def align_face(self, face, image_size=182, margin=44): minsize = 50 # minimum size of face threshold = [0.7, 0.6, 0.6] # three steps's threshold factor = 0.709 # scale factor try: img = face except (IOError, ValueError, IndexError) as e: errorMessage = 'Unable to align image' print(errorMessage) else: if img.ndim < 2: print('Unable to align image') if img.ndim == 2: img = facenet.to_rgb(img) img = img[:, :, 0:3] bounding_boxes, _ = detect_face.detect_face( img, minsize, self.model_align_pnet, self.model_align_rnet, self.model_align_onet, threshold, factor) nrof_faces = bounding_boxes.shape[0] if nrof_faces > 0: det = bounding_boxes[:, 0:4] img_size = np.asarray(img.shape)[0:2] if nrof_faces > 1: 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 = det[index, :] 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') return scaled, bb else: print('Unable to align image') return None, None
def main(args): sleep(random.random()) output_dir = os.path.expanduser(args.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__)) facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv)) dataset = facenet.get_dataset(args.input_dir) print('Creating networks and loading parameters') with tf.Graph().as_default(): gpu_options = tf.GPUOptions( per_process_gpu_memory_fraction=args.gpu_memory_fraction) sess = tf.Session(config=tf.ConfigProto(gpu_options=gpu_options, log_device_placement=False)) with sess.as_default(): pnet, rnet, onet = align.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) with open(bounding_boxes_filename, "w") as text_file: nrof_images_total = 0 nrof_successfully_aligned = 0 if args.random_order: random.shuffle(dataset) for cls in dataset: output_class_dir = os.path.join(output_dir, cls.name) if not os.path.exists(output_class_dir): os.makedirs(output_class_dir) if args.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, _ = align.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 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)) 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') nrof_successfully_aligned += 1 filename_base, file_extension = os.path.splitext( output_filename) if args.detect_multiple_faces: output_filename_n = "{}_{}{}".format( filename_base, i, file_extension) else: output_filename_n = "{}{}".format( filename_base, file_extension) 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)) print('Total number of images: %d' % nrof_images_total) print('Number of successfully aligned images: %d' % nrof_successfully_aligned)
phase_train_placeholder = tf.get_default_graph().get_tensor_by_name( "phase_train:0") embedding_size = embeddings.get_shape()[1] classifier_filename_exp = os.path.expanduser(classifier_filename) with open(classifier_filename_exp, 'rb') as infile: (model, class_names) = pickle.load(infile) while True: last_ret, frame = camera.read() frame = cv2.resize(frame, (0, 0), fx=scale, fy=scale) if img_size is None: img_size = np.asarray(frame.shape)[0:2] if frame.ndim == 2: frame = facenet.to_rgb(frame) frame = frame[:, :, 0:3] bounding_boxes = detect_face_cnn.detect_face(frame) if len(bounding_boxes) > 0: for i in range(len(bounding_boxes)): cropped = None scaled = None scaled_reshape = None bb = [0, 0, 0, 0] emb_array = np.zeros((1, embedding_size)) bb[0] = int(np.maximum(bounding_boxes[i][0], 0)) bb[1] = int(np.maximum(bounding_boxes[i][1], 0)) bb[2] = int(np.minimum(bounding_boxes[i][2], img_size[1]))
def main(args): align = align_dlib.AlignDlib(os.path.expanduser(args.dlib_face_predictor)) landmarkIndices = align_dlib.AlignDlib.OUTER_EYES_AND_NOSE output_dir = os.path.expanduser(args.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__)) facenet.store_revision_info(src_path, output_dir, ' '.join(sys.argv)) dataset = facenet.get_dataset(args.input_dir) random.shuffle(dataset) # Scale the image such that the face fills the frame when cropped to crop_size scale = float(args.face_size) / args.image_size nrof_images_total = 0 nrof_prealigned_images = 0 nrof_successfully_aligned = 0 for cls in dataset: output_class_dir = os.path.join(output_dir, cls.name) if not os.path.exists(output_class_dir): os.makedirs(output_class_dir) 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') 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: img = facenet.to_rgb(img) if args.use_center_crop: scaled = misc.imresize(img, args.prealigned_scale, interp='bilinear') sz1 = scaled.shape[1]/2 sz2 = args.image_size/2 aligned = scaled[int(sz1-sz2):int(sz1+sz2),int(sz1-sz2):int(sz1+sz2),:] else: aligned = align.align(args.image_size, img, landmarkIndices=landmarkIndices, skipMulti=False, scale=scale) if aligned is not None: print(image_path) nrof_successfully_aligned += 1 misc.imsave(output_filename, aligned) elif args.prealigned_dir: # Face detection failed. Use center crop from pre-aligned dataset class_name = os.path.split(output_class_dir)[1] image_path_without_ext = os.path.join(os.path.expanduser(args.prealigned_dir), class_name, filename) # Find the extension of the image exts = ('jpg', 'png') for ext in exts: temp_path = image_path_without_ext + '.' + ext image_path = '' if os.path.exists(temp_path): image_path = temp_path break try: img = misc.imread(image_path) except (IOError, ValueError, IndexError) as e: errorMessage = '{}: {}'.format(image_path, e) print(errorMessage) else: scaled = misc.imresize(img, args.prealigned_scale, interp='bilinear') sz1 = scaled.shape[1]/2 sz2 = args.image_size/2 cropped = scaled[(sz1-sz2):(sz1+sz2),(sz1-sz2):(sz1+sz2),:] print(image_path) nrof_prealigned_images += 1 misc.imsave(output_filename, cropped) else: print('Unable to align "%s"' % image_path) print('Total number of images: %d' % nrof_images_total) print('Number of successfully aligned images: %d' % nrof_successfully_aligned) print('Number of pre-aligned images: %d' % nrof_prealigned_images)