weilaweila / Dlib_face_detection_from_camera

Real-time facial landmarks detection / 摄像头人脸检测并进行特征点标定

Face detection with features points

Introduction

Detect faces from camera, and draw the 5/68 feature points of faces;

1. Use "shape_predictor_5_face_landmarks.dat", which is trained on the dlib 5-point face landmark dataset with 7198 faces. and identify the corners of the eyes and bottom of the nose:

   

2. Use "shape_predictor_68_face_landmarks.dat", which is trained on the ibug 300-W dataset (https://ibug.doc.ic.ac.uk/resources/facial-point-annotations/)

   This model is designed to work well with dlib's HOG face detector and the CNN face detector.

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

   

• Please install python packages: dlib and numpy at first:

pip3 install -r requirements.txt

About Source Code

Python 源码介绍如下:

1. Use camera in Python / Python OpenCv 调用摄像头;

   python3 how_to_use_camera.py:

2. Show the 68 features points from local images / 显示本地图像文件中的人脸特征;

   python3 get_features_from_images.py:

3. Real-time facial landmarks detect and draw feature points /这一步将调用摄像头进行实时人脸检测和特征点绘制;

   python3 get_features_from_camera.py:

More

Author: coneypo

Blog: https://www.cnblogs.com/AdaminXie/p/8472743.html

Mail: [e-mail]

AD: 用我的滴滴云 AI 大师推荐码: 7788, 购买滴滴云 GPU/vGPU/机器学习产品享 9 折优惠, 点击 https://www.didiyun.com/ 前往滴滴云官网

Thanks for your support.