python+opencv实现人脸识别笔记四（识别出人脸）

我们需要调用保存的训练模型来识别人脸，话不多说直接上代码。
新建 识别出我.py

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 = '/home/dong/PycharmProjects/untitled/人脸识别/data/me'
other_faces_path = '/home/dong/PycharmProjects/untitled/人脸识别/data/zhang'
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)  

这些代码都和上一篇中的相同
最主要的是接下来的代码。
继续添加

saver = tf.train.Saver()  
sess = tf.Session()  
saver.restore(sess, tf.train.latest_checkpoint('/home/dong/PycharmProjects/untitled/FaceRecognition-tensorflow/模型'))
   
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  
cv2.namedWindow("识别")

# 视频来源，可以来自一段已存好的视频，也可以直接来自USB摄像头
cap = cv2.VideoCapture("/home/dong/Videos/meimei/13.mp4")

# 告诉OpenCV使用人脸识别分类器
classfier = cv2.CascadeClassifier(
    "/home/dong/PycharmProjects/untitled/venv/lib/python3.6/site-packages/cv2/data/haarcascade_frontalface_alt2.xml")

# 识别出人脸后要画的边框的颜色，RGB格式
color = (0, 0, 0)

while cap.isOpened():
    ok, frame = cap.read()  # 读取一帧数据
    if not ok:
        break

            # 将当前帧转换成灰度图像
    grey = cv2.cvtColor(frame, cv2.COLOR_BGR2GRAY)

    # 人脸检测，1.2和2分别为图片缩放比例和需要检测的有效点数
    faceRects = classfier.detectMultiScale(grey, 1.3, 5)
    if len(faceRects) > 0:  # 大于0则检测到人脸
        for faceRect in faceRects:  # 单独框出每一张人脸
            x1, y1, w1, h1 = faceRect
            face = frame[y1 - 10: y1 + h1 + 10, x1 - 10: x1 + w1 + 10]
            faces = cv2.resize(face, (size, size))
            print(is_my_face(faces))
            b = is_my_face(faces)
            cv2.rectangle(frame, (x1 - 10, y1 - 10), (x1 + w1 + 10, y1 + h1 + 10), color, 2)
            font = cv2.FONT_HERSHEY_SIMPLEX
            if b == True:
                cv2.putText(frame, "name:%s" % ("dong"), (x1 + 30, y1 + 30), font, 1, (255, 0, 255), 4)
            else:
                cv2.putText(frame, "name:%s" % ("tan"), (x1 + 30, y1 + 30), font, 1, (255, 0, 255), 4)
        # 显示图像
    cv2.imshow("识别", frame)
    c = cv2.waitKey(10)
    if c & 0xFF == ord('q'):  # 如果强制停止执行程序，结束视频放映
        break

        # 释放摄像头并销毁所有窗口
cap.release()
cv2.destroyAllWindows()
print(faceRects)


sess.close()

如果出现了TypeError: Cannot interpret feed_dict key as Tensor: Can not convert a float into a Tensor.
改错：
查看是否重用了y，x和keep_prob。。。有重用的地方，改另外的变量即可。。

现在给出我的识别结果