/* 版权声明:可以任意转载,转载时请标明文章原始出处和作者信息 .*/
###人脸识别程序共分为4个部分,大致结构如下:
####1.get_my_faces_dlib.py
使用opencv获取个人的人脸图像,并通过dlib库中的人脸特征提取,截取获取的正样本人脸数据集。
该程序共包括如下2个重要部分:
(1)定义relight函数,对摄像头拍摄的图像进行光线的转换,多样化样本。
(2)dlib函数针对的是灰度图像,对图像进行灰度转换和resize,存储图像均为64*64.
# get_my_faces_dlib.py
import cv2
import dlib
import random
import os
# import sys
out_dir = 'my_faces'
size = 64
if not os.path.exists(out_dir):
os.makedirs(out_dir)
def relight(img, light=1, beta=0):
w = img.shape[1]
h = img.shape[0]
# h, w, _ = img.shape
for i in range(h):
for j in range(w):
for c in range(3):
temp = int(img[i,j,c]*light+beta)
if temp>255:
temp=255
elif temp<0:
temp=0
img[i,j,c] = temp
return img
detector = dlib.get_frontal_face_detector()
cam = cv2.VideoCapture(0)
index = 1
while True:
if index<=500:
print('Being processed picture %s' % index)
success, img = cam.read()
gray_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
dets = detector(gray_image, 1) # 返回是一个框[(x1,y1),(x2,y2)]
for i, d in enumerate(dets):
y1 = d.top() if d.top()>0 else 0
y2 = d.bottom() if d.bottom()>0 else 0
x1 = d.left() if d.left()>0 else 0
x2 = d.right() if d.right()>0 else 0
face = img[y1:y2, x1:x2]
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(out_dir+'/'+str(index)+'.jpg',face)
index += 1
key = cv2.waitKey(30) & 0xff
if key==27:
break
else:
print('finished')
break
####2.set_other_faces.py
对已有的数据集,如LFW数据集,通过重新提取图像到指定的输出文件夹中,形成train过程中的负样本集。
该程序共包括如下2个重要部分:
(1)读取已有数据集input_img中的图像。
(2)利用dlib库中的人脸特征函数将(1)中读取的图像进行人脸的截取,并重新写入新的文件夹other_faces中。
# set_other_faces.py
#encoding: utf-8
import cv2
import os
import dlib
import sys
# 定义数据文件夹
out_dir = 'other_faces'
# 定义待提取数据文件夹,在这里用的是LFW的数据集
input_dir = 'input_img'
# 建立输出文件夹out_dir
if not os.path.exists(out_dir):
os.makedirs(out_dir)
# 提取人脸的特征,使用dlib自带的检测器
size = 64
detector = dlib.get_frontal_face_detector()
# 读入输入文件夹中的图像,并输出到特定的out_dir文件夹中
index = 1
for (path, namedir, filenames) in os.walk(input_dir):
# 对输入文件夹input_dir中的每一个jpg图像进行提取并输出到out_dir中。
for filename in filenames:
if filename.endswith('.jpg'):
# 提取图像的路径
img_path = path + '/' + filename
img = cv2.imread(img_path)
# 提取人脸的检测框,获得dets,dlib是对灰度图像进行处理的,故转为灰度图像
gray_image = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
dets = detector(gray_image, 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):
y1 = d.top() if d.top()>0 else 0
y2 = d.bottom() if d.bottom()>0 else 0
x1 = d.left() if d.left()>0 else 0
x2 = d.right() if d.right()>0 else 0
# 在原彩色图像中截取face区域,注意不能是对灰度图像进行处理
face = img[y1:y2, x1:x2]
# img[y:y+h,x:x+w] 截取框内的人脸
# 对截取的人脸图像进行resize,并显示输出
face = cv2.resize(face, (size, size))
cv2.imshow('image', face)
# 将resize后的人脸写入out_dir文件夹中
cv2.imwrite(out_dir + '/'+ str(index)+'.jpg',face)
index += 1
# 设定终止key,按esc键停止
key = cv2.waitKey(30) & 0xff
if key== 27:
sys.exit(0)
# 按q键停止
# if cv2.waitKey(30) & 0xff == ord('q'):
# sys.exit(0)
####3.train_faces.py
训练my_faces和other_faces中的图像,获取准确率高于0.99的训练模型并保存。
该程序共包括如下2个重要部分:
(1)读入图像,特加入了填补函数getPaddingSize,防止图像进行resize的时候失真。
(2)图像转化可读入数据集,image转化为矩阵,label转化为one-hot编码,正样本为[0,1],负样本为[1,0].
(3)将整个正样本和负样本进行随机划分为测试集和训练集,test_size=0.05。
(4)利用CNN进行训练,三层卷积层,维度分别为(32,64,64),卷积核大小均为3;每一层均采用maxpool,池化大小均为2;且都采用dropout操作来减小过拟合。全连接层维度为512,并使用dropout,softmax输出为2。
(5)当所有图像被训练两轮后且测试准确率大于0.99时,将训练结果模型保存在项目目录中,以供实时测试使用。
# train_faces.py
#encoding: 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
my_faces_path = 'my_faces'
other_faces_path = 'other_faces'
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 = biasVariable([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(200):
# 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('第%s次训练,loss=%s' % (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('%s,acc=%s'%(n*num_batch+i, acc))
# 准确率大于0.99时保存并退出
if acc > 0.99 and n > 2:
saver.save(sess, './train_faces.model', global_step=n*num_batch+i)
sys.exit(0)
print('accuracy less 0.99, exited!')
cnnTrain()
####4.is_my_face.py
测试过程直接采用保存的训练模型中的参数,使用opencv获取实时图像,检测摄像头获取的人脸是否是本人,输出为True or False。
# is_my_face.py
saver = tf.train.Saver()
sess = tf.Session()
saver.restore(sess, tf.train.latest_checkpoint('.'))
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()
如下图所示,当摄像头读入本人时,显示True,是其他人的时候,显示False。
NOTE:
- 正样本和负样本的比例不可过大,在实际操作过程中,录入正样本太少,与LFW庞大的样本量对比,会造成测试的准备率极低。
- train_face的range,应根据个人的样本量调整,太少,会造成未达到要求的acc就输出accuracy less 0.99, exited!,保存不了训练模型。
完整代码详见github_face_reg,相互学习。