使用人脸识别、机器学习、Redis、Python、Streamlit构建一个全面的考勤系统web应用程序,本课程旨在教你如何使用人脸识别技术创建一个完整的考勤系统。您将学习人脸识别、图像处理和机器学习算法的原理,这些原理能够创建准确可靠的考勤系统。在整个课程中,你将使用Python编程语言和各种库,如OpenCV、Numpy、Pandas、Insightface、Redis来构建一个全面的考勤系统。您将从学习人脸检测、特征提取和人脸识别算法的基础开始。然后,您将把这些算法集成到您将从头构建的考勤系统中。在课程结束时,您将拥有一个完整的考勤系统,能够识别人并根据他们的面部特征标记他们的出勤情况。本课程适合编程和机器学习初学者,不需要人脸识别的先验知识。Attendance System With Face Recognition In Python 2023

本课程涵盖的主题包括:人脸识别和考勤系统简介基本图像处理技术特征提取和维数约简人脸检测和识别算法人脸识别的机器学习利用人脸识别构建考勤系统Redis with python集成Redis和人脸识别系统。注册表单(添加新的人员数据)Streamlit for实际时间预测注册表单报告本课程结束时,您将对如何使用人脸识别技术创建一个完整的考勤系统有深刻的理解。您还将掌握将这些知识应用于其他计算机视觉应用的技能。课程上见。

MP4 |视频:h264,1280×720 |语言:英语+中英文字幕(云桥CG资源站 机译)|课程时长:9小时30分钟 含课程文件

你会学到什么
实时现场考勤系统
用人脸识别检测和识别人名和角色
开发3个Streamlit Web应用程序
集成人脸识别模型和Redis数据库
使用Python了解Redis
App-1:实时现场考勤系统
App-2:新师生登记表
App-3:报告

要求
至少初学Python
至少开始使用Pandas、Numpy和OpenCV库

课程目录:
Section 1: Introduction

Lecture 1 Introduction

Lecture 2 Course Curriculum

Lecture 3 Complete Resources

Lecture 4 OpenCV with Python

Section 2: Setting up Environment

Lecture 5 [IMPORTANT] What Python version to install ?

Lecture 6 Install appropriate Python version

Lecture 7 Install Virtual Environment

Lecture 8 Install Required Packages

Section 3: Redis as Database Crash Course [Python]: Optional

Lecture 9 Useful links

Lecture 10 Setting up Redis cloud

Lecture 11 Connect notebook to Redis CLI (Client) using host, port and password

Lecture 12 Redis Data Structures

Lecture 13 Redis: Strings commands (“set”, “get”)

Lecture 14 Redis: String – SET part 2

Lecture 15 Redis: String – Part 3

Lecture 16 Redis: String – Part 4

Lecture 17 Redis: String – part 5

Lecture 18 Redis: String – part 6

Lecture 19 Redis String: String (additional commands)

Lecture 20 Intro to Redis with Python

Lecture 21 Redis List

Lecture 22 Redis List part 2

Lecture 23 Redis List part 3

Lecture 24 Redis List part 4

Lecture 25 Redis List part 5

Section 4: Face Recognition with InsightFace API

Lecture 26 Useful Links

Lecture 27 Automatic Fast Face Recongnition System Intro

Lecture 28 What and Why Insightface

Lecture 29 InsightFace Install

Lecture 30 Import insightface & how to solve common error import error

Lecture 31 Configure Pretrained Models of Insightface in python

Lecture 32 Assignment Solution: Configure “bufallo_sc” model

Lecture 33 Get Face Analysis results/report from Insightface python

Lecture 34 Draw bounding box, Key points, Age, Gender for multiple faces part -1

Lecture 35 Draw bounding box, Key points, Age, Gender for multiple faces part -2

Lecture 36 Assignment Solution: bbox, keypoints, score for buffalo_sc model

Section 5: Attendance System : Fast Face Recognition

Lecture 37 Introduction to Attendance System and What we are building in this course

Lecture 38 Flow Diagram of Attendance System

Lecture 39 Get Data & Understand the folder structure of data

Lecture 40 Fast Face Recognition: Data Preparation in Python

Lecture 41 Fast Face Recognition (FFR): Data Preparation – Clean Text (labels)

Lecture 42 FFR: Data Preparation – define path of all images

Lecture 43 FFR: Data Preparation – Extract Facial Embeddings from all images

Lecture 44 Predicting Person name part 1

Lecture 45 Machine Learning (ML) Search Algorithm – Euclidean Distance

Lecture 46 ML Search Algorithm – Manhattan Distance

Lecture 47 ML Search Algorithm – Chebyshev Distance

Lecture 48 ML Search Algorithm – Minkowski Distances

Lecture 49 ML Search Algorithm – Cosine Similarity

Lecture 50 Distance vs Similarity methods

Lecture 51 ML Search Algorithm – Distance Method

Lecture 52 ML Search Algorithm – Similarity Method

Lecture 53 ML Search Algorithm in Python

Lecture 54 Analyzing Euclidean , Manhattan and Cosine values for test image

Lecture 55 Predicting Person Name with Euclidean Distance

Lecture 56 Predicting Person Name with Manhattan Distance

Lecture 57 Predicting Person Name with Cosine similarity

Lecture 58 Advantages of Cosine similarity over Euclidean and Manhattan Distance.

Lecture 59 Identify Multiple Person Name in one image part 1

Lecture 60 Identify Multiple Person Name in one image part 2

Lecture 61 Identify Multiple Person Name in one image part 3

Lecture 62 Identify Multiple Person Name in one image part 4

Lecture 63 Optimize Collected data (facial embeddings) and save

Lecture 64 Optimize Collected data (facial embeddings) and save part 2

Section 6: Attendance System : Registration Form & Integrate to Redis

Lecture 65 Save Collected data into Redis Database

Lecture 66 Save Collected data into Redis Database part 2

Lecture 67 Idea of Registration form in Python

Lecture 68 Registration form: Collect details of new Students and Teachers

Lecture 69 Registration form: Collect face embedding samples for new registry

Lecture 70 Registration form: Store information in Redis database

Section 7: Attendance System : Real Time Person name detection

Lecture 71 What we are developing

Lecture 72 Preparing Python module for Real time prediction

Lecture 73 Retrieve data from database

Lecture 74 Real Time Person Name prediction

Lecture 75 Real Time Person Name Prediction part 2

Section 8: WEB APP Installations

Lecture 76 Install Visual Studio Code

Lecture 77 Install required libraries

Section 9: Attendance Web App

Lecture 78 Streamlit App Intro

Lecture 79 Create Home and connect all Pages from Home page

Lecture 80 Import face_rec into app and retrive data from Redis

Lecture 81 Apply Spinner to face_rec and reduce the time to start the app

Lecture 82 Real Time Person name detection using streamlit webrtc

Lecture 83 Find time at which person name is detected

Lecture 84 Save Logs (person name and time) in Redis database

Lecture 85 Save Logs (person name and time) in Redis database part 2

Lecture 86 Show Logs in Streamlit Report

Lecture 87 Show Logs: Add refresh button

Lecture 88 Show Logs: Create tabs for Registered users and Logs

Lecture 89 Testing logs

Lecture 90 Registration Form part 1

Lecture 91 Registration Form Part 2

Lecture 92 Registration Form part 3

Lecture 93 Registration Form part 4

Lecture 94 Testing Registration form

Section 10: BONUS

Lecture 95 Bonus Lecture

Anyone who like to develop End to End Face Recognition based Attendance System.

发表回复

后才能评论