tensorflow74 使用tensorflow dlib opencv做特定人臉識別
阿新 • • 發佈:2019-01-08
01 基本環境
# 該blog完整參考 http://tumumu.cn/2017/05/02/deep-learning-face/
# 原始碼地址: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
# 本實驗需要有一個攝像頭,筆記本自帶的即可
# tensorflow_demo\SpecificFaceRecognition\get_my_faces.py 用dlib生成自己臉的jpg影象
# tensorflow_demo\SpecificFaceRecognition\get_my_faces_opencv.py 用opencv生成自己臉的jpg影象(效果沒有dlib好)
# tensorflow_demo\SpecificFaceRecognition\set_other_faces.py 預處理lfw的人臉資料
# tensorflow_demo\SpecificFaceRecognition\train_faces.py 人臉識別訓練
# tensorflow_demo\SpecificFaceRecognition\is_my_face.py 人臉識別測試
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 獲取本人圖片集
使用get_my_faces.py
獲取本人的10000張頭像照片,儲存到./my_faces
目錄。只需啟動get_my_faces.py
get_my_faces_opencv.py
是採用opencv庫採集的,速度比dlib的get_my_faces.py
快些。dlib效果會好些。
get_my_faces.py
# -*- codeing: utf-8 -*-
import cv2
import dlib
import os
import sys
import random
# 使用攝像頭採集某人的人臉資料,儲存到./my_faces目錄
output_dir = './my_faces'
size = 64
if not os.path.exists(output_dir):
os.makedirs(output_dir)
# 改變圖片的亮度與對比度
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自帶的frontal_face_detector作為我們的特徵提取器
detector = dlib.get_frontal_face_detector()
# 開啟攝像頭 引數為輸入流,可以為攝像頭或視訊檔案
camera = cv2.VideoCapture(0)
index = 1
while True:
if (index <= 10000):
print('Being processed picture %s' % index)
# 從攝像頭讀取照片
success, img = camera.read()
# 轉為灰度圖片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector進行人臉檢測
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]
# 調整圖片的對比度與亮度, 對比度與亮度值都取隨機數,這樣能增加樣本的多樣性
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 獲取其他人臉圖片集
下載http://vis-www.cs.umass.edu/lfw/lfw.tgz人臉資料集。
windows下,可以使用winrar解壓,注意要先選[檢視檔案],然後再解壓,才能解壓出所有子目錄及檔案。
加壓後的檔案放到./input_img
目錄下。
然後,使用set_other_people.py
處理./input_img
目錄下的解壓檔案,把大約13000+張頭像預處理到./other_faces
目錄。
set_other_people.py
# -*- codeing: utf-8 -*-
import sys
import os
import cv2
import dlib
# 下載 lfw.tgz 並解壓所有檔案到./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自帶的frontal_face_detector作為我們的特徵提取器
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
# 從檔案讀取圖片
img = cv2.imread(img_path)
# 轉為灰度圖片
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
# 使用detector進行人臉檢測 dets為返回的結果
dets = detector(gray_img, 1)
# 使用enumerate 函式遍歷序列中的元素以及它們的下標
# 下標i即為人臉序號
# left:人臉左邊距離圖片左邊界的距離 ;right:人臉右邊距離圖片左邊界的距離
# top:人臉上邊距離圖片上邊界的距離 ;bottom:人臉下邊距離圖片上邊界的距離
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]
# 調整圖片的尺寸
face = cv2.resize(face, (size, size))
cv2.imshow('image', face)
# 儲存圖片
cv2.imwrite(output_dir + '/' + str(index) + '.jpg', face)
index += 1
key = cv2.waitKey(30) & 0xff
if key == 27:
sys.exit(0)
04 訓練模型
使用train_faces.py
來訓練模型,模型保持到./model
目錄下
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中的人臉資料訓練,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
# //表示整除符號
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)
# 將圖片放大, 擴充圖片邊緣部分
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)
# 將圖片資料與標籤轉換成陣列
imgs = np.array(imgs)
labs = np.array([[0, 1] if lab == my_faces_path else [1, 0] for lab in labs])
# 隨機劃分測試集與訓練集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size = 0.05, random_state = random.randint(0, 100))
# 引數:圖片資料的總數,圖片的高、寬、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)
# 將資料轉換成小於1的數
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)))
# 圖片塊,每次取100張圖片
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():
# 第一層
W1 = weightVariable([3, 3, 3, 32]) # 卷積核大小(3,3), 輸入通道(3), 輸出通道(32)
b1 = biasVariable([32])
# 卷積
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 減少過擬合,隨機讓某些權重不更新
drop1 = dropout(pool1, keep_prob_5)
# 第二層
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)
# 第三層
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)
# 全連線層
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)
# 輸出層
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)
# 比較標籤是否相等,再求的所有數的平均值,tf.cast(強制轉換型別)
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_, 1)), tf.float32))
# 將loss與accuracy儲存以供tensorboard使用
tf.summary.scalar('loss', cross_entropy)
tf.summary.scalar('accuracy', accuracy)
merged_summary_op = tf.summary.merge_all()
# 資料儲存器的初始化
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)張圖片
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]
# 開始訓練資料,同時訓練三個變數,返回三個資料
_, 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)
# 列印損失
# print("loss ", n*num_batch + i, loss)
if (n * num_batch + i) % 100 == 0:
# 獲取測試資料的準確率
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)
# 準確率大於0.98時儲存並退出
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 使用模型進行識別
使用is_my_face.py
來驗證模型,檢測到是自己的臉時,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
# 使用攝像頭採集人臉,使用./model中的模型檢測是否為特定的人臉
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
# //表示整除符號
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)
# 將圖片放大, 擴充圖片邊緣部分
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)
# 將圖片資料與標籤轉換成陣列
imgs = np.array(imgs)
labs = np.array([[0, 1] if lab == my_faces_path else [1, 0] for lab in labs])
# 隨機劃分測試集與訓練集
train_x, test_x, train_y, test_y = train_test_split(imgs, labs, test_size = 0.05, random_state = random.randint(0, 100))
# 引數:圖片資料的總數,圖片的高、寬、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)
# 將資料轉換成小於1的數
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)))
# 圖片塊,每次取128張圖片
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():
# 第一層
W1 = weightVariable([3, 3, 3, 32]) # 卷積核大小(3,3), 輸入通道(3), 輸出通道(32)
b1 = biasVariable([32])
# 卷積
conv1 = tf.nn.relu(conv2d(x, W1) + b1)
# 池化
pool1 = maxPool(conv1)
# 減少過擬合,隨機讓某些權重不更新
drop1 = dropout(pool1, keep_prob_5)
# 第二層
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)
# 第三層
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)
# 全連線層
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)
# 輸出層
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自帶的frontal_face_detector作為我們的特徵提取器
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]
# 調整圖片的尺寸
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 關於opencv獲取特定人臉資料
這個使用opencv的程式碼還需要完善,需要多個分類器組合使用,這裡僅僅給出了一個分類器haarcascade_frontalface_default.xml,效果不是很好。opencv自帶的分類器在opencv原始碼的data目錄下面。
get_my_faces_opencv.py
import cv2
import os
import sys
import random
# 這個使用opencv的程式碼還需要完善
# 需要更多的分類器,並且判斷準確的人臉後才儲存
# 這裡貼出來僅供參考
out_dir = './my_faces1'
if not os.path.exists(out_dir):
os.makedirs(out_dir)
# 改變亮度與對比度
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
# 獲取分類器
haar = cv2.CascadeClassifier('haarcascade_frontalface_default.xml')
# 開啟攝像頭 引數為輸入流,可以為攝像頭或視訊檔案
camera = cv2.VideoCapture(0)
n = 1
while 1:
if (n <= 10000):
print('It`s processing %s image.' % n)
# 讀幀
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