编号：A343
大小：149M
环境：Python3.7、OpenCV4.5、dlib、Pycharm2020
简介：利用 Python 开发，借助 Dlib 库捕获摄像头中的人脸，提取人脸特征，通过计算特征值之间的欧氏距离，来和预存的人脸特征进行对比，判断是否匹配，达到人脸识别的目的；

– 完成的功能

– 新的人脸数据集和识别模型

– 做到视频识别， 实时显示人脸信息

– 可摄像头添加人脸， 且可改名

– 可通过文件夹方式批量添加人脸

– GUI化， 基本无卡顿

.. image:: introduction/main_interface.png

:align: center

.. image:: introduction/main_figure_interface.png

:align: center

关于算法：

– 基于 Residual Neural Network / 残差网络的 CNN 模型;

– This model is a ResNet network with 29 conv layers. It’s essentially a version of the ResNet-34 network from the paper Deep Residual Learning for Image Recognition by He, Zhang, Ren, and Sun with a few layers removed and the number of filters per layer reduced by half.

实现流程：

– 安装依赖库

– 进行人脸信息采集录入

– 提取所有录入人脸数据存入 “features_all.csv”

– 调用摄像头进行实时人脸识别

关于代码：

#. 树状图:

├── main_interface.py # Step0. Start First

├── get_faces_from_camera.py # Step1. Faces register

├── features_extraction_to_csv.py # Step2. Features extraction

├── face_reco_from_camera.py # Step3. Faces recognition

├── how_to_use_camera.py # Use the default camera by opencv

├── data

│ ├── data_dlib # Dlib’s model

│ │ ├── dlib_face_recognition_resnet_model_v1.dat

│ │ ├── shape_predictor_5_face_landmarks.dat

│ │ └── shape_predictor_68_face_landmarks.dat

│ ├── data_faces_from_camera # Face images captured from camera (will generate after step 1)

│ │ ├── person_1

│ │ │ ├── img_face_1.jpg

│ │ │ └── img_face_2.jpg

│ │ └── person_2

│ │ └── img_face_1.jpg

│ │ └── img_face_2.jpg

│ └── features_all.csv # CSV to save all the features of known faces (will generate after step 2)

├── introduction # Some files for readme.rst

│ ├── main_figure_interface.png

│ ├── main_interface.png

│ └── overview.png

└── requirements.txt # Some python packages needed

用到的 Dlib 相关模型函数:

#. Dlib 正向人脸检测器 (based on HOG), output:

.. code-block:: python

detector = dlib.get_frontal_face_detector()

faces = detector(img_gray, 0)

#. Dlib 人脸预测器, output: ,

will use shape_predictor_68_face_landmarks.dat

.. code-block:: python

# This is trained on the ibug 300-W dataset (https://ibug.doc.ic.ac.uk/resources/facial-point-annotations/)

# Also note that this model file is designed for use with dlib’s HOG face detector.

# That is, it expects the bounding boxes from the face detector to be aligned a certain way, the way dlib’s HOG face detector does it.

# It won’t work as well when used with a face detector that produces differently aligned boxes,

# such as the CNN based mmod_human_face_detector.dat face detector.

predictor = dlib.shape_predictor(“data/data_dlib/shape_predictor_68_face_landmarks.dat”)

shape = predictor(img_rd, faces[i])

#. 特征描述子 Face recognition model, the object maps human faces into 128D vectors

.. code-block:: python

face_rec = dlib.face_recognition_model_v1(“data/data_dlib/dlib_face_recognition_resnet_model_v1.dat”)

源码介绍:

#. get_face_from_camera.py:

进行 Face register / 人脸信息采集录入

* 请注意存储人脸图片时，矩形框不要超出摄像头范围，要不然无法保存到本地;

* 超出会有 “out of range” 的提醒;

#. features_extraction_to_csv.py:

从上一步存下来的图像文件中，提取人脸数据存入CSV;

* 会生成一个存储所有特征人脸数据的 “features_all.csv”；

* size: n*128 , n means n people you registered and 128 means 128D features of the face

#. face_reco_from_camera.py:

这一步将调用摄像头进行实时人脸识别; / This part will implement real-time face recognition;

* Compare the faces captured from camera with the faces you have registered which are saved in “features_all.csv”

* 将捕获到的人脸数据和之前存的人脸数据进行对比计算欧式距离, 由此判断是否是同一个人;

运行展示

配套文件

我们提供完整项目文件清单如下：
文件目录
├ 1.项目源码
├ 2.运行截图
└ 3.演示视频