这个demo效果还是不错的,比单纯的使用opencv判断效率要高。
该blog完整参考 http://tumumu.cn/2017/05/02/deep-learning-face/
01 基本环境
win10 Tensorflow_gpu1.2.1 python3.5.3 dlib opencv
源码:https://github.com/5455945/tensorflow_demo/tree/master/SpecificFaceRecognition
# 该blog完整参考 http://tumumu.cn/2017/05/02/deep-learning-face/
# 源码地址:https://github.com/5455945/tensorflow_demo.git
# https://github.com/5455945/tensorflow_demo/tree/master/SpecificFaceRecognition
# win10 Tensorflow_gpu1.2.1 python3.5.3 dlib opencv
# CUDA v8.0 cudnn-8.0-windows10-x64-v5.1
# 本实验需要有一个摄像头,笔记本自带的即可
# tensorflow_demo\SpecificFaceRecognition\get_my_faces.py 用dlib生成自己脸的jpg图像
# tensorflow_demo\SpecificFaceRecognition\get_my_faces_opencv.py 用opencv生成自己脸的jpg图像(效果没有dlib好)
# tensorflow_demo\SpecificFaceRecognition\set_other_faces.py 预处理lfw的人脸数据
# tensorflow_demo\SpecificFaceRecognition\train_faces.py 人脸识别训练
# tensorflow_demo\SpecificFaceRecognition\is_my_face.py 人脸识别测试
pip3 install tensorflow==1.2.1
pip3 install tensorflow_gpu==1.2.1
pip3 install numpy==1.13.1+mkl
pip3 install opencv-python==3.2.0
pip3 install dlib==19.4.0
# 一定要注意scikit-learn和scipy的版本
pip3 install scikit-learn==0.18.2
pip3 install scipy==0.19.1
02 获取本人图片集
使用get_my_faces.py
获取本人的10000张头像照片,保存到./my_faces
目录。只需启动get_my_faces.py
,坐在电脑前,摆出不同脸部表情和姿势即可。大约1小时左右可采集10000张。
get_my_faces_opencv.py
是采用opencv库采集的,速度比dlib的get_my_faces.py
快些。dlib效果会好些。
get_my_faces.py
# -*- codeing: utf-8 -*-
import cv2
import dlib
import os
import sys
import random
# 使用摄像头采集某人的人脸数据,保存到./my_faces目录
output_dir = './my_faces'
size = 64
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# 改变图片的亮度与对比度
def relight(img, light=1, bias=0):
w = img.shape[1]
h = img.shape[0]
#image = []
for i in range(0,w):
for j in range(0,h):
for c in range(3):
tmp = int(img[j,i,c]*light + bias)
if tmp > 255:
tmp = 255
elif tmp < 0:
tmp = 0
img[j, i, c] = tmp
return img
# 使用dlib自带的frontal_face_detector作为我们的特征提取器
detector = dlib.get_frontal_face_detector()
# 打开摄像头 参数为输入流,可以为摄像头或视频文件
camera = cv2.VideoCapture(0)
index = 1
while True:
if (index <= 10000):
print('Being processed picture %s' % index)
# 从摄像头读取照片
success, img = camera.read()
# 转为灰度图片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector进行人脸检测
dets = detector(gray_img, 1)
for i, d in enumerate(dets):
x1 = d.top() if d.top() > 0 else 0
y1 = d.bottom() if d.bottom() > 0 else 0
x2 = d.left() if d.left() > 0 else 0
y2 = d.right() if d.right() > 0 else 0
face = img[x1:y1, x2:y2]
# 调整图片的对比度与亮度, 对比度与亮度值都取随机数,这样能增加样本的多样性
face = relight(face, random.uniform(0.5, 1.5), random.randint(-50, 50))
face = cv2.resize(face, (size,size))
cv2.imshow('image', face)
cv2.imwrite(output_dir+'/'+str(index)+'.jpg', face)
index += 1
key = cv2.waitKey(30) & 0xff
if key == 27:
break
else:
print('Finished!')
break
03 获取其他人脸图片集
下载http://vis-www.cs.umass.edu/lfw/lfw.tgz人脸数据集。
windows下,可以使用winrar解压,注意要先选[查看文件],然后再解压,才能解压出所有子目录及文件。
加压后的文件放到./input_img
目录下。
然后,使用set_other_people.py
处理./input_img
目录下的解压文件,把大约13000+张头像预处理到./other_faces
目录。
set_other_people.py
# -*- codeing: utf-8 -*-
import sys
import os
import cv2
import dlib
# 下载 lfw.tgz 并解压所有文件到./input_img
# wget http://vis-www.cs.umass.edu/lfw/lfw.tgz
input_dir = './input_img'
output_dir = './other_faces'
size = 64
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# 使用dlib自带的frontal_face_detector作为我们的特征提取器
detector = dlib.get_frontal_face_detector()
index = 1
for (path, dirnames, filenames) in os.walk(input_dir):
for filename in filenames:
if filename.endswith('.jpg'):
print('Being processed picture %s' % index)
img_path = path + '/' + filename
# 从文件读取图片
img = cv2.imread(img_path)
# 转为灰度图片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector进行人脸检测 dets为返回的结果
dets = detector(gray_img, 1)
# 使用enumerate 函数遍历序列中的元素以及它们的下标
# 下标i即为人脸序号
# left:人脸左边距离图片左边界的距离 ;right:人脸右边距离图片左边界的距离
# top:人脸上边距离图片上边界的距离 ;bottom:人脸下边距离图片上边界的距离
for i, d in enumerate(dets):
x1 = d.top() if d.top() > 0 else 0
y1 = d.bottom() if d.bottom() > 0 else 0
x2 = d.left() if d.left() > 0 else 0
y2 = d.right() if d.right() > 0 else 0
# img[y:y+h, x:x+w]
face = img[x1:y1, x2:y2]
# 调整图片的尺寸
face = cv2.resize(face, (size, size))
cv2.imshow('image', face)
# 保存图片
cv2.imwrite(output_dir + '/' + str(index) + '.jpg', face)
index += 1
key = cv2.waitKey(30) & 0xff
if key == 27:
sys.exit(0)
04 训练模型
使用train_faces.py
来训练模型,模型保持到./model
目录下
train_faces.py
# -*- codeing: utf-8 -*-
import tensorflow as tf
import cv2
import numpy as np
import os
import random
import sys
from sklearn.model_selection import train_test_split
# 使用./my_faces和./other_faces中的人脸数据训练,保持模型到./model中
my_faces_path = './my_faces'
other_faces_path = './other_faces'
model_path = './model'
if not os.path.exists(model_path):
os.makedirs(model_path)
size = 64
imgs = []
labs = []
def getPaddingSize(img):
h, w, _ = img.shape
top, bottom, left, right = (0, 0, 0, 0)
longest = max(h, w)
if w < longest:
tmp = longest - w
# //表示整除符号
left = tmp // 2
right = tmp - left
elif h < longest:
tmp = longest - h
top = tmp // 2
bottom = tmp - top
else:
pass
return top, bottom, left, right
def readData(path , h = size, w = size):
for filename in os.listdir(path):
if filename.endswith('.jpg'):
filename = path + '/' + filename
img = cv2.imread(filename)
top, bottom, left, right = getPaddingSize(img)
# 将图片放大, 扩充图片边缘部分
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value = [0, 0, 0])
img = cv2.resize(img, (h, w))
imgs.append(img)
labs.append(path)
readData(my_faces_path)
readData(other_faces_path)
# 将图片数据与标签转换成数组
imgs = np.array(imgs)
labs = np.array([[0, 1] if lab == my_faces_path else [1, 0] for lab in labs])
# 随机划分测试集与训练集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size = 0.05, random_state = random.randint(0, 100))
# 参数:图片数据的总数,图片的高、宽、通道
train_x = train_x.reshape(train_x.shape[0], size, size, 3)
test_x = test_x.reshape(test_x.shape[0], size, size, 3)
# 将数据转换成小于1的数
train_x = train_x.astype('float32') / 255.0
test_x = test_x.astype('float32') / 255.0
print('train size: %s, test size: %s' % (len(train_x), len(test_x)))
# 图片块,每次取100张图片
batch_size = 100
num_batch = len(train_x) // batch_size
x = tf.placeholder(tf.float32, [None, size, size, 3])
y_ = tf.placeholder(tf.float32, [None, 2])
keep_prob_5 = tf.placeholder(tf.float32)
keep_prob_75 = tf.placeholder(tf.float32)
def weightVariable(shape):
init = tf.random_normal(shape, stddev = 0.01)
return tf.Variable(init)
def biasVariable(shape):
init = tf.random_normal(shape)
return tf.Variable(init)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = 'SAME')
def maxPool(x):
return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME')
def dropout(x, keep):
return tf.nn.dropout(x, keep)
def cnnLayer():
# 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])
# 卷积
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 减少过拟合,随机让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
# 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)
# 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)
# 全连接层
Wf = weightVariable([8 * 8 * 64, 512])
bf = biasVariable([512])
drop3_flat = tf.reshape(drop3, [-1, 8 * 8 * 64])
dense = tf.nn.relu(tf.matmul(drop3_flat, Wf) + bf)
dropf = dropout(dense, keep_prob_75)
# 输出层
Wout = weightVariable([512, 2])
bout = weightVariable([2])
#out = tf.matmul(dropf, Wout) + bout
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
def cnnTrain():
out = cnnLayer()
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits = out, labels = y_))
train_step = tf.train.AdamOptimizer(0.01).minimize(cross_entropy)
# 比较标签是否相等,再求的所有数的平均值,tf.cast(强制转换类型)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_, 1)), tf.float32))
# 将loss与accuracy保存以供tensorboard使用
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
merged_summary_op = tf.summary.merge_all()
# 数据保存器的初始化
saver = tf.train.Saver()
with tf.Session() as sess:
sess.run(tf.global_variables_initializer())
summary_writer = tf.summary.FileWriter('./tmp', graph = tf.get_default_graph())
for n in range(10):
# 每次取128(batch_size)张图片
for i in range(num_batch):
batch_x = train_x[i*batch_size : (i + 1) * batch_size]
batch_y = train_y[i*batch_size : (i + 1) * batch_size]
# 开始训练数据,同时训练三个变量,返回三个数据
_, loss, summary = sess.run([train_step, cross_entropy, merged_summary_op],
feed_dict = {x:batch_x,y_:batch_y, keep_prob_5:0.5, keep_prob_75:0.75})
summary_writer.add_summary(summary, n * num_batch + i)
# 打印损失
# print("loss ", n*num_batch + i, loss)
if (n * num_batch + i) % 100 == 0:
# 获取测试数据的准确率
acc = accuracy.eval({x:test_x, y_:test_y, keep_prob_5:1.0, keep_prob_75:1.0})
print(n * num_batch + i, "acc:", acc, " loss:", loss)
# 准确率大于0.98时保存并退出
if acc > 0.98 and n > 2:
saver.save(sess, model_path + '/train_faces.model', global_step = n * num_batch + i)
sys.exit(0)
print('accuracy less 0.98, exited!')
cnnTrain()
'''
train size: 22782, test size: 1200
0 acc: 0.560833 loss: 0.760013
100 acc: 0.923333 loss: 0.280099
200 acc: 0.945833 loss: 0.255821
300 acc: 0.953333 loss: 0.246161
400 acc: 0.958333 loss: 0.113214
500 acc: 0.9625 loss: 0.183178
600 acc: 0.964167 loss: 0.119886
700 acc: 0.971667 loss: 0.134483
800 acc: 0.943333 loss: 0.142579
900 acc: 0.953333 loss: 0.143854
1000 acc: 0.958333 loss: 0.167131
1100 acc: 0.965 loss: 0.10453
1200 acc: 0.975833 loss: 0.132573
1300 acc: 0.976667 loss: 0.191987
1400 acc: 0.9825 loss: 0.0590191
'''
05 使用模型进行识别
使用is_my_face.py
来验证模型,检测到是自己的脸时,返回true。
is_my_face.py
# -*- codeing: utf-8 -*-
import tensorflow as tf
import cv2
import dlib
import numpy as np
import os
import random
import sys
from sklearn.model_selection import train_test_split
# 使用摄像头采集人脸,使用./model中的模型检测是否为特定的人脸
my_faces_path = './my_faces'
other_faces_path = './other_faces'
model_path = './model'
size = 64
imgs = []
labs = []
def getPaddingSize(img):
h, w, _ = img.shape
top, bottom, left, right = (0, 0, 0, 0)
longest = max(h, w)
if w < longest:
tmp = longest - w
# //表示整除符号
left = tmp // 2
right = tmp - left
elif h < longest:
tmp = longest - h
top = tmp // 2
bottom = tmp - top
else:
pass
return top, bottom, left, right
def readData(path , h = size, w = size):
for filename in os.listdir(path):
if filename.endswith('.jpg'):
filename = path + '/' + filename
img = cv2.imread(filename)
top,bottom,left,right = getPaddingSize(img)
# 将图片放大, 扩充图片边缘部分
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value = [0, 0, 0])
img = cv2.resize(img, (h, w))
imgs.append(img)
labs.append(path)
readData(my_faces_path)
readData(other_faces_path)
# 将图片数据与标签转换成数组
imgs = np.array(imgs)
labs = np.array([[0, 1] if lab == my_faces_path else [1, 0] for lab in labs])
# 随机划分测试集与训练集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size = 0.05, random_state = random.randint(0, 100))
# 参数:图片数据的总数,图片的高、宽、通道
train_x = train_x.reshape(train_x.shape[0], size, size, 3)
test_x = test_x.reshape(test_x.shape[0], size, size, 3)
# 将数据转换成小于1的数
train_x = train_x.astype('float32') / 255.0
test_x = test_x.astype('float32') / 255.0
print('train size:%s, test size:%s' % (len(train_x), len(test_x)))
# 图片块,每次取128张图片
batch_size = 128
num_batch = len(train_x) // 128
x = tf.placeholder(tf.float32, [None, size, size, 3])
y_ = tf.placeholder(tf.float32, [None, 2])
keep_prob_5 = tf.placeholder(tf.float32)
keep_prob_75 = tf.placeholder(tf.float32)
def weightVariable(shape):
init = tf.random_normal(shape, stddev = 0.01)
return tf.Variable(init)
def biasVariable(shape):
init = tf.random_normal(shape)
return tf.Variable(init)
def conv2d(x, W):
return tf.nn.conv2d(x, W, strides = [1, 1, 1, 1], padding = 'SAME')
def maxPool(x):
return tf.nn.max_pool(x, ksize = [1, 2, 2, 1], strides = [1, 2, 2, 1], padding = 'SAME')
def dropout(x, keep):
return tf.nn.dropout(x, keep)
def cnnLayer():
# 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])
# 卷积
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 减少过拟合,随机让某些权重不更新
drop1 = dropout(pool1, keep_prob_5)
# 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)
# 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)
# 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, 2])
bout = weightVariable([2])
out = tf.add(tf.matmul(dropf, Wout), bout)
return out
output = cnnLayer()
predict = tf.argmax(output, 1)
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint(model_path))
def is_my_face(image):
res = sess.run(predict, feed_dict={x: [image/255.0], keep_prob_5:1.0, keep_prob_75: 1.0})
if res[0] == 1:
return True
else:
return False
# 使用dlib自带的frontal_face_detector作为我们的特征提取器
detector = dlib.get_frontal_face_detector()
cam = cv2.VideoCapture(0)
while True:
_, img = cam.read()
gray_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
dets = detector(gray_image, 1)
if not len(dets):
# print('Can`t get face.')
cv2.imshow('img', img)
key = cv2.waitKey(30) & 0xff
if key == 27:
sys.exit(0)
for i, d in enumerate(dets):
x1 = d.top() if d.top() > 0 else 0
y1 = d.bottom() if d.bottom() > 0 else 0
x2 = d.left() if d.left() > 0 else 0
y2 = d.right() if d.right() > 0 else 0
face = img[x1:y1, x2:y2]
# 调整图片的尺寸
face = cv2.resize(face, (size, size))
print('Is this my face? %s' % is_my_face(face))
cv2.rectangle(img, (x2, x1), (y2, y1), (255, 0, 0), 3)
cv2.imshow('image', img)
key = cv2.waitKey(30) & 0xff
if key == 27:
sys.exit(0)
sess.close()
'''
train size:22782, test size:1200
Is this my face? True
Is this my face? True
Is this my face? True
...
'''
06 关于opencv获取特定人脸数据
这个使用opencv的代码还需要完善,需要多个分类器组合使用,这里仅仅给出了一个分类器haarcascade_frontalface_default.xml,效果不是很好。opencv自带的分类器在opencv源码的data目录下面。
get_my_faces_opencv.py
import cv2
import os
import sys
import random
# 这个使用opencv的代码还需要完善
# 需要更多的分类器,并且判断准确的人脸后才保存
# 这里贴出来仅供参考
out_dir = './my_faces1'
if not os.path.exists(out_dir):
os.makedirs(out_dir)
# 改变亮度与对比度
def relight(img, alpha=1, bias=0):
w = img.shape[1]
h = img.shape[0]
#image = []
for i in range(0,w):
for j in range(0,h):
for c in range(3):
tmp = int(img[j,i,c]*alpha + bias)
if tmp > 255:
tmp = 255
elif tmp < 0:
tmp = 0
img[j,i,c] = tmp
return img
# 获取分类器
haar = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# 打开摄像头 参数为输入流,可以为摄像头或视频文件
camera = cv2.VideoCapture(0)
n = 1
while 1:
if (n <= 10000):
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, (64,64))
'''
if n % 3 == 1:
face = relight(face, 1, 50)
elif n % 3 == 2:
face = relight(face, 0.5, 0)
'''
face = relight(face, random.uniform(0.5, 1.5), random.randint(-50, 50))
cv2.imshow('img', face)
cv2.imwrite(out_dir+'/'+str(n)+'.jpg', face)
n+=1
key = cv2.waitKey(30) & 0xff
if key == 27:
break
else:
break