人臉識別是計算機視覺研究領域的一個熱點。而人臉識別包含了諸多步驟，其實現技術流程如下圖所示(摘自http://www.techshino.com/upfiles/images/%E4%BA%BA%E8%84%B8%E8%AF%86%E5%88%AB%E6%8A%80%E6%9C%AF%E6%B5%81%E7%A8%8B(2).png)：

       在上述過程中，人臉檢測是非常關鍵的一步，特別是在大多數應用場景條件下，監控視訊影象中問題包含了自然場景，而針對此類的應用，首要的是實現人臉檢測。

從上述原理圖可以看出，該模型由三個步驟組成：

步驟一：P-NET，該步驟主要生成了一堆候選區域的邊框，並採用NMS(非極大值)機制進行相應的合併。這與目標檢測過程中的原理類似。

步驟二：R-NET，即對步驟一的結果再進一步細劃，得到更精細的候選區域。

步驟三：O-NET，輸出結果。(人臉邊框和特徵點位置)

上述三個模型的具體卷積細節原理如下圖所示：

         下面基於Tensorflow進行實驗，其中MTCNN相應的程式碼如下所示：

class PNet(Network):
    def setup(self):
        (self.feed('data') #pylint: disable=no-value-for-parameter, no-member
             .conv(3, 3, 10, 1, 1, padding='VALID', relu=False, name='conv1')
             .prelu(name='PReLU1')
             .max_pool(2, 2, 2, 2, name='pool1')
             .conv(3, 3, 16, 1, 1, padding='VALID', relu=False, name='conv2')
             .prelu(name='PReLU2')
             .conv(3, 3, 32, 1, 1, padding='VALID', relu=False, name='conv3')
             .prelu(name='PReLU3')
             .conv(1, 1, 2, 1, 1, relu=False, name='conv4-1')
             .softmax(3,name='prob1'))

        (self.feed('PReLU3') #pylint: disable=no-value-for-parameter
             .conv(1, 1, 4, 1, 1, relu=False, name='conv4-2'))
        
class RNet(Network):
    def setup(self):
        (self.feed('data') #pylint: disable=no-value-for-parameter, no-member
             .conv(3, 3, 28, 1, 1, padding='VALID', relu=False, name='conv1')
             .prelu(name='prelu1')
             .max_pool(3, 3, 2, 2, name='pool1')
             .conv(3, 3, 48, 1, 1, padding='VALID', relu=False, name='conv2')
             .prelu(name='prelu2')
             .max_pool(3, 3, 2, 2, padding='VALID', name='pool2')
             .conv(2, 2, 64, 1, 1, padding='VALID', relu=False, name='conv3')
             .prelu(name='prelu3')
             .fc(128, relu=False, name='conv4')
             .prelu(name='prelu4')
             .fc(2, relu=False, name='conv5-1')
             .softmax(1,name='prob1'))

        (self.feed('prelu4') #pylint: disable=no-value-for-parameter
             .fc(4, relu=False, name='conv5-2'))

class ONet(Network):
    def setup(self):
        (self.feed('data') #pylint: disable=no-value-for-parameter, no-member
             .conv(3, 3, 32, 1, 1, padding='VALID', relu=False, name='conv1')
             .prelu(name='prelu1')
             .max_pool(3, 3, 2, 2, name='pool1')
             .conv(3, 3, 64, 1, 1, padding='VALID', relu=False, name='conv2')
             .prelu(name='prelu2')
             .max_pool(3, 3, 2, 2, padding='VALID', name='pool2')
             .conv(3, 3, 64, 1, 1, padding='VALID', relu=False, name='conv3')
             .prelu(name='prelu3')
             .max_pool(2, 2, 2, 2, name='pool3')
             .conv(2, 2, 128, 1, 1, padding='VALID', relu=False, name='conv4')
             .prelu(name='prelu4')
             .fc(256, relu=False, name='conv5')
             .prelu(name='prelu5')
             .fc(2, relu=False, name='conv6-1')
             .softmax(1, name='prob1'))

        (self.feed('prelu5') #pylint: disable=no-value-for-parameter
             .fc(4, relu=False, name='conv6-2'))

        (self.feed('prelu5') #pylint: disable=no-value-for-parameter
             .fc(10, relu=False, name='conv6-3'))

# 建立MTCNN模型
def create_mtcnn(sess, model_path):
    if not model_path:
        model_path,_ = os.path.split(os.path.realpath(__file__))

    with tf.variable_scope('pnet'):
        data = tf.placeholder(tf.float32, (None,None,None,3), 'input')
        pnet = PNet({'data':data})
        pnet.load(os.path.join(model_path, 'det1.npy'), sess)
    with tf.variable_scope('rnet'):
        data = tf.placeholder(tf.float32, (None,24,24,3), 'input')
        rnet = RNet({'data':data})
        rnet.load(os.path.join(model_path, 'det2.npy'), sess)
    with tf.variable_scope('onet'):
        data = tf.placeholder(tf.float32, (None,48,48,3), 'input')
        onet = ONet({'data':data})
        onet.load(os.path.join(model_path, 'det3.npy'), sess)
        
    pnet_fun = lambda img : sess.run(('pnet/conv4-2/BiasAdd:0', 'pnet/prob1:0'), feed_dict={'pnet/input:0':img})
    rnet_fun = lambda img : sess.run(('rnet/conv5-2/conv5-2:0', 'rnet/prob1:0'), feed_dict={'rnet/input:0':img})
    onet_fun = lambda img : sess.run(('onet/conv6-2/conv6-2:0', 'onet/conv6-3/conv6-3:0', 'onet/prob1:0'), feed_dict={'onet/input:0':img})
    return pnet_fun, rnet_fun, onet_fun