# Dlib_face_recognition_from_camera

**Repository Path**: Eric_995/Dlib_face_recognition_from_camera

## Basic Information

- **Project Name**: Dlib_face_recognition_from_camera
- **Description**: Detect and recognize the faces from camera / 调用摄像头进行人脸识别，支持多张人脸同时识别
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 6
- **Created**: 2019-05-17
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

Face recognition from camera
############################

Introduction
************

Detect and recognize single/multi-faces from camera;

调用摄像头进行人脸识别，支持多张人脸同时识别;


#. 摄像头人脸录入 / Face register

   .. image:: introduction/get_face_from_camera.png
      :align: center

#. 提取特征建立人脸数据库 / Generate database from images captured
#. 利用摄像头进行人脸识别 / Face recognizer
   
   当单张人脸 / When single-face:
   
   .. image:: introduction/face_reco_single_person.png
      :align: center

   当多张人脸 / When multi-faces:
   
   .. image:: introduction/face_reco_two_people.png
      :align: center

** 关于精度 / About accuracy:

* When using a distance threshold of ``0.6``, the dlib model obtains an accuracy of ``99.38%`` on the standard LFW face recognition benchmark.


Steps
*****

#. 进行 face register / 人脸信息采集录入

   .. code-block:: python

      python3 get_face_from_camera.py

#. 提取所有录入人脸数据存入 features_all.csv

   .. code-block:: python

      python3 get_features_into_CSV.py

#. 调用摄像头进行实时人脸识别

   .. code-block:: python

      python3 face_reco_from_camera.py


*****************



#. 新增功能：摄像头可以录制视频






*****************

# OpenCv 调用摄像头
# 默认调用笔记本摄像头

import cv2

cap = cv2.VideoCapture(0)

# cap.set(propId, value)
# 设置视频参数: propId - 设置的视频参数, value - 设置的参数值
cap.set(3, 480)

# cap.isOpened() 返回 true/false, 检查摄像头初始化是否成功
print(cap.isOpened())

# cap.read()
""" 
返回两个值
    先返回一个布尔值, 如果视频读取正确, 则为 True, 如果错误, 则为 False; 
    也可用来判断是否到视频末尾;
    
    再返回一个值, 为每一帧的图像, 该值是一个三维矩阵;
    
    通用接收方法为: 
        ret,frame = cap.read();
        ret: 布尔值;
        frame: 图像的三维矩阵;
        这样 ret 存储布尔值, frame 存储图像;
        
        若使用一个变量来接收两个值, 如:
            frame = cap.read()
        则 frame 为一个元组, 原来使用 frame 处需更改为 frame[1]
"""

while cap.isOpened():
    ret_flag, img_camera = cap.read()
    cv2.imshow("camera", img_camera)

    # 每帧数据延时 1ms, 延时为0, 读取的是静态帧
    k = cv2.waitKey(1)

    # 按下 's' 保存截图
    if k == ord('s'):
        cv2.imwrite("test.jpg", img_camera)

    # 按下 'q' 退出
    if k == ord('q'):
        break

# 释放所有摄像头
cap.release()

# 删除建立的所有窗口
cv2.destroyAllWindows()



*****************

#  使用摄像头录制视频


# coding:utf-8
 	+import sys
 	+import cv2
 	+import warnings
 	+warnings.filterwarnings('ignore')
 	+face_cascade = cv2.CascadeClassifier(r'./haarcascade_frontalface_default.xml')
 	+#face_cascade.load('D:\\opencv\\haarcascades\\haarcascade_frontalface_default.xml')
 	+camear = cv2.VideoCapture(0)#用摄像头
 	+fps = 20
 	+## some videowriter props
 	+size = (int(camear.get(cv2.CAP_PROP_FRAME_WIDTH)),
 	+        int(camear.get(cv2.CAP_PROP_FRAME_HEIGHT)))
 	+videowriter = cv2.VideoWriter("test.mp4",-1,fps,size)
 	+while(1):
 	+    ret,frame = camear.read()
 	+    gray = cv2.cvtColor(frame,cv2.COLOR_BGR2GRAY)
 	+    faces = face_cascade.detectMultiScale(gray,1.3,5)
 	+    for (x,y,w,h) in faces:
 	+        img = cv2.rectangle(frame,(x,y),(x+w,y+h),(255,0,0),2)
 	+        roi_gray = gray[y:y+h,x:x+w]
 	+        cv2.imshow('camera',frame)
 	+        videowriter.write(frame)
 	+    if cv2.waitKey(5)&0xff ==27:
 	+            break
 	+camear.release()
 	+cv2.destroyAllWindows()