1、window安装dlib、face_recognition

ace_recognition简介

face_recognition是Python的一个开源人脸识别库，支持Python 3.3+和Python 2.7。引用官网介绍：

Recognize and manipulate faces from Python or from the command line with the world's simplest face recognition library.

安装配置

我目前的开发环境是，操作系统：Win10，Python3.6：Anaconda集成开发环境。在安装 face_recognition的过程中花费了一些时间，所以把安装过程记录下来。

使用pip安装

pip install face_recognition

如果安装失败了，那基本上是因为依赖的dlib库安装失败了，需要手动安装。网上介绍的安装dlib库的方法大都很复杂，需要下载源代码，然后手动编译。

安装dlib

1、下载

dlib-19.8.1-cp36-cp36m-win_amd64.whl

2、安装

pip install dlib-19.8.1-cp36-cp36m-win_amd64.whl

pip install dlib

pip show dlib #验证dlib是否安装成功

安装face_recognition_models

1、下载 face_recognition_models 0.3.0

2、解压压缩包，进入face_recognition_models-0.3.0目录，安装

python setup.py install

pip show face_recognition_models

安装face_recognition

1、下载 face_recognition 1.0.0

2、解压压缩包，进入face_recognition目录，安装

python setup.py install

pip show face_recognition

2、下载代码

https://github.com/ageitgey/face_recognition.git

3、运行代码

facerec_from_webcam.py

因为原有代码仅对摄像头进行读取，修改以下文件可以读取摄像头文件

# video_capture = cv2.VideoCapture("hamilton_clip.mp4")

video_capture = cv2.VideoCapture("rtsp://192.168.1.11:444/subtype=1&subchannanel=1")

# video_capture = cv2.VideoCapture(0, cv2.CAP_DSHOW)

# Load a sample picture and learn how to recognize it.

obama_image = face_recognition.load_image_file("obama.jpg")

obama_face_encoding = face_recognition.face_encodings(obama_image)[0]

# Load a second sample picture and learn how to recognize it.

biden_image = face_recognition.load_image_file("biden.jpg")

biden_face_encoding = face_recognition.face_encodings(biden_image)[0]

sungebingimage = face_recognition.load_image_file("sungebing.jpg")

sungebing_face_encoding = face_recognition.face_encodings(sungebingimage)[0]

ssjimage = face_recognition.load_image_file("ssj.jpg")

ssjimage_face_encoding = face_recognition.face_encodings(ssjimage)[0]

# Create arrays of known face encodings and their names

known_face_encodings = [

obama_face_encoding,

biden_face_encoding,

ssjimage_face_encoding,

sungebing_face_encoding

]

known_face_names = [

"Barack Obama",

"Joe Biden",

"sun shengjie",

"sungebing"

]

4、也可以在项目的最后将摄像头读取的视频转为视频流输出，通过web显示。