Coder Social home page Coder Social logo

face_recognizer's Introduction

Face Recognizer on Jetson

*** Copy Right 2020 Kevin Yu. All rights reserved.

*** Author: Kevin Yu

*** Update Time: 2020/05/24

*** Contact: [email protected]

This repo demonstrates how to use Dlib, a powerful Object Detection library, to detect and identify faces in real-time. Dlib is able to compile with CUDA, which means, the detector can run with GPU on the Jetson. All the demos below are tested on my Jetson AGX Xavier DevKit, it should also work on other Jetson Platforms such as the Jetson Nano and the Jetson TX2.

*** Notes: You may find more detailed description of the project HERE

Table of Contents

Demo

Live-Demo

Prerequisite

Dependencies

The Face Detection API depends on the following libraries:

  • Dlib
  • Face_recognition
  • Pickle
  • OpenCV

Notes:

OpenCV and Pickle are pre-installed with JetPack, so do not need to reinstalled.

For detailed steps to install Dlib and Face_recognition module, follow the Dlib installation instructions in the Setup section.

Setup

$ cd ~
$ git clone https://github.com/yqlbu/face_recognizer
$ cd face_recognizer/
$ sudo chmod +x setup.sh
$ ./setup.sh

How To Use

Train the custom dataset

Notes: you may customize the dataset inside /images based on your own need. To do so, you need to correctly name the image file for each image inside /images.

$ python3 training.py

Recognize unknown faces

$ python3 recognizer.py

Run the detector to identify faces of an input image

$ python3 detector.py

Run the detector in real-time to identify faces of an input stream

Notes: the input sources are not limited to Camera stream, but any form of MJPEG stream such as Video, RTSP, and HTTP Stream

$ python3 live-demo.py

Reference

Inspired by Paul McWhorter [source]

face_recognizer's People

Contributors

piyoki avatar

Stargazers

 avatar  avatar

Watchers

 avatar  avatar

face_recognizer's Issues

Video face recognization by deepstreamSDK?

Hi,
I run this project sucessfully, thank you for sharing. I got 7~8 FPS(live-demo.py) on Nvidia Jetson AGX Xavier, I think performance will improve with deepstreamSDK. Do you know how to set up video face recognization by deepstreamSDK and your project?

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.