img_center = img_size / 2
offsets = np.vstack([
(det[:, 0] + det[:, 2]) / 2 -
img_center[1],
(det[:, 1] + det[:, 3]) / 2 -
img_center[0]
])
offset_dist_squared = np.sum(
np.power(offsets, 2.0), 0)
index = np.argmax(
bounding_box_size -
offset_dist_squared * 2.0
) # some extra weight on the centering
det_arr.append(det[index, :])
else:
det_arr.append(np.squeeze(det))
for i, det in enumerate(det_arr):
det = np.squeeze(det)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - margin / 2, 0)
bb[1] = np.maximum(det[1] - margin / 2, 0)
bb[2] = np.minimum(det[2] + margin / 2,
img_size[1])
bb[3] = np.minimum(det[3] + margin / 2,
img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(
cropped, (image_size, image_size),
interp='bilinear')
nrof_successfully_aligned += 1
output_filename_n = "{}_{}.{}".format(
output_filename.split('.')[0], i,
output_filename.split('.')[-1])
misc.imsave(output_filename_n, scaled)
#text_file.write('%s %d %d %d %d\n' % (output_filename_n, bb[0], bb[1], bb[2], bb[3]))
else:
print('Unable to align "%s"' % image_path)
#text_file.write('%s\n' % (output_filename))
os.remove(os.path.join(settings.BASE_DIR,
f'media/datab/revision_info.txt'))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' %
nrof_successfully_aligned)