-
Notifications
You must be signed in to change notification settings - Fork 8
/
Copy pathidentify_face_video.py
151 lines (125 loc) · 6.74 KB
/
identify_face_video.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
from scipy import misc
import cv2
import numpy as np
import facenet
import detect_face
import os
import time
import pickle
input_video="YOUR VIDEO PATH"
modeldir = './model/20170512-110547.pb'
classifier_filename = './classifier/classifier_2017.pkl'
npy='./npy'
train_img="./train_img"
now = time.strftime("%Y-%m-%d-%H_%M_%S",time.localtime(time.time()))
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 = 53 # minimum size of face
threshold = [0.6, 0.7, 0.7] # three steps's threshold
factor = 0.709 # scale factor
margin = 44
frame_interval = 3
batch_size = 1000
image_size = 182
input_image_size = 160
HumanNames = os.listdir(train_img)
HumanNames.sort()
print('Loading Modal')
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)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
video_capture = cv2.VideoCapture(input_video)
video_capture.set(cv2.CAP_PROP_FRAME_WIDTH,1280);#640
video_capture.set(cv2.CAP_PROP_FRAME_HEIGHT,720);#480、20
filename = './output_video/'+now+r'.m4v'
fourcc = cv2.VideoWriter_fourcc('m','p','4','v')
out = cv2.VideoWriter(filename, fourcc, 30, (1280, 720))#20
c = 0
print('Start Recognition')
prevTime = 0
while True:
ret, frame = video_capture.read()
#frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5) #resize frame (optional)
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('Detected_FaceNum: %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 very close!')
continue
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)
best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
# print("predictions")
print(best_class_indices,' with accuracy ',best_class_probabilities)
# print(best_class_probabilities)
if best_class_probabilities>0.53:
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] + 20
print('Result Indices: ', best_class_indices[0])
print(HumanNames)
for H_i in HumanNames:
if HumanNames[best_class_indices[0]] == H_i:
#Unknown thre < 0.65
if best_class_probabilities < 0.65:
result_names = "Unknown"
cv2.putText(frame, result_names, (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX,0.5, (0, 255, 0), thickness=1, lineType=1)
elif best_class_probabilities >= 0.65:
result_names = HumanNames[best_class_indices[0]]
cv2.putText(frame, result_names, (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX,0.5, (0, 255, 0), thickness=1, lineType=1)
#result_names = HumanNames[best_class_indices[0]]
#cv2.putText(frame, result_names, (text_x, text_y),cv2.FONT_HERSHEY_COMPLEX_SMALL,0.8, (0, 255, 0), thickness=1, lineType=1)
else:
print('Alignment Failure')
# c+=1
out.write(frame)
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
out.release()
video_capture.release()
cv2.destroyAllWindows()