def translatevideo(self, cap, videoout=__videoout):
print("output dir is {}".format(videoout))
# if not os.path.exists(video):
# print("file is not exit, and use camera")
# video = 0
ret, frame = cap.read()
sub = 0
top = 0
while ret:
frame = cv2.cvtColor(frame, cv2.COLOR_BGR2RGB)
box, pot = detect_face.detect_face(frame, self.__minsize, self.__pnet, self.__rnet, self.__onet, self.__threshold, self.__factor)
try:
length = np.shape(pot)[1]
except:
length = 0
for i in range(length):
prefix = ''.join(random.sample(string.ascii_letters + string.digits, 8))
det = box[i, 0:4]
img = frame[int(det[1]):int(det[3]), int(det[0]):int(det[2])]
savepath = os.path.join(videoout + "/" + prefix + str(sub) + ".jpg")
misc.imsave(savepath, img)
sub = sub + 1
print("top save the number of photo is {}".format(sub))
ret, frame = cap.read()
top = top + 1
print("top to progress the number of fps is {}".format(top))
def translateface(self, input=__input, output=__out):
criter = 249
dataset = facenet.get_dataset(input)
for cls in dataset:
assert (len(cls.image_paths)>0, 'There must be at least one image for each class in the dataset')
paths, labels = facenet.get_image_paths_and_labels(dataset)
try:
[os.mkdir(os.path.join(output, label)) for label in set(labels)]
except:
print('Please detect the folder under the {} first and try again'.format(output))
return 0
for i in range(len(paths)):
path = paths[i]
img = cv2.imread(path)
w, h, d = img.shape
if w > criter:
img = cv2.resize(img, (int(h*criter/w), criter))
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB)
# cv2.imshow("input", cv2.cvtColor(img, cv2.COLOR_RGB2BGR))
# cv2.waitKey(0)
box,_ = detect_face.detect_face(img, self.__minsize, self.__pnet, self.__rnet, self.__onet, self.__threshold, self.__factor)
det = box[:, 0:4]
img = cv2.cvtColor(img, cv2.COLOR_RGB2BGR)
for j in range(np.shape(box)[0]):
res = img[int(det[j][1]):int(det[j][3]), int(det[j][0]):int(det[j][2])]
# cv2.imshow("result",res)
# cv2.waitKey(0)
savepath = os.path.join(output + "/" + labels[i], path.split('/')[-1])
#print(savepath)
cv2.imwrite(savepath, res)
def load_and_align_data(image_path,
image_size=160,
margin=44,
gpu_memory_fraction=1.0):
'''
:param image_path: 图片的地址
:param image_size: 对齐后图片的大小
:param margin: 图片界限
:param gpu_memory_fraction: GPU设定
:return: images: 对齐后的人脸集合，list
bounding_boxes：人脸框集合 ndarray,n*5,[x1 x2 y1 y2 p], float32
face_exist：是否存在人脸，布尔值，True：存在；False：不存在
img：读取的图片
'''
minsize = 20 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
face_exist = True
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)
images = []
img = cv2.imread(image_path)
img = cv2.cvtColor(img, cv2.COLOR_BGR2RGB) # BGR to 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_path.remove(image_path)
print("没检测到人脸")
face_exist = False
else: # 检测到人脸
for per_box in bounding_boxes:
box = per_box[0:4]
bb = np.zeros(4, dtype=np.int32)
bb[0] = np.maximum(box[0] - margin / 2, 0)
bb[1] = np.maximum(box[1] - margin / 2, 0)
bb[2] = np.minimum(box[2] + margin / 2, img_size[1])
bb[3] = np.minimum(box[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)
images.append(prewhitened)
return images, img, bounding_boxes, face_exist
filename = './test/Benedict Cumberbatch_001.png'
'''
Mtcnn 检测人脸
'''
minsize = 20
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
graph = tf.Graph() # tf图
sess = tf.Session(graph=graph)
with graph.as_default():
pnet, rnet, onet = detect_face.create_mtcnn(sess, None)
image = cv2.imread(filename)
image = cv2.cvtColor(image, cv2.COLOR_BGR2RGB) # BGR to RGB
bounding_boxes, _ = detect_face.detect_face(image, minsize, pnet, rnet, onet,
threshold, factor)
box = bounding_boxes[0:3].astype(int)
for number in range(box.shape[0]):
cv2.rectangle(image, (box[number, 0], box[number, 1]),
(box[number, 2], box[number, 3]), (0, 255, 255), 1)
face = image[box[number, 1]:box[number, 3], box[number, 0]:box[number, 2]]
'''
进行性别/年龄检测
年龄检测有点不准，建议不要使用人脸输入，人体输入似乎更好, 也可能和性别/年龄检测模型有关
'''
ag = age_and_gender(device_id='/gpu:0', GENDER_LIST=['Male', 'Female'])
best_choice, second_choice = ag.predict(
mode=1, # 0: 年龄；1：性别
image_file=filename,
image_bound=face,
use_tf_to_read=True, # 整张图为True，优先级高于人脸图
def align(self, path_input, path_output):
# get dataset
dataset = facenet.get_dataset(path_input)
# create output dir
if not os.path.exists(path_output):
os.makedirs(path_output)
# 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(path_output, 'bounding_boxes_%05d.txt' % random_key)
with open(bounding_boxes_filename, "w") as text_file:
# number of images
nrof_images_total = 0
# number of successfully alinged faces
nrof_successfully_aligned = 0
for cls in dataset:
path_output_class = os.path.join(path_output, cls.name)
if not os.path.exists(path_output_class):
os.makedirs(path_output_class)
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(path_output_class, filename + '.png')
print(image_path)
if not os.path.exists(output_filename):
try:
img = misc.imread(image_path)
print('read data dimension: ', img.ndim)
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)
print('to_rgb data dimension: ', img.ndim)
img = img[:, :, 0:3]
# bounding boxes
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]
print('detected_face: %d' % nrof_faces)
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_temp = np.zeros(4, dtype=np.int32)
bb_temp[0] = np.maximum(det[0], 0)
bb_temp[1] = np.maximum(det[1], 0)
bb_temp[2] = np.minimum(det[2], img_size[1])
bb_temp[3] = np.minimum(det[3], img_size[0])
cropped_temp = img[bb_temp[1]:bb_temp[3], bb_temp[0]:bb_temp[2], :]
scaled_temp = misc.imresize(cropped_temp, (self.image_size, self.image_size), interp='bilinear')
nrof_successfully_aligned += 1
misc.imsave(output_filename, scaled_temp)
text_file.write('%s %d %d %d %d\n' % (output_filename, bb_temp[0], bb_temp[1], bb_temp[2], bb_temp[3]))
else:
print('No faces 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 detetface(self, img):
faceBound, point = detect_face.detect_face(img, self.__minsize, self.__pnet, self.__rnet, self.__onet, self.__threshold, self.__factor)
return faceBound, point