python 人脸识别

╰半橙微兮° 2022-05-16 07:57 206阅读 0赞

python版本 3.7.0  
![这里写图片描述][70]

# 1、 安装 cmake #

pip install cmake  
![这里写图片描述][70 1]

# 2、安装 boost #

pip install boost  
![这里写图片描述][70 2]

# 3、安装 dlib #

pip install dlib  
![这里写图片描述][70 3]

# 4、安装 face\_recognition #

pip install face\_recognition  
![这里写图片描述][70 4]

# 5、验证 #

face\_recognition 本地模型路径 要识别图片路径  
输出：文件名 识别的人名  
![这里写图片描述][70 5]

注意：**文件名以人名命名**  
![这里写图片描述][70 6]

# 6、寻找人脸位置 #

face\_detection “路径”  
输出：人脸像素坐标  
![这里写图片描述][70 7]

# 7、调整灵敏度 #

face\_recognition –tolerance 灵敏度 本地模型路径 要识别图片路径  
注：**默认0.6,识别度越低识别难度越高**  
![这里写图片描述][70 8]

# 8、计算每次面部距离 #

face\_recognition –show-distance true 本地模型路径 要识别图片路径  
![这里写图片描述][70 9]

# 9、只是想知道每张照片中人物的姓名，却不关心文件名，可以这样做： #

face\_recognition 本地模型路径 要识别图片路径 | cut -d ‘,’ -f2

![这里写图片描述][70 10]

# 10、加速识别 #

face\_recognition –cpus 使用内核数 本地模型路径 要识别图片路径  
使用四核识别：  
face\_recognition –cpus 4 本地模型路径 要识别图片路径  
![这里写图片描述][70 11]  
使用全部内核识别：  
face\_recognition –cpus -1 本地模型路径 要识别图片路径![这里写图片描述][70 12]

# 11、自动查找图像中的所有面孔 #

import face\_recognition

image = face\_recognition.load\_image\_file(“吴京.jpg”)  
face\_locations = face\_recognition.face\_locations(image)

# 12、识别图像中的面孔并识别他们是谁 #

import face_recognition
    
    picture_of_me = face_recognition.load_image_file("me.jpg")
    my_face_encoding = face_recognition.face_encodings(picture_of_me)[0]
    
    # my_face_encoding now contains a universal 'encoding' of my facial features that can be compared to any other picture of a face!
    
    unknown_picture = face_recognition.load_image_file("unknown.jpg")
    unknown_face_encoding = face_recognition.face_encodings(unknown_picture)[0]
    
    # Now we can see the two face encodings are of the same person with `compare_faces`!
    
    results = face_recognition.compare_faces([my_face_encoding], unknown_face_encoding)
    
    if results[0] == True:
        print("It's a picture of me!")
    else:
        print("It's not a picture of me!")

参考地址：  
[https://github.com/ageitgey/face\_recognition\#face-recognition][https_github.com_ageitgey_face_recognition_face-recognition]

[70]: /images/20220516/3979db39b4d4427ca65f925b8c706217.png
[70 1]: /images/20220516/cf5e8f5f09a24c3b82454537d07e22f5.png
[70 2]: /images/20220516/f5efbf905923488386f903136ccc091d.png
[70 3]: /images/20220516/075b86d067b84f84a693a635585efea1.png
[70 4]: /images/20220516/86486755b2fd4b1bbd738d21c3bedea0.png
[70 5]: /images/20220516/7b96e777721b42be8c00a1b0ea9a1047.png
[70 6]: /images/20220516/e3f9a2bb29d046abbf98f7aebf7b88f6.png
[70 7]: /images/20220516/8d8e4392246c4bbc996fb43f41ecaf17.png
[70 8]: /images/20220516/38647d19b1244d53955ca969ba187736.png
[70 9]: /images/20220516/bb90e4ea4bad4cbaa2c5e0a90893d08e.png
[70 10]: /images/20220516/1a9fb7b2f1de4941a060766df09dd9c3.png
[70 11]: /images/20220516/cbf905f39ca040358ad8b60ff16d6f03.png
[70 12]: /images/20220516/f2d350c62f7b44549557d1a849efd7c7.png
[https_github.com_ageitgey_face_recognition_face-recognition]: https://github.com/ageitgey/face_recognition#face-recognition