-
Notifications
You must be signed in to change notification settings - Fork 0
/
realtime_facenet_git.py
179 lines (148 loc) · 7.49 KB
/
realtime_facenet_git.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
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
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 matplotlib.pyplot as pltexi
import numpy as np
import argparse
import facenet
import detect_face
import os
from PIL import Image
from os.path import join as pjoin
import sys
sys.path.append(r'C:\Users\nrdas\Downloads\FaceID\liveness_model')
from keras_liveness import livenessDetection
import time
import copy
import math
import json
import pickle
from sklearn.svm import SVC
from livenessmodel import get_liveness_model
import joblib
pred = [[0]]
print('Creating networks and loading parameters')
# livemodel = load_model(r'C:\Users\nrdas\Downloads\FaceID\liveness_model\model\liveness.model')
# lenet = pickle.loads(open(r'C:\Users\nrdas\Downloads\FaceID\liveness_model\model\le.pickle', 'rb').read())
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, 'models')
detect = livenessDetection()
minsize = 20 # 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 = ['nitish', 'unauthorized']
print('Loading feature extraction model')
modeldir = '20170511-185253\\20170511-185253.pb'
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 = 'classifier/my_classifier.pkl'
classifier_filename_exp = os.path.expanduser(classifier_filename)
with open(classifier_filename_exp, 'rb') as infile:
(model, class_names) = pickle.load(infile)
# model = pickle.load(infile)
print('load classifier file-> %s' % classifier_filename_exp)
video_capture = cv2.VideoCapture(0)
video_capture.set(3, 640)
video_capture.set(4, 480)
c = 0
# #video writer
# fourcc = cv2.VideoWriter_fourcc(*'DIVX')
# out = cv2.VideoWriter('3F_0726.avi', fourcc, fps=30, frameSize=(640,480))
input_vid = []
print('Start Recognition!')
prevTime = 0
while True:
ret, frame = video_capture.read()
liveimg = cv2.resize(frame, (100,100))
frame = cv2.resize(frame, (0,0), fx=0.5, fy=0.5) #resize frame (optional)
curTime = time.time() # 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]
bb = np.zeros((nrof_faces, 4), dtype=np.int32)
for i in range(nrof_faces):
cropped = []
scaled = []
scaled_reshape = []
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 inner of range!')
continue
cropped.append(frame[bb[i][1]:bb[i][3], bb[i][0]:bb[i][2], :])
if not(detect.run_inf2(cropped[0])):
print('SKIPPING A FACE AS IT IS FAKE')
continue
cropped[0] = facenet.flip(cropped[0], False)
# scaled.append(misc.imresize(cropped[0], (image_size, image_size), interp='bilinear'))
scaled.append(np.array(Image.fromarray(cropped[0]).resize((image_size, image_size), resample=Image.BILINEAR)))
scaled[0] = cv2.resize(scaled[0], (input_image_size,input_image_size),
interpolation=cv2.INTER_CUBIC)
scaled[0] = facenet.prewhiten(scaled[0])
scaled_reshape.append(scaled[0].reshape(-1, input_image_size, input_image_size,3))
# print(cropped[0].shape, scaled[0].shape, scaled_reshape[0].shape)
feed_dict = {images_placeholder: scaled_reshape[0], 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)
# Create binary classifier for each authorized user ?
# if new input face is negative for every classifier, it's unrecognized
# if new input passes on one of the classifiers it is that person
print('YOOOOOOOOOOOOOOOOOOOOOOOOOOO', best_class_indices, predictions)
best_class_probabilities = predictions[np.arange(len(best_class_indices)), best_class_indices]
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: ', best_class_indices[0])
for H_i in HumanNames:
if HumanNames[best_class_indices[0]] == H_i:
result_names = HumanNames[best_class_indices[0]]
cv2.putText(frame, result_names, (text_x, text_y), cv2.FONT_HERSHEY_COMPLEX_SMALL,
1, (0, 0, 255), thickness=1, lineType=2)
else:
print('Unable to align')
sec = curTime - prevTime
prevTime = curTime
fps = 1 / (sec)
str = 'FPS: %2.3f' % fps
# c+=1
text_fps_x = len(frame[0]) - 150
text_fps_y = 20
cv2.putText(frame, str, (text_fps_x, text_fps_y),
cv2.FONT_HERSHEY_COMPLEX_SMALL, 1, (0, 0, 0), thickness=1, lineType=2)
# c+=1
cv2.imshow('Video', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
video_capture.release()
# #video writer
# out.release()
cv2.destroyAllWindows()