def detect(self,image_path):
aligned = []
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
errorMessage = '{}: {}'.format(image_path, e)
logging.info(errorMessage)
else:
if img.ndim < 2:
logging.info('Unable to align "%s"' % image_path)
return []
if img.ndim == 2:
img = facenet.to_rgb(img)
img = img[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(img, self.minsize, self.pnet, self.rnet, self.onet, self.threshold, self.factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det_all = bounding_boxes[:, 0:4]
img_size = np.asarray(img.shape)[0:2]
for boxindex in range(nrof_faces):
det = np.squeeze(det_all[boxindex, :])
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(det[0] - self.margin / 2, 0)
bb[1] = np.maximum(det[1] - self.margin / 2, 0)
bb[2] = np.minimum(det[2] + self.margin / 2, img_size[1])
bb[3] = np.minimum(det[3] + self.margin / 2, img_size[0])
left, top, right, bottom = bb[0], bb[1], bb[2], bb[3]
aligned.append({'x': left,'y':top,'w':right-left,'h':bottom-top})
return aligned
def detect_human_face(img_file):
global g_facenet
minsize = 20 # minimum size of face
threshold = [0.85, 0.85, 0.9] # three steps's threshold
factor = 0.709 # scale factor
img = np.asarray(Image.open(img_file).convert('RGB'))
p, r, o = g_facenet
bounding_boxes, _ = detect_face.detect_face(img, minsize, p, r, o,
threshold, factor)
return len(bounding_boxes) > 0
def load_and_align_data(image_paths, image_size, margin, gpu_memory_fraction):
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
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)
tmp_image_paths = copy.copy(image_paths)
img_list = []
face_area = []
file_list = []
for image in tmp_image_paths:
img = misc.imread(os.path.expanduser(image), mode='RGB')
img_size = np.asarray(img.shape)[0:2]
bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet,
onet, threshold, factor)
if len(bounding_boxes) < 1:
image_paths.remove(image)
print("can't detect face, remove ", image)
continue
for box in bounding_boxes:
det = np.squeeze(box[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], :]
aligned = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
prewhitened = facenet.prewhiten(aligned)
img_list.append(prewhitened)
face_area.append(
Image.open(image).crop((bb[0], bb[1], bb[2], bb[3])))
file_list.append(image)
images = np.stack(img_list)
return images, face_area, file_list
def _detectSingleFace(path, minsize=50, threshold = [0.6, 0.7, 0.7], factor=0.709,pad=5,image_size=160,preprocsingFunc=None):
I=imread(path,mode='RGB')
if preprocsingFunc:
I=preprocsingFunc(I)
box, point=detect_face(I,minsize,pnet_fun,rnet_fun,onet_fun,threshold,factor)
if len(box)==0:
return None
h,w=I.shape[0:2]
x1, y1, x2, y2, acc = box[0]
x1, y1, x2, y2 = max(x1-pad, 0), max(y1-pad, 0), min(x2+pad, w), min(y2+pad, h)
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
cropped=I[y1:y2,x1:x2]
aligned = misc.imresize(cropped, (image_size, image_size), interp='bilinear')
prewhitened=facenet.prewhiten(aligned)
return prewhitened
def main(data_dir, min_size):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.0)
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, npy)
minsize = min_size # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
dataset = face_net.get_dataset(data_dir)
number_sample = 0
number_face_detected = 0
for cls in dataset:
for image_path in cls.image_paths:
number_sample = number_sample + 1
img = cv2.imread(image_path, cv2.IMREAD_UNCHANGED)
if img.ndim == 2:
img = face_net.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):
print('{0} face detected : {1}'.format(
nrof_faces, image_path))
elif (nrof_faces == 2):
print('{0} face detected : {1}'.format(
nrof_faces, image_path))
number_face_detected = number_face_detected + 1
else:
number_face_detected = number_face_detected + 1
print("Finish!!!!")
print('Number face detected {0}'.format(number_face_detected))
if ret == False:
break
# frame = cv2.resize(frame, (650, 650), fx=0.5, fy=0.5) # resize frame (optional)
number_frame += 1
# curTime = time.time() + 1 # calc fps
timeF = frame_interval
if (c % timeF == 0):
find_results = []
if frame.ndim == 2:
frame = face_net.to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
frame, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
# if nrof_faces > 0:
# print('Detected_FaceNum: %d' % nrof_faces)
output_filename = os.path.expanduser(
output_dir + '/{0}_{1}_{2}.jpg'.format(
nrof_faces, number_frame,
datetime.strftime(datetime.now(), '%Y%m%d%H%M%S%f')))
cv2.imwrite(output_filename, frame)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
det_arr = []
img_size = np.asarray(frame.shape)[0:2]
if nrof_faces > 1:
if constants.ALIGN_DETECT_MULTIPLE_FACES:
def main(data_dir, output_dir):
sleep(random.random())
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('argument default'))
dataset = face_net.get_dataset(data_dir)
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants.GPU_MEMORY_FRACTION_DEFAULT)
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 = constants.FACE_REG_MINSIZE # minimum size of face
threshold = constants.ALIGN_THRESHOLD # three steps's threshold
factor = constants.ALIGN_FACTOR # scale factor
# Add a random key to the filename to allow alignment using multiple processes
random_key = np.random.randint(0, high=99999)
face_detected_list = []
nrof_images_total = 0
nrof_successfully_aligned = 0
if constants.ALIGN_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 constants.ALIGN_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')
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
except (IOError, ValueError, IndexError) as e:
error_message = '{}: {}'.format(image_path, e)
print(error_message)
else:
if img.ndim < 2:
print('Unable to align "%s"' % image_path)
face_detected_list.append('Unable to align {0}'.format(image_path))
# text_file.write('%s\n' % (output_filename))
continue
if img.ndim == 2:
img = face_net.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 constants.ALIGN_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] - constants.COMPARE_MARGIN_DEFAULT / 2, 0)
bb[1] = np.maximum(det[1] - constants.COMPARE_MARGIN_DEFAULT / 2, 0)
bb[2] = np.minimum(det[2] + constants.COMPARE_MARGIN_DEFAULT / 2, img_size[1])
bb[3] = np.minimum(det[3] + constants.COMPARE_MARGIN_DEFAULT / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(cropped, (constants.ALIGN_IMAGE_SIZE, constants.ALIGN_IMAGE_SIZE), interp='bilinear')
nrof_successfully_aligned += 1
filename_base, file_extension = os.path.splitext(output_filename)
if constants.ALIGN_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)
face_detected_list.append('%s --- BOX [%d , %d , %d , %d]\n' % (output_filename_n, bb[0], bb[1], bb[2], bb[3]))
else:
face_detected_list.append('Unable to align {0}'.format(image_path))
print('Total number of images: %d' % nrof_images_total)
print('Number of successfully aligned images: %d' % nrof_successfully_aligned)
return nrof_images_total, nrof_successfully_aligned, face_detected_list
def main(image_path, data_dir, model_dir, classifier_file):
npy = ''
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants.
GPU_MEMORY_FRACTION_DEFAULT)
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 = constants.FACE_REG_MINSIZE # minimum size of face
threshold = constants.ALIGN_THRESHOLD # three steps's threshold
factor = constants.ALIGN_FACTOR # scale factor
frame_interval = 3
image_size = 160
input_image_size = 160
human_names = os.listdir(data_dir)
human_names.sort()
print('Loading feature extraction model')
face_net.load_model(model_dir)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
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_file)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
c = 0
print('Start Recognition!')
frame = cv2.imread(image_path, 0)
time_f = frame_interval
if c % time_f == 0:
if frame.ndim == 2:
frame = face_net.to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
frame, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
print('Face Detected: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
cropped = []
scaled = []
scaled_reshape = []
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
emb_array = np.zeros((1, embedding_size))
bb[i][0] = det[i][0]
bb[i][1] = det[i][1]
bb[i][2] = det[i][2]
bb[i][3] = det[i][3]
# inner exception
if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][2] >= len(
frame[0]) or bb[i][3] >= len(frame):
print('face is too close')
break
cropped.append(frame[bb[i][1]:bb[i][3],
bb[i][0]:bb[i][2], :])
cropped[i] = face_net.flip(cropped[i], False)
scaled.append(
misc.imresize(cropped[i], (image_size, image_size),
interp='bilinear'))
scaled[i] = cv2.resize(
scaled[i], (input_image_size, input_image_size),
interpolation=cv2.INTER_CUBIC)
scaled[i] = face_net.prewhiten(scaled[i])
scaled_reshape.append(scaled[i].reshape(
-1, input_image_size, input_image_size, 3))
feed_dict = {
images_placeholder: scaled_reshape[i],
phase_train_placeholder: False
}
emb_array[0, :] = sess.run(embeddings,
feed_dict=feed_dict)
predictions = model.predict_proba(emb_array)
print(predictions)
best_class_indices = np.argmax(predictions, axis=1)
# print(best_class_indices)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)),
best_class_indices]
print(best_class_probabilities)
cv2.rectangle(frame, (bb[i][0], bb[i][1]),
(bb[i][2], bb[i][3]), (0, 255, 0),
2) # boxing face
# plot result idx under box
text_x = bb[i][0]
text_y = bb[i][3] - 10
print(
i, 'Result Indices: ', best_class_indices[0],
' : ', 'Face detected of : {0}'.format(
human_names[best_class_indices[0]]))
print(human_names)
for H_i in human_names:
# print(H_i)
if human_names[best_class_indices[
0]] == H_i and best_class_probabilities >= constants.FACE_REG_POSSIBILITY:
result_names = human_names[
best_class_indices[0]]
cv2.putText(frame,
str(i) + ': ' + result_names,
(text_x, text_y),
cv2.FONT_HERSHEY_PLAIN,
1, (0, 0, 255),
thickness=1,
lineType=1)
print('------------------')
else:
print('Unable to align')
frame = cv2.resize(frame, (0, 0), fx=0.5,
fy=0.5) # resize frame (optional)
cv2.imshow('Image', frame)
cv2.imwrite('output/' + image_path.split('/')[-1], frame)
if cv2.waitKey(1000000) & 0xFF == ord('q'):
sys.exit("Thanks")
def align(image_path):
print('Creating networks and loading parameters')
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=1.0)
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)
filename = os.path.splitext(os.path.split(image_path)[1])[0]
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)
return
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]
print('nrof_faces: %s' % nrof_faces)
n = 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,:]
for one in det:
one = np.squeeze(one)
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(one[0] - 5.0 / 2, 0)
bb[1] = np.maximum(one[1] - 5.0 / 2, 0)
bb[2] = np.minimum(one[2] + 5.0 / 2, img_size[1])
bb[3] = np.minimum(one[3] + 5.0 / 2, img_size[0])
cropped = img[bb[1]:bb[3], bb[0]:bb[2], :]
scaled = misc.imresize(cropped, (128, 128),
interp='bilinear')
misc.imsave('/dl/' + str(n) + '.png', scaled)
n += 1
else:
print('Unable to align "%s"' % image_path)
def face_verification(img_pairs_list):
model = 'C:\\Users\\User\\.conda\\envs\\facenet_test\\Lib\\site-packages\\facenet\\align'
model_facenet = r'C:\\Users\\User\\Desktop\\facenett\\20180402-114759' # 模型在你电脑中的路径
# mtcnn相关参数
minsize = 40
threshold = [0.4, 0.5, 0.6] # pnet、rnet、onet三个网络输出人脸的阈值，大于阈值则保留，小于阈值则丢弃
factor = 0.709 # scale factor
# 创建mtcnn网络
with tf.Graph().as_default():
sess = tf.Session()
with sess.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, model)
margin = 44
image_size = 160
with tf.Graph().as_default():
with tf.Session() as sess:
# 根据模型文件载入模型
facenet.load_model(model_facenet)
# 得到输入、输出等张量
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
phase_train_placeholder = tf.get_default_graph(
).get_tensor_by_name("phase_train:0")
# 设置可视化进度条相关参数
jd = '\r %2d%%\t [%s%s]'
bar_num_total = 50
total_num = len(img_pairs_list)
result, dist = [], []
for i in range(len(img_pairs_list)):
# 画进度条
if i % round(
total_num / bar_num_total) == 0 or i == total_num - 1:
bar_num_alright = round(bar_num_total * i / total_num)
alright = '#' * bar_num_alright
not_alright = '□' * (bar_num_total - bar_num_alright)
percent = (bar_num_alright / bar_num_total) * 100
print(jd % (percent, alright, not_alright), end='')
# 读取一对人脸图像
img_pairs = img_pairs_list[i]
img_list = []
img1 = cv2.imread(img_pairs[0])
img2 = cv2.imread(img_pairs[1])
img_size1 = np.asarray(img1.shape)[0:2]
img_size2 = np.asarray(img2.shape)[0:2]
# 检测该对图像中的人脸
bounding_box1, _1 = detect_face.detect_face(
img1, minsize, pnet, rnet, onet, threshold, factor)
bounding_box2, _2 = detect_face.detect_face(
img2, minsize, pnet, rnet, onet, threshold, factor)
# 未检测到人脸，则将结果标为-1，后续计算准确率时排除
if len(bounding_box1) < 1 or len(bounding_box2) < 1:
result.append(-1)
dist.append(-1)
continue
# 将图片1加入img_list
det = np.squeeze(bounding_box1[0, 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_size1[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size1[0])
cropped = img1[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = cv2.resize(cropped, (image_size, image_size))
prewhitened = facenet.prewhiten(aligned)
img_list.append(prewhitened)
# 将图片2加入img_list
det = np.squeeze(bounding_box2[0, 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_size2[1])
bb[3] = np.minimum(det[3] + margin / 2, img_size2[0])
cropped = img2[bb[1]:bb[3], bb[0]:bb[2], :]
aligned = cv2.resize(cropped, (image_size, image_size))
prewhitened = facenet.prewhiten(aligned)
img_list.append(prewhitened)
images = np.stack(img_list)
# 将两个人脸转化为512维的向量
feed_dict = {
images_placeholder: images,
phase_train_placeholder: False
}
emb = sess.run(embeddings, feed_dict=feed_dict)
# 计算两个人脸向量的距离
ed = np.sqrt(np.sum(np.square(np.subtract(emb[0], emb[1]))))
dist.append(ed)
# 根据得出的人脸间的距离，判断是否属于同一个人
if ed <= 1.1:
result.append(1)
else:
result.append(0)
return result, dist
# 创建 tensorflow 网络并加载参数
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)
path = "C:\\Users\\xuefe\\Desktop\\facef\\a\\image\\"
img_dirs = os.listdir(path)
image_path = "C:\\Users\\xuefe\\Desktop\\facex\\b\\"
for im in img_dirs:
img = path + '\\' + im
img = misc.imread(img)
bounding_boxes, face_points = detect_face.detect_face(
img, minsize, pnet, rnet, onet, threshold, factor)
if bounding_boxes.shape[0] != 1:
continue
# 通过人脸框置信度以及鼻子和眼睛的x坐标进行筛选
if (bounding_boxes[0][4] <= 0.999) or ( # bounding_box[0][4]为人脸框的置信度
(face_points[2][0] <= face_points[0][0]
and face_points[2][0] <= face_points[1][0]) or ( # face_points表示
face_points[2][0] >= face_points[0][0]
and face_points[2][0] >= face_points[1][0])): # 人脸的五个关键点
continue # 如果置信度过低或者人脸很歪则丢掉图片
else:
print(im, ':', bounding_boxes[0][4])
misc.imsave(image_path + im, img)
def RecognizeFace(frames, model=None, class_names=None):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=0.6)
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, npy)
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 32
frame_interval = 3
batch_size = 1000
image_size = 160
input_image_size = 160
print('Loading feature extraction model')
facenet.load_model(modeldir)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
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)
if model == None or class_names == None:
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
# video_capture = cv2.VideoCapture("akshay_mov.mp4")
c = 0
HumanNames = class_names
print(HumanNames)
print('Start Recognition!')
prevTime = 0
# ret, frame = video_capture.read()
#frame = cv2.imread(img_path,0)
#frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5) #resize frame (optional)
total_faces_detected = {}
for frame in frames:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)
curTime = time.time() + 1 # calc fps
timeF = frame_interval
if (c % timeF == 0):
find_results = []
if frame.ndim == 2:
frame = facenet.to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
frame, minsize, pnet, rnet, onet, threshold,
factor)
nrof_faces = bounding_boxes.shape[0]
print('Face Detected: %d' % nrof_faces)
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
img_size = np.asarray(frame.shape)[0:2]
cropped = []
scaled = []
scaled_reshape = []
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
emb_array = np.zeros((1, embedding_size))
bb[i][0] = det[i][0]
bb[i][1] = det[i][1]
bb[i][2] = det[i][2]
bb[i][3] = det[i][3]
#inner exception
if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][
2] >= len(frame[0]) or bb[i][3] >= len(
frame):
print('face is too close')
break
cropped.append(frame[bb[i][1]:bb[i][3],
bb[i][0]:bb[i][2], :])
cropped[i] = facenet.flip(cropped[i], False)
scaled.append(
misc.imresize(cropped[i],
(image_size, image_size),
interp='bilinear'))
scaled[i] = cv2.resize(
scaled[i],
(input_image_size, input_image_size),
interpolation=cv2.INTER_CUBIC)
scaled[i] = facenet.prewhiten(scaled[i])
scaled_reshape.append(scaled[i].reshape(
-1, input_image_size, input_image_size, 3))
feed_dict = {
images_placeholder: scaled_reshape[i],
phase_train_placeholder: False
}
emb_array[0, :] = sess.run(embeddings,
feed_dict=feed_dict)
predictions = model.predict_proba(emb_array)
print(predictions)
best_class_indices = np.argmax(predictions,
axis=1)
# print(best_class_indices)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)),
best_class_indices]
#plot result idx under box
text_x = bb[i][0]
text_y = bb[i][3] + 20
print('Result Indices: ',
best_class_indices[0])
print(HumanNames)
for H_i in HumanNames:
# print(H_i)
if HumanNames[best_class_indices[
0]] == H_i and best_class_probabilities >= 0.4:
result_names = HumanNames[
best_class_indices[0]]
if result_names in total_faces_detected:
if predictions[0][best_class_indices[
0]] > total_faces_detected[
result_names]:
total_faces_detected[
result_names] = predictions[
0][best_class_indices[
0]]
else:
total_faces_detected[
result_names] = predictions[0][
best_class_indices[0]]
else:
print("BHAKKK")
if len(total_faces_detected) == 0:
return None
else:
x = sorted(total_faces_detected.items(),
key=operator.itemgetter(1))
return [x[len(x) - 1][0]]
def image_array_align_data(image_arr,
image_path,
pnet,
rnet,
onet,
image_size=160,
margin=32,
detect_multiple_faces=True):
"""
截取人脸的类
:param image_arr: 人脸像素点数组
:param image_path: 拍摄人脸存储路径
:param pnet: caffe模型
:param rnet: caffe模型
:param onet: caffe模型
:param image_size: 图像大小
:param margin: 边缘截取
:param gpu_memory_fraction: 允许的gpu内存大小
:param detect_multiple_faces: 是否可以识别多张脸，默认为False
:return: 若成功，返回截取的人脸数组集合如果没有检测到人脸，直接返回一个1*3的0矩阵
"""
minsize = MINSIZE # minimum size of face
threshold = THRESHOLD # three steps's threshold
factor = FACTOR # scale factor
img = image_arr
bounding_boxes, _ = detect_face(img, minsize, pnet, rnet, onet, threshold,
factor)
nrof_faces = bounding_boxes.shape[0]
nrof_successfully_aligned = 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))
images = np.zeros((len(det_arr), image_size, image_size, 3))
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], :]
# 进行图片缩放 cv2.resize(img,(w,h))
scaled = misc.imresize(cropped, (image_size, image_size),
interp='bilinear')
nrof_successfully_aligned += 1
# 保存检测的头像
filename_base = BASE_DIR + os.sep + 'media' + os.sep + 'face_160' + os.sep + datetime.datetime.now(
).strftime('%Y-%m-%d')
if not os.path.exists(filename_base):
os.mkdir(filename_base)
filename = os.path.basename(image_path)
filename_name, file_extension = os.path.splitext(filename)
# 多个人脸时，在picname后加_0 _1 _2 依次累加。
output_filename_n = "{}/{}_{}{}".format(filename_base,
filename_name, i,
file_extension)
misc.imsave(output_filename_n, scaled)
scaled = prewhiten(scaled)
scaled = crop(scaled, False, 160)
scaled = flip(scaled, False)
images[i] = scaled
if nrof_faces > 0:
return images
else:
return np.zeros((1, 3))
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 = 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, _ = 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]
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] - 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
misc.imsave(output_filename, scaled)
text_file.write(
'%s %d %d %d %d\n' %
(output_filename, 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)
def main(test_dir, data_dir, model_dir, classifier_file):
with tf.Graph().as_default():
gpu_options = tf.GPUOptions(per_process_gpu_memory_fraction=constants.
GPU_MEMORY_FRACTION_DEFAULT)
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 = constants.FACE_REG_MINSIZE # minimum size of face
threshold = constants.ALIGN_THRESHOLD # three steps's threshold
factor = constants.ALIGN_FACTOR # scale factor
image_size = 160
input_image_size = 160
human_names = os.listdir(data_dir)
human_names.sort()
print('Loading feature extraction model')
face_net.load_model(model_dir)
images_placeholder = tf.get_default_graph().get_tensor_by_name(
"input:0")
embeddings = tf.get_default_graph().get_tensor_by_name(
"embeddings:0")
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_file)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
c = 0
print('Start Recognition!')
dataset = face_net.get_dataset(test_dir)
number_of_face_recognition = 0
for cls in dataset:
for image_path in cls.image_paths:
frame = cv2.imread(image_path, 0)
if frame.ndim == 2:
frame = face_net.to_rgb(frame)
frame = frame[:, :, 0:3]
bounding_boxes, _ = detect_face.detect_face(
frame, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]
if nrof_faces > 0:
det = bounding_boxes[:, 0:4]
cropped = []
scaled = []
scaled_reshape = []
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
emb_array = np.zeros((1, embedding_size))
bb[i][0] = det[i][0]
bb[i][1] = det[i][1]
bb[i][2] = det[i][2]
bb[i][3] = det[i][3]
# inner exception
if bb[i][0] <= 0 or bb[i][1] <= 0 or bb[i][
2] >= len(
frame[0]) or bb[i][3] >= len(frame):
print(
'Face is too close {0}'.format(image_path))
break
cropped.append(frame[bb[i][1]:bb[i][3],
bb[i][0]:bb[i][2], :])
cropped[i] = face_net.flip(cropped[i], False)
scaled.append(
misc.imresize(cropped[i],
(image_size, image_size),
interp='bilinear'))
scaled[i] = cv2.resize(
scaled[i],
(input_image_size, input_image_size),
interpolation=cv2.INTER_CUBIC)
scaled[i] = face_net.prewhiten(scaled[i])
scaled_reshape.append(scaled[i].reshape(
-1, input_image_size, input_image_size, 3))
feed_dict = {
images_placeholder: scaled_reshape[i],
phase_train_placeholder: False
}
emb_array[0, :] = sess.run(embeddings,
feed_dict=feed_dict)
predictions = model.predict_proba(emb_array)
best_class_indices = np.argmax(predictions, axis=1)
# print(best_class_indices)
best_class_probabilities = predictions[
np.arange(len(best_class_indices)),
best_class_indices]
# plot result idx under box
for H_i in human_names:
# print(H_i)
if human_names[best_class_indices[0]] == H_i \
and H_i in image_path:
print('{0} : {1}'.format(
best_class_probabilities, image_path))
number_of_face_recognition = number_of_face_recognition + 1
else:
print('Unable to recognition {0}'.format(image_path))
print("Finish!!!!")
print('Number face detected {0}'.format(number_of_face_recognition))