在此之前我已经大概说过tensorflow的简单流程，中间应用函数我会在例子中加以注释(更详细的可以查阅tensorflow中的函数讲解)。应用cnn实现的视频中人物识别，本想先讲一下cnn的原理，但基于时间和别人都以将的很详细在此就多说，直接上例子
1 简单图片中的人脸检测
在刚开始学时需要有兴趣，并且能快速实现结果。从结果到原因，再从原因到结果才是最好的学习方法(纯属个人观点)
## 基于haar特征
## 图片中的人物识别
import cv2
#读取图像，支持 bmp、jpg、png、tiff 等常用格式
img = cv2.imread("C:/Users/test2/Desktop/1.jpg")
# "D:\Test\2.jpg"
#创建窗口并显示图像
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)#将图片转化成灰度
path="F:/机器学习-物体识别/haar_like/haarcascade_frontalface_alt2.xml"
path="F:/haar_like/haarcascade_frontalface_alt2.xml"
face_cascade = cv2.CascadeClassifier("haarcascade_frontalface_alt2.xml")
face_cascade.load(path) #一定要告诉编译器文件所在的具体位置
#'''此文件是opencv的haar人脸特征分类器'''
faces = face_cascade.detectMultiScale(gray, 1.3, 5)
for (x,y,w,h) in faces:
img = cv2.rectangle(img,(x,y),(x+w,y+h),(0,0,255),5)
cv2.imshow('img',img)
cv2.waitKey()2 从摄像头中识别人脸
## 基于haar特征
## 通过摄像头可以识别出视频中的人物
import cv2
cap = cv2.VideoCapture(0) # 使用第5个摄像头（我的电脑插了5个摄像头）
path="F:\haar_like\haarcascades\haarcascade_frontalface_default.xml"
face_cascade = cv2.CascadeClassifier(path) # 加载人脸特征库
while(True):
ret, frame = cap.read() # 读取一帧的图像
gray = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY) # 转灰
faces = face_cascade.detectMultiScale(frame, scaleFactor = 1.15, minNeighbors = 5, minSize = (5, 5)) # 检测人脸
for(x, y, w, h) in faces:
cv2.rectangle(frame, (x, y), (x + w, y + h), (0, 0, 255), 3) # 用矩形圈出人脸
cv2.imshow('Face Recognition', frame)
if cv2.waitKey(1) & 0xFF == ord('q'):
break
cap.release() # 释放摄像头
cv2.destroyAllWindows()3 基于cnn+tensorflow实现摄像头中人脸的识别
有上述2个简单例子实现人脸检测你肯定不满足吧！对，所以我自己通过cnn+tensorflow搭建识别摄像头中人脸的算法。
#通过摄像头拍摄获取人脸训练集
import os
import random
import numpy as np
import cv2
#创建文件夹函数
def createdir(*args):
''' create dir'''
for item in args:
#判断路径是否存在
if not os.path.exists(item):
#不存在就创建
os.makedirs(item)
#照片的尺寸
IMGSIZE = 64
#获取照片的大小将其裁剪为正方形
def getpaddingSize(shape):
#照片的长宽
h, w = shape
longest = max(h, w)
#将最长的边进行处理
result = (np.array([longest]*4, int) - np.array([h, h, w, w], int)) // 2
return result.tolist()
#处理照片函数
def dealwithimage(img, h=64, w=64):
#获取照片的尺寸
top, bottom, left, right = getpaddingSize(img.shape[0:2])
#扩充图像
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
#对图像进行倍数的放大和缩小 也可以直接的输入尺寸大小
img = cv2.resize(img, (h, w))
return img #返回图像
#图像的增强
def relight(imgsrc, alpha=1, bias=0):
#astype实现图片像素的数据类型转换
imgsrc = imgsrc.astype(float)
#对像素点的值进行变换
imgsrc = imgsrc * alpha + bias
imgsrc[imgsrc < 0] = 0
imgsrc[imgsrc > 255] = 255
imgsrc = imgsrc.astype(np.uint8)
return imgsrc #返回转变后的像素值
#得到面部照片并保存
def getfacefromcamera(outdir):
createdir(outdir)
camera = cv2.VideoCapture(0)
path="F:\haar_like\haarcascades\haarcascade_frontalface_default.xml"
haar = cv2.CascadeClassifier(path)
n = 1
while 1:
if (n <= 200):
print('It`s processing %s image.' % n)
# 读帧
success, img = camera.read()
#对图像进行灰度处理
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
#检测出人脸用vector保存各个人脸的坐标、大小（用矩形表示）
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))
#处理训练图片
face = relight(face, random.uniform(0.5, 1.5), random.randint(-50, 50))
#给图片添加标号
cv2.imwrite(os.path.join(outdir, str(n)+'.jpg'), face)
#显示名字
cv2.putText(img, 'haha', (f_x, f_y - 20), cv2.FONT_HERSHEY_SIMPLEX, 1, 255, 2)
img = cv2.rectangle(img, (f_x, f_y), (f_x + f_w, f_y + f_h), (0, 0, 255), 3)
n+=1
cv2.imshow('img', img)
key = cv2.waitKey(30) & 0xff
if key == 27:
break
else:
break
camera.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
#输入保存照片的类别
name = input('please input yourename: ')
#将照片保存
getfacefromcamera(os.path.join('F:/ml/image/trainfaces', name))#tensorflow_face_conv.py文件
#coding=utf-8
import os
import logging as log
import matplotlib.pyplot as plt
import common
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import cv2
SIZE = 64
#用于得到传递进来的真实的训练样本
x_data = tf.placeholder(tf.float32, [None, SIZE, SIZE, 3])
y_data = tf.placeholder(tf.float32, [None, None])
keep_prob_5 = tf.placeholder(tf.float32)
keep_prob_75 = tf.placeholder(tf.float32)
#权重函数
def weightVariable(shape):
#从服从指定正太分布的数值中取出指定大小的数组
init = tf.random_normal(shape, stddev=0.01)
#定义了变量后的初始化变量
return tf.Variable(init)
#bais函数
def biasVariable(shape):
#从服从指定正太分布的数值中取出指定大小的数组
init = tf.random_normal(shape)
#定义了变量后的初始化变量
return tf.Variable(init)
#卷积函数
def conv2d(x, W):
#以W为卷积核，步长为1没有填充进行卷积
return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME') #返回卷积后的值
#池化层函数
def maxPool(x):
#以2x2为池化曾核的大小，以步长为2进行下采样
return tf.nn.max_pool(x, ksize=[1, 2, 2, 1], strides=[1, 2, 2, 1], padding='SAME')
# 减少过拟合函数，随机让某些权重不更新
def dropout(x, keep):
return tf.nn.dropout(x, keep)
#卷积层构建函数
def cnnLayer(classnum):
# 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/卷积核的个数(32)
b1 = biasVariable([32]) # 设置权重
conv1 = tf.nn.relu(conv2d(x_data, W1) + b1) # 进行卷积并对其进行非线性化处理
pool1 = maxPool(conv1) # 进行池化曾操作
# 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*8*64, 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
#训练函数的设置
def train(train_x, train_y, tfsavepath):
''' train'''
log.debug('train')
out = cnnLayer(train_y.shape[1]) #进行卷及处理
#softmax_cross_entropy_with_logits计算loss是代价值，也就是我们要最小化的值
#对所有损失求平均
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out, labels=y_data))
#最速下降法让交叉熵下降，步长为0.01
train_step = tf.train.AdamOptimizer(0.01).minimize(cross_entropy)
#查看目标判断是否准确
accuracy = tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out, 1), tf.argmax(y_data, 1)), tf.float32))
#训练模型的保存
saver = tf.train.Saver()
with tf.Session() as sess: #开启一个会话
sess.run(tf.global_variables_initializer()) #初始化模型的所有参数
batch_size = 10
num_batch = len(train_x) // 10 #返回其整数结果
for n in range(10):
r = np.random.permutation(len(train_x)) #返回一个新的数组
train_x = train_x[r, :]
train_y = train_y[r, :]
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]
_, loss = sess.run([train_step, cross_entropy],\
feed_dict={x_data:batch_x, y_data:batch_y,
keep_prob_5:0.75, keep_prob_75:0.75})
print(n*num_batch+i, loss)
# 获取测试数据的准确率
acc = accuracy.eval（{x_data:train_x, y_data:train_y, keep_prob_5:1.0, keep_prob_75:1.0})
print('after 10 times run: accuracy is ', acc)
saver.save(sess, tfsavepath)
def validate(test_x, tfsavepath):
''' validate '''
output = cnnLayer(2)
#predict = tf.equal(tf.argmax(output, 1), tf.argmax(y_data, 1))
predict = output
saver = tf.train.Saver()
with tf.Session() as sess:
saver.restore(sess, tfsavepath)
res = sess.run([predict, tf.argmax(output, 1)],
feed_dict={x_data: test_x,
keep_prob_5:1.0, keep_prob_75: 1.0})
return res
if __name__ == '__main__':
pass
#实现人脸检测的程序 defined_face.py
#coding=utf-8
import os
import logging as log
import matplotlib.pyplot as plt
import common
import numpy as np
from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf
import cv2
import tensorflow_face_conv as myconv
def createdir(*args):
''' create dir'''
for item in args:
if not os.path.exists(item):
os.makedirs(item)
IMGSIZE = 64
def getpaddingSize(shape):
''' get size to make image to be a square rect '''
h, w = shape
longest = max(h, w)
result = (np.array([longest]*4, int) - np.array([h, h, w, w], int)) // 2
return result.tolist()
def dealwithimage(img, h=64, w=64):
''' dealwithimage '''
#img = cv2.imread(imgpath)
top, bottom, left, right = getpaddingSize(img.shape[0:2])
img = cv2.copyMakeBorder(img, top, bottom, left, right, cv2.BORDER_CONSTANT, value=[0, 0, 0])
img = cv2.resize(img, (h, w))
return img
def relight(imgsrc, alpha=1, bias=0):
'''relight'''
imgsrc = imgsrc.astype(float)
imgsrc = imgsrc * alpha + bias
imgsrc[imgsrc < 0] = 0
imgsrc[imgsrc > 255] = 255
imgsrc = imgsrc.astype(np.uint8)
return imgsrc
def getface(imgpath, outdir):
''' get face from path file'''
filename = os.path.splitext(os.path.basename(imgpath))[0]
img = cv2.imread(imgpath)
path="F:\haar_like\haarcascades\haarcascade_frontalface_default.xml"
haar = cv2.CascadeClassifier(path)
gray_img = cv2.cvtColor(img, cv2.COLOR_BGR2GRAY)
faces = haar.detectMultiScale(gray_img, 1.3, 5)
n = 0
for f_x, f_y, f_w, f_h in faces:
n += 1
face = img[f_y:f_y+f_h, f_x:f_x+f_w]
# may be do not need resize now
#face = cv2.resize(face, (64, 64))
face = dealwithimage(face, IMGSIZE, IMGSIZE)
for inx, (alpha, bias) in enumerate([[1, 1], [1, 50], [0.5, 0]]):
facetemp = relight(face, alpha, bias)
cv2.imwrite(os.path.join(outdir, '%s_%d_%d.jpg' % (filename, n, inx)), facetemp)
#从文件目录获取所有文件的函数
def getfilesinpath(filedir):
#获得一个路径下面所有的文件路径
for (path, dirnames, filenames) in os.walk(filedir):
for filename in filenames:
#判断是否为.jpg结尾的图片
if filename.endswith('.jpg'):
yield os.path.join(path, filename)
for diritem in dirnames:
getfilesinpath(os.path.join(path, diritem))
#得到图片中的面部函数
def generateface(pairdirs):
''' generate face '''
for inputdir, outputdir in pairdirs:
for name in os.listdir(inputdir):
inputname, outputname = os.path.join(inputdir, name), os.path.join(outputdir, name)
if os.path.isdir(inputname):
createdir(outputname)
for fileitem in getfilesinpath(inputname):
getface(fileitem, outputname)
#读取图片并生成列表
def readimage(pairpathlabel):
'''read image to list'''
imgs = []
labels = []
for filepath, label in pairpathlabel:
for fileitem in getfilesinpath(filepath):
#从路径中读取图片
img = cv2.imread(fileitem)
#进行列表拼接
imgs.append(img)
labels.append(label)
return np.array(imgs), np.array(labels)#返回数组列表
#获得一个矩阵
def onehot(numlist):
b = np.zeros([len(numlist), max(numlist)+1])
b[np.arange(len(numlist)), numlist] = 1
return b.tolist()
def getfileandlabel(filedir):
dictdir = dict([[name, os.path.join(filedir, name)] \
for name in os.listdir(filedir) if os.path.isdir(os.path.join(filedir, name))])
dirnamelist, dirpathlist = dictdir.keys(), dictdir.values()
indexlist = list(range(len(dirnamelist)))
return list(zip(dirpathlist, onehot(indexlist))), dict(zip(indexlist, dirnamelist))
def main(_):
savepath = 'F:/ml/image/checkpoint/face.ckpt'
isneedtrain = False
if os.path.exists(savepath+'.meta') is False:
isneedtrain = True
if isneedtrain:
#first generate all face
log.debug('generateface')
generateface([['F:/ml/image/trainfaces', 'F:/ml/image/trainfaces']])
pathlabelpair, indextoname = getfileandlabel('F:/ml/image/trainfaces')
train_x, train_y = readimage(pathlabelpair)
train_x = train_x.astype(np.float32) / 255.0
log.debug('len of train_x : %s', train_x.shape)
myconv.train(train_x, train_y, savepath)
log.debug('training is over, please run again')
else:
testfromcamera(savepath)
#print(np.column_stack((out, argmax)))
def testfromcamera(chkpoint):
camera = cv2.VideoCapture(0)
path="F:\haar_like\haarcascades\haarcascade_frontalface_default.xml"
haar = cv2.CascadeClassifier(path)
pathlabelpair, indextoname = getfileandlabel('F:/ml/image/trainfaces')
output = myconv.cnnLayer(len(pathlabelpair))
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), (0, 0, 255), 3)
n+=1
cv2.imshow('img', img)
key = cv2.waitKey(30) & 0xff
if key == 27:
break
else:
break
camera.release()
cv2.destroyAllWindows()
if __name__ == '__main__':
# first generate all face
main(0)
testfromcamera(checkpoint)在此基于tensorflow框架的搭建已经完成，但我还是不满足，我想基于代码不借助框架实现图片的识别。后面我会继续更新不解与框架识别的代码。
本文章为转载内容，我们尊重原作者对文章享有的著作权。如有内容错误或侵权问题，欢迎原作者联系我们进行内容更正或删除文章。
