Face Detection and Alignment with MTCNN 人脸检测对齐快速实现 Python代码

旧城等待， 2022-05-13 02:20 164阅读 0赞

论文[Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks][]提出了一种多任务-级联的卷积神经网络框架，用以实现人脸检测和对齐。构成人脸检测和对齐的级联网络的三个部分分别为：P-Net，R-Net和O-Net.  
(1)P-Net：Proposal Net，用于实现人脸候选框提取；  
(2)R-Net：Refine Net，在P-Net输出结果的基础上进一步去除错误的候选框；  
(3)O-Net：Output Net，与R-Net类似，最终输出人脸bounding box以及landmark。

本篇介绍通过一个Python的mtcnn包快速实现一个人脸检测和对齐程序。

环境:

Ubuntu16.04 / python3.6 / tensorflow 1.10.1 / opencv 3.4

通过pip安装mtcnn:

$pip install mtcnn

安装完成后可以使用mtcnn的detect\_faces方法实现图片中的人脸检测与对齐，代码实现：

from mtcnn.mtcnn import MTCNN
    import cv2
    
    img = cv2.imread("test.jpg")
    detector = MTCNN()
    
    face_list = detector.detect_faces(img) # face detect and alignment
    
    for face in face_list:
        box = face["box"]
        confidence = face["confidence"]
        keypoints = face["keypoints"]
        
        # draw boundingbox
        x,y,w,h = box
        cv2.rectangle(img,(x,y),(x+w,y+h),(0,255,0),2)
        
        # put the confidence
        cv2.putText(img,str(round(confidence,4)),(x,y-10),0,0.5,(255,0,0))
        
        # draw keypoints
        cv2.circle(img,keypoints["left_eye"],1,(0,0,255),2)
        cv2.circle(img,keypoints["right_eye"],1,(0,0,255),2)
        cv2.circle(img,keypoints["nose"],1,(0,0,255),2)
        cv2.circle(img,keypoints["mouth_left"],1,(0,0,255),2)
        cv2.circle(img,keypoints["mouth_right"],1,(0,0,255),2)
       
    cv2.imwrite("result.jpg",img)

测试结果：  
![这里写图片描述][70]

[Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks]: https://arxiv.org/pdf/1604.02878.pdf
[70]: /images/20220513/9d6efa73953846be83e4daa283998350.png