python tensorflow人脸识别_opencv，tensorflow，cnn实现人脸识别

opencv实现人脸检测，tensorflow利用cnn实现人脸识别，python完成

github地址: https://github.com/wangdxh/tensorflow-learn

基础知识

获得人脸数据

tensorflow_face_camera.py

def getfacefromcamera(outdir):

createdir(outdir)

camera = cv2.VideoCapture(0)

haar = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

n = 1

while 1:

if (n <= 200):

print('It`s processing %s image.' % n)

# 读帧

success, img = camera.read()

gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

faces = haar.detectMultiScale(gray_img, 1.3, 5)

for f_x, f_y, f_w, f_h in faces:

face = img[f_y:f_y+f_h, f_x:f_x+f_w]

face = cv2.resize(face, (IMGSIZE, IMGSIZE))

#could deal with face to train

face = relight(face, random.uniform(0.5, 1.5), random.randint(-50, 50))

cv2.imwrite(os.path.join(outdir, str(n)+'.jpg'), face)

cv2.putText(img, 'haha', (f_x, f_y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字

img = cv2.rectangle(img, (f_x, f_y), (f_x + f_w, f_y + f_h), (255, 0, 0), 2)

n+=1

cv2.imshow('img', img)

key = cv2.waitKey(30) & 0xff

if key == 27:

break

else:

break

camera.release()

cv2.destroyAllWindows()

name = input('please input yourename: ')

getfacefromcamera(os.path.join('./image/trainfaces', name))

根据输入的名字在./image/trainfaces目录下面创建子目录，将本次采集的头像保存在该目录之下

使用opencv打开摄像头，获取头像

检测出人脸的区域，调整一下亮暗度，将图片保存

保存200张之后，采集结束

创建cnn网络

具体在tensorflow_face_conv.py

def cnnLayer(classnum):

''' create cnn layer'''

# 第一层

W1 = weightVariable([3, 3, 3, 32]) # 卷积核大小(3,3)， 输入通道(3)， 输出通道(32)

b1 = biasVariable([32])

conv1 = tf.nn.relu(conv2d(x_data, W1) + b1)

pool1 = maxPool(conv1)

# 减少过拟合，随机让某些权重不更新

drop1 = dropout(pool1, keep_prob_5) # 32 * 32 * 32 多个输入channel 被filter内积掉了

# 第二层

W2 = weightVariable([3, 3, 32, 64])

b2 = biasVariable([64])

conv2 = tf.nn.relu(conv2d(drop1, W2) + b2)

pool2 = maxPool(conv2)

drop2 = dropout(pool2, keep_prob_5) # 64 * 16 * 16

# 第三层

W3 = weightVariable([3, 3, 64, 64])

b3 = biasVariable([64])

conv3 = tf.nn.relu(conv2d(drop2, W3) + b3)

pool3 = maxPool(conv3)

drop3 = dropout(pool3, keep_prob_5) # 64 * 8 * 8

# 全连接层

Wf = weightVariable([8*16*32, 512])

bf = biasVariable([512])

drop3_flat = tf.reshape(drop3, [-1, 8*16*32])

dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)

dropf = dropout(dense, keep_prob_75)

# 输出层

Wout = weightVariable([512, classnum])

bout = weightVariable([classnum])

#out = tf.matmul(dropf, Wout) + bout

out = tf.add(tf.matmul(dropf, Wout), bout)

return out

使用tf创建3层cnn，3 * 3的filter，输入为rgb所以：

第一层的channel是3，图像宽高为64，输出32个filter，maxpooling是缩放一倍

第二层的输入为32个channel，宽高是32，输出为64个filter，maxpooling是缩放一倍

第三层的输入为64个channel，宽高是16，输出为64个filter，maxpooling是缩放一倍

所以最后输入的图像是8 * 8 * 64，卷积层和全连接层都设置了dropout参数

将输入的8 * 8 * 64的多维度，进行flatten，映射到512个数据上，然后进行softmax，输出到onehot类别上，类别的输入根据采集的人员的个数来确定。

图片发自简书App

识别人脸分类

tensorflow_face.py

训练神经网络

def getfileandlabel(filedir):

''' get path and host paire and class index to name'''

dictdir = dict([[name, os.path.join(filedir, name)] \

for name in os.listdir(filedir) if os.path.isdir(os.path.join(filedir, name))])

#for (path, dirnames, _) in os.walk(filedir) for dirname in dirnames])

dirnamelist, dirpathlist = dictdir.keys(), dictdir.values()

indexlist = list(range(len(dirnamelist)))

return list(zip(dirpathlist, onehot(indexlist))), dict(zip(indexlist, dirnamelist))

pathlabelpair, indextoname = getfileandlabel('./image/trainfaces')

train_x, train_y = readimage(pathlabelpair)

train_x = train_x.astype(np.float32) / 255.0

myconv.train(train_x, train_y, savepath)

将人脸从子目录内读出来，根据不同的人名，分配不同的onehot值，这里是按照遍历的顺序分配序号，然后训练，完成之后会保存checkpoint

图像识别之前将像素值转换为0到1的范围

需要多次训练的话，把checkpoint下面的上次训练结果删除，代码有个判断，有上一次的训练结果，就不会再训练了

识别图像

def testfromcamera(chkpoint):

camera = cv2.VideoCapture(0)

haar = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')

pathlabelpair, indextoname = getfileandlabel('./image/trainfaces')

output = myconv.cnnLayer(len(pathlabelpair))

#predict = tf.equal(tf.argmax(output, 1), tf.argmax(y_data, 1))

predict = output

saver = tf.train.Saver()

with tf.Session() as sess:

#sess.run(tf.global_variables_initializer())

saver.restore(sess, chkpoint)

n = 1

while 1:

if (n <= 20000):

print('It`s processing %s image.' % n)

# 读帧

success, img = camera.read()

gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)

faces = haar.detectMultiScale(gray_img, 1.3, 5)

for f_x, f_y, f_w, f_h in faces:

face = img[f_y:f_y+f_h, f_x:f_x+f_w]

face = cv2.resize(face, (IMGSIZE, IMGSIZE))

#could deal with face to train

test_x = np.array([face])

test_x = test_x.astype(np.float32) / 255.0

res = sess.run([predict, tf.argmax(output, 1)],\

feed_dict={myconv.x_data: test_x,\

myconv.keep_prob_5:1.0, myconv.keep_prob_75: 1.0})

print(res)

cv2.putText(img, indextoname[res[1][0]], (f_x, f_y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2) #显示名字

img = cv2.rectangle(img, (f_x, f_y), (f_x + f_w, f_y + f_h), (255, 0, 0), 2)

n+=1

cv2.imshow('img', img)

key = cv2.waitKey(30) & 0xff

if key == 27:

break

else:

break

camera.release()

cv2.destroyAllWindows()

从训练的结果中恢复训练识别的参数，然后用于新的识别判断

打开摄像头，采集到图片之后，进行人脸检测，检测出来之后，进行人脸识别，根据结果对应到人员名字，显示在图片中人脸的上面

遗留问题

weight 和 bias 的初始化好像有些问题，随机初始化会造成在某些情况下cost很大，梯度下不去，导致train结果很差。重新跑一次命中率又搞了，随机这里可以使用truncated_normal再测试测试。

输出的种类数目是根据采集的人数去动态变化，但是没有给陌生人预留class，所以结果肯定在某个采集的人中，区别不出陌生人来，可以在onehot的个数加1，增加一个陌生人类别，再进行测试。