python+OpenCV+TensorFlow实现人脸识别
一个简单的小demo，不太会用GitHub，所以代码直接贴上来。
第一步，获取自己的照片，我们生成10000张，大小都是64*64，下面是生成图片的代码，
import cv2 import os import sys import random out_dir='./my_faces' if not os.path.exists(out_dir): os.makedirs(out_dir) #改变亮度和对比度 def relight(img,alpha=1,bias=0): w, h = img.shape[:2] for i in range(0,w): for j in range(0,h): for c in range(3): tmp=int(img[i,j,c]*alpha+bias) if tmp>255: tmp=255 elif tmp<0: tmp=0 img[i,j,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.' % str(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) ''' #改变图像的亮度，增加图像的对比性，可以识别不同光源下的人脸 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
第二步、处理其他人的照片，同样大小是64*64，图集是在网上下载的，我也上传上来，先看存放格式
接下来放代码：
import sys import os import cv2 input_path='lfw/lfw' output_dir='other_faces' size=64 if not os.path.exists(output_dir): os.makedirs(output_dir) #获取分类器 haar=cv2.CascadeClassifier('haarcascade_frontalface_default.xml') index=1 #返回路径，文件夹名称，文件名称 for (path,dirnames,filenames) in os.walk(input_path): for filename in filenames: if filename.endswith('.jpg'): print('being processed picture %s' % str(index)) img_path=path+'/'+filename # print(img_path) #从文件中读取图片 img=cv2.imread(img_path) #转为灰度图片 gray_img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) #使用haar 进行人脸检测 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] #统一保存为64*64格式 face=cv2.resize(face,(size,size)) cv2.imshow('img',face) cv2.imwrite(output_dir+'/'+str(index)+'.jpg',face) index+=1 if index==10000: sys.exit(0) key=cv2.waitKey(30)&0xff if key==27: sys.exit(0)
第三步、完成了数据集的处理，我们可以训练自己的模型了。
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) #添加标签，根据路径判别类别 if path==my_faces_path: labs.append([0,1]) else: labs.append([1,0]) # labs.append(path) readData(my_faces_path) readData(other_faces_path) #将图片数据和标签转换成数组 imgs=np.array(imgs) # print(imgs) #处理标签 labs=np.array([0,1] if lab==my_faces_path else [1,0] for lab in labs) # print(labs) #随机划分测试集和训练集 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))) #分批次 每个批次取100张 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) #随机权值向量 def weightVariable(shape): init = tf.random_normal(shape,stddev=0.01) return tf.Variable(init) #随机偏置向量 def baisVariable(shape): init=tf.random_normal(shape) return tf.Variable(init) #定义卷积函数 def conv2d(x,W): return tf.nn.conv2d(x,W,strides=[1,1,1,1],padding='SAME') #定义最大池化 def maxPool(x): return tf.nn.max_pool(x,ksize=[1,2,2,1],strides=[1,2,2,1],padding='SAME') #定义丢失函数 def dropout(x,keep): return tf.nn.dropout(x,keep) #建立cnn训练模型 def cnnLayer(): #第一层 #卷积核大小（3,3） 通道是3 输出通道32 W1=weightVariable([3,3,3,32]) b1=baisVariable([32]) #卷积 conv1=tf.nn.relu(conv2d(x,W1)+b1) #池化 pool1=maxPool(conv1) #减少过拟合，随机让某些权值不更新 drop1=dropout(pool1,keep_prob_5) #第二层 W2=weightVariable([3,3,32,64]) b2=baisVariable([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=baisVariable([64]) conv3=tf.nn.relu(conv2d(drop2,W3)+b3) pool3=maxPool(conv3) drop3=dropout(pool3,keep_prob_5) #全连接层 Wf=weightVariable([64*64,512]) bf=baisVariable([512]) #将特征图展开 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.add(tf.matmul(dropf,Wout),bout) return out def cnnTrain(): out =cnnLayer() #损失函数 cross_entropy=tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out,labels=y_)) #优化器 train_step=tf.train.AdamOptimizer(0.01).minimize(cross_entropy) #比较标签是否相等，再求得所有数的平均值 accuaracy=tf.reduce_mean(tf.cast(tf.equal(tf.argmax(out,1),tf.argmax(y_,1)),tf.float32)) #将loss与accuary 保存以供tensorboard使用 tf.summary.scalar('loss',cross_entropy) tf.summary.scalar('accuracy',accuaracy) #使用merge_all 可以管理我们的summary 但是容易出错 merged_summary_op=tf.summary.merge_all() #数据保存器初始化 saver=tf.train.Saver() with tf.Session(config=tf.ConfigProto(log_device_placement=True)) as sess: #初始化所有向量 sess.run(tf.global_variables_initializer()) summary_writer=tf.summary.FileWriter('./tmp',graph=tf.get_default_graph()) index=0 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('次数 %d ,lossing: %.4f' % (n*num_batch+i,loss)) if (n*num_batch+i)%100==0: #获取测试数据的准确率 acc=sess.run(accuaracy,feed_dict={x:test_x,y_:test_y,keep_prob_5:1.0,keep_prob_75:1.0}) print('次数 %d , 准确率: %.4f' % (n*num_batch+i,acc)) #当准确率连续十次大于0.99时 保存并退出 if acc>0.99: index+=1 else: index=0 if index>10: # model_path=os.path.join(os.getcwd(),'train_faces.model') saver.save(sess,'./tmp/train_faces.model',global_step=n*num_batch+i) sys.exit(0) print('accuary less 0.99,exited!') cnnTrain()
第四步、我们读取模型，开始识别是否是我自己了，完活收工。
import tensorflow as tf import sys import os import numpy as np import random import cv2 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 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) #将图片方法，扩充图片的边缘部分 img=cv2.copyMakeBorder(img,top,bottom,left,right,cv2.BORDER_CONSTANT,value=[0,0,0]) img=cv2.resize(img,(h,w)) imgs.append(img) if path==my_faces_path: labs.append([0,1]) else: labs.append([1,0]) readData(my_faces_path) readData(other_faces_path) #将图片数据转换成数组 imgs=np.array(imgs) #随机划分测试集和训练集 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) #将数据转成成小于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))) #批次 batch_size=128 num_batch=len(train_x)//128 x=tf.placeholder(tf.float32,shape=[None,size,size,3]) y_=tf.placeholder(tf.float32,shape=[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 #卷积核大小（3.3） 输入通道3 输出32 W1=weightVariable([3,3,3,32]) b1=biasVariable([32]) conv1=tf.nn.relu(conv2d(x,W1)+b1) pool1=maxPool(conv1) 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 # [宽*高，要提取的纬度] Wf=weightVariable([64*64,512]) bf=biasVariable([512]) drop3_flat=tf.reshape(drop3,[-1,64*64]) dense=tf.nn.relu(tf.matmul(drop3_flat,Wf)+bf) dropf=dropout(dense,keep_prob_5) #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('tmp/')) 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OpenCV 检测人脸 haar=cv2.CascadeClassifier('haarcascade_frontalface_default.xml') camera=cv2.VideoCapture(0) flag=1 while True: _,img=camera.read() gray_img=cv2.cvtColor(img,cv2.COLOR_BGR2GRAY) faces=haar.detectMultiScale(gray_img,1.3,5) if not len(faces): cv2.imshow('img',img) key=cv2.waitKey(30)&0xff if key==27: sys.exit(0) #标记矩形框 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,(size,size)) flag+=1 if is_my_face(face): print('嗨，张先生，我认出你了') cv2.imwrite('test_faces/' + str(flag) + '.jpg', face) cv2.rectangle(img,(f_x,f_y),(f_x+f_w,f_y+f_h),(0,0,255),3) else: cv2.rectangle(img,(f_x,f_y),(f_x+f_w,f_y+f_h),(255,0,0),3) cv2.imshow('image',img) key=cv2.waitKey(30)&0xff if key==27: sys.exit(0) sess.close()
让我们来看看效果，如果是我的脸用红色框标记，如果不是我的脸用蓝色框标记：
完整代码：下载地址