FACE
RECOGNITION
ATTENDANCE
GUIDE : Mrs.Jean Celia Grace
TEAM
MEMBERS
POOJA S
RAJALAKSHMI
K
OVERVIEW
Abstarct
Problem Statement
Objective
Architecture
Modules
Literature Survey
References
ABSTRACT
⚬This project aims to enhance traditional attendance
systems by resolving a common problem: the absence
of real-time, hour-specific live detection.
⚬Existing systems often require manual input or
periodic scans, causing delays in updating attendance
records.
⚬To overcome this challenge, the project introduces
live detection technology, automating the process and
ensuring precise attendance percentages for each hour.
PROBLEM STATEMENT
This project aims to improve traditional attendance systems by
addressing a common issue:
The lack of real-time, hour-specific detection. Current systems
rely on manual input or periodic scans, resulting in delays in
updating attendance records. To solve this problem, the project
introduces live detection technology to automate the process,
ensuring accurate attendance percentages for every hour.
OBJECTIVE
The primary goal is to develop an attendance management system with live detection for every class hour. Key objectives
include:
⚬Enabling automated attendance tracking to
Implementing a real-time face Addressing the absence of live
eliminate manual intervention.
recognition system for accurate detection in older versions to
student identification. enhance the system's overall
⚬ Calculating attendance percentages on an
efficiency.
hourly basis for a detailed view of student
participation.
ARCHITECTURE DIAGRAM
Live Camera Feed: Captures real-time video footage.
Face Detection & Recognition Module : Identifies faces in the live
feed using OpenCV or similar libraries & Uses a pre-trained deep
learning model for accurate student identification.
Attendance Logging Module: Records attendance data with
timestamps and student IDs.
Automated Calculation Algorithm: Processes data to calculate hourly
attendance percentages.
User Interface: Provides a user-friendly interface for students and
instructors to view real-time attendance information.
MODULES
1. Live Face Detection Module: Implements real-time face detection
algorithms.
2. Face Recognition Module: Utilizes a pre-trained model for student
identification.
3. Attendance Logging Module: Records attendance data with
timestamps and class information.
4. Automated Calculation Module: Processes attendance data to
calculate hourly percentages.
5. User Interface Module: Develops interfaces for users to view live
attendance information.
LITERATURE REVIEW
BASE PAPER TITLE : Face Recognition Attendance System Based on Real-Time
Video Processing.
Author name : HAO YANG AND XIAOFENG HAN
Date of publication : July 10, 2020
The face recognition time attendance system and manual fingerprint punching are
more stable and correctly identify check-ins, and the rate of skipping classes is
significantly reduced compared with the control group
REFERENCE
Hao Yang and Xiaofeng Han, “Face Recognition Attendance System Based on Real-
Time Video Processing”, vol.8, pp.July 10, 2020.
K. Solanki and P. Pittalia, ‘‘Review of face recognition techniques,’’ Int. J. Comput.
Appl., vol. 133, no. 12, pp. 20–24, Jan. 2016.
C. Stoll, R. Palluel-Germain, R. Caldara, J. Lao, M. W. G. Dye, F. Aptel, and O.
Pascalis, ‘‘Face recognition is shaped by the use of sign language,’’ J. Deaf Stud.
Deaf Educ., vol. 23, no. 1, pp. 1–9, 2018.
THANK YOU!
