結合OpenCV與TensorFlow進行人臉識別

作爲新手來說，這是一個最簡單的人臉識別模型，難度不大，代碼量也不算多，下面就逐一來講解，數據集的準備就不多說了，因人而異。

一. 獲取數據集的所有路徑

利用os模塊來生成一個包含所有數據路徑的list

def my_face():
    path  = os.listdir("./my_faces")
    image_path = [os.path.join("./my_faces/",img) for img in path]
    return image_path
def other_face():
    path = os.listdir("./other_faces")
    image_path = [os.path.join("./other_faces/",img) for img in path]
    return image_path
image_path = my_face().__add__(other_face())   #將兩個list合併成爲一個list

二. 構造標籤

標籤的構造較爲簡單，1表示本人，0表示其他人。

 label_my= [1 for i in my_face()]
 label_other = [0 for i in other_face()]
 label = label_my.__add__(label_other)              #合併兩個list

三.構造數據集

利用tf.data.Dataset.from_tensor_slices()構造數據集，

def preprocess(x,y):
    x = tf.io.read_file(x)   #讀取數據
    x = tf.image.decode_jpeg(x,channels=3)  #解碼成jpg格式的數據
    x = tf.cast(x,tf.float32) / 255.0      #歸一化
    y = tf.convert_to_tensor(y)				#轉成tensor
    return x,y

data = tf.data.Dataset.from_tensor_slices((image_path,label))
data_loader = data.repeat().shuffle(5000).map(preprocess).batch(128).prefetch(1)

四.構造模型

class CNN_WORK(Model):
    def __init__(self):
        super(CNN_WORK,self).__init__()
        self.conv1 = layers.Conv2D(32,kernel_size=5,activation=tf.nn.relu)
        self.maxpool1 = layers.MaxPool2D(2,strides=2)
        
        self.conv2 = layers.Conv2D(64,kernel_size=3,activation=tf.nn.relu)
        self.maxpool2 = layers.MaxPool2D(2,strides=2)
        
        self.flatten = layers.Flatten()
        self.fc1 = layers.Dense(1024)
        self.dropout = layers.Dropout(rate=0.5)
        self.out = layers.Dense(2)
    
    def call(self,x,is_training=False):
        x = self.conv1(x)
        x = self.maxpool1(x)
        x = self.conv2(x)
        x = self.maxpool2(x)
        
        x = self.flatten(x)
        x = self.fc1(x)
        x = self.dropout(x,training=is_training)
        x = self.out(x)
   
        
        if not is_training:
            x = tf.nn.softmax(x)
        return x
model = CNN_WORK()

五.定義損失函數，精度函數，優化函數

def cross_entropy_loss(x,y):
    y = tf.cast(y,tf.int64)
    loss = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=y,logits=x)
    return tf.reduce_mean(loss)

def accuracy(y_pred,y_true):
    correct_pred = tf.equal(tf.argmax(y_pred,1),tf.cast(y_true,tf.int64))
    return tf.reduce_mean(tf.cast(correct_pred,tf.float32),axis=-1)
optimizer = tf.optimizers.SGD(0.002)    

六.開始跑步我們的模型

def run_optimizer(x,y):
    with tf.GradientTape() as g:
        pred = model(x,is_training=True)
        loss = cross_entropy_loss(pred,y)
    training_variabel = model.trainable_variables
    gradient = g.gradient(loss,training_variabel)
    optimizer.apply_gradients(zip(gradient,training_variabel))
model.save_weights("face_weight")  #保存模型    

最後跑的準確率還是挺高的。

七.openCV登場

最後利用OpenCV的人臉檢測模塊，將檢測到的人臉送入到我們訓練好了的模型中進行預測根據預測的結果進行標識。

cap = cv2.VideoCapture(0)

face_cascade = cv2.CascadeClassifier('C:\\Users\Wuhuipeng\AppData\Local\Programs\Python\Python36\Lib\site-packages\cv2\data/haarcascade_frontalface_alt.xml')

while True:
    ret,frame = cap.read()

    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)

    faces = face_cascade.detectMultiScale(gray,scaleFactor=1.2,minNeighbors=5,minSize=(5,5))

    for (x,y,z,t) in faces:
        img = frame[y:y+t,x:x+z]
        try:
            img = cv2.resize(img,(64,64))
            img = tf.cast(img,tf.float32) / 255.0
            img = tf.reshape(img,[-1,64,64,3])
        
            pred = model(img)
            pred = tf.argmax(pred,axis=1).numpy()
        except:
            pass
        if(pred[0]==1):
            cv2.putText(frame,"wuhuipeng",(x-10,y-10),cv2.FONT_HERSHEY_SIMPLEX,1.2,(255,255,0),2)
        
        cv2.rectangle(frame,(x,y),(x+z,y+t),(0,255,0),2)
    cv2.imshow('find faces',frame)
    if cv2.waitKey(1)&0xff ==ord('q'):
        break
cap.release()
cv2.destroyAllWindows()

完整代碼地址github.

Thank for your read！！！