face_recognition人脸识别项目

本项目的人脸识别是基于业内领先的C++开源库 dlib中的深度学习模型，用Labeled Faces in the Wild人脸数据集进行测试，有高达99.38%的准确率。但对小孩和亚洲人脸的识别准确率尚待提升。

环境配置：基于windows10下

dlib 19.7.0
dlib-19.7.0-cp36-cp36m-win_amd64.whl
pip install dlib-19.7.0-cp36-cp36m-win_amd64.whl

python 3.6
face-recognition 1.3.0
face-recognition-models 0.3.0
numpy 1.19.5
opencv-python 4.4.0
Pillow 8.1.2``
scipy 1.5.4

import face_recognition
import cv2
import numpy as np

# This is a demo of running face recognition on live video from your webcam. It's a little more complicated than the
# other example, but it includes some basic performance tweaks to make things run a lot faster:
#   1. Process each video frame at 1/4 resolution (though still display it at full resolution)
#   2. Only detect faces in every other frame of video.

# PLEASE NOTE: This example requires OpenCV (the `cv2` library) to be installed only to read from your webcam.
# OpenCV is *not* required to use the face_recognition library. It's only required if you want to run this
# specific demo. If you have trouble installing it, try any of the other demos that don't require it instead.

# Get a reference to webcam #0 (the default one)
#video_capture = cv2.VideoCapture(0)
#url='rtsp://admin:1qaz2wsx@192.168.3.2:554/h264/ch35/sub/av_stream'
#cap=cv2.VideoCapture(url)
#input_movie = cv2.VideoCapture("abama.mp4")
#input_movie = cv2.VideoCapture("demo1.mp4")
input_movie = cv2.VideoCapture("demo2.mp4")
length = int(input_movie.get(cv2.CAP_PROP_FRAME_COUNT))


# 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