基于mtcnn和facenet的实时人脸检测与识别系统开发 - 知乎

    import numpy as np
import cv2

cap = cv2.VideoCapture(0)

while(True):
    # Capture frame-by-frame
    ret, frame = cap.read()

    # Our operations on the frame come here
    gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # Display the resulting frame
    cv2.imshow('frame',gray)
    if cv2.waitKey(1) & 0xFF == ord('q'):
        break

# When everything done, release the capture
cap.release()
cv2.destroyAllWindows()

    %%time
#图片人脸检测
import cv2
import sys
# Get user supplied values
imagePath = "./multi_faces.jpg"
# Create the haar cascade
faceCascade = cv2.CascadeClassifier("./haarcascade_frontalface_alt2.xml") 
# Read the image
image = cv2.imread(imagePath)#2
gray = cv2.cvtColor(image, cv2.COLOR_BGR2GRAY)#3
# Detect faces in the image
faces = faceCascade.detectMultiScale(
    gray,
    scaleFactor=1.15,
    minNeighbors=5,
    minSize=(5,5),
    flags = cv2.cv.CV_HAAR_SCALE_IMAGE
) #4
print "Found {0} faces!".format(len(faces))#5
for (x, y, w, h) in faces:
    cv2.rectangle(image, (x, y), (x+w, y+h), (0, 255, 0), 2) #6
cv2.imshow("Faces found", image)#7
cv2.waitKey(0) #8

    #建立mtcnn人脸检测模型，加载参数
print('Creating networks and loading parameters')
gpu_memory_fraction=1.0
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, './davidsandberg_facenet-master/data/')

bounding_boxes, _ = detect_face.detect_face(img, minsize, pnet, rnet, onet, threshold, factor)
nrof_faces = bounding_boxes.shape[0]#人脸数目
print('找到人脸数目为：{}'.format(nrof_faces))

crop_faces=[]
for face_position in bounding_boxes:
    face_position=face_position.astype(int)
    print(face_position[0:4])
    cv2.rectangle(img_color, (face_position[0], face_position[1]), (face_position[2], face_position[3]), (0, 255, 0), 2)
    crop=img_color[face_position[1]:face_position[3],
             face_position[0]:face_position[2],]
    
    crop = cv2.resize(crop, (96, 96), interpolation=cv2.INTER_CUBIC )

    
    print(crop.shape)
    crop_faces.append(crop)
    plt.imshow(crop)
    plt.show()
    
plt.imshow(img_color)
plt.show()

    #建立facenet embedding模型
print('建立facenet embedding模型')
tf.Graph().as_default()
sess = tf.Session()
images_placeholder = tf.placeholder(tf.float32, shape=(batch_size, 
                                                       image_size, 
                                                       image_size, 3), name='input')

phase_train_placeholder = tf.placeholder(tf.bool, name='phase_train')



embeddings = network.inference(images_placeholder, pool_type, 
                               use_lrn, 
                               1.0, 
                               phase_train=phase_train_placeholder)



ema = tf.train.ExponentialMovingAverage(1.0)
saver = tf.train.Saver(ema.variables_to_restore())
#ckpt = tf.train.get_checkpoint_state(os.path.expanduser(model_dir))
#saver.restore(sess, ckpt.model_checkpoint_path)

model_checkpoint_path='./model-20160506.ckpt-500000'
#ckpt = tf.train.get_checkpoint_state(os.path.expanduser(model_dir))
#model_checkpoint_path='model-20160506.ckpt-500000'


#saver.restore(sess, ckpt.model_checkpoint_path)
saver.restore(sess, model_checkpoint_path)
print('facenet embedding模型建立完毕')

######省略部分代码
emb_data = sess.run([embeddings], 
                            feed_dict={images_placeholder: face_data, phase_train_placeholder: False })[0]
        

    #训练KNN分类

from sklearn import metrics  
from sklearn.externals import joblib

X_train, X_test, y_train, y_test = train_test_split(X, train_y, test_size=.3, random_state=42)

# KNN Classifier  
def knn_classifier(train_x, train_y):  
    from sklearn.neighbors import KNeighborsClassifier  
    model = KNeighborsClassifier()  
    model.fit(train_x, train_y)  
    return model  

classifiers = knn_classifier 

model = classifiers(X_train,y_train)  
predict = model.predict(X_test)  

accuracy = metrics.accuracy_score(y_test, predict)  
print ('accuracy: %.2f%%' % (100 * accuracy)  ) 
  
    
#保存模型
joblib.dump(model, 'knn.model')

    model = joblib.load('knn.model')
predict = model.predict(X_test) 
print ('识别结果为：{}'.format(predict))