人脸识别
借鉴别人的代码，首先，获取自己的图片信息，利用dlib切分成只有脸部信息的64*64的小图片。代码get_my_faces.py：
import cv2
import dlib
import os
import sys
import random
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 = 6641
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(1) & 0xff
if key == 27:
break
else:
print('Finished!')
break
接下来获取人脸小数据集，lfw，生成人脸小图片：代码如下：
# -*- codeing: utf-8 -*-
import sys
import os
import cv2
import dlib
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)
最后，进行训练，其实我看了源码，实则是一个类似于二分类器的东西，代码如下：
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))
#print (labs)
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 (test_x)
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(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(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)
# 准确率大于0.98时保存并退出
if acc > 0.98 and n > 2:
saver.save(sess, './train_faces.model', global_step=n*num_batch+i)
sys.exit(0)
print('accuracy less 0.98, exited!')
cnnTrain()
最后，可以打开摄像头检测是否识别成功，代码如下：
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
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 = biasVariable([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('.'))
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()
检测结果取决于自己的人脸图片数据集，获取自己图片的时候多方位的采集数据。