Scribd
Upload
3 views

Attendance_System_Report

The Attendance Checking System, developed by the Diamonds team, utilizes artificial intelligence and computer vision to automate student attendance tracking through facial recognition. The system features a user-friendly frontend, a Flask-based backend for processing, and a database for storing student data and attendance logs. Key challenges include ensuring accuracy under varying conditions and optimizing performance for large classes, with future improvements planned for model training and cross-platform integration.

Uploaded by

horaned409
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
3 views

Attendance_System_Report

The Attendance Checking System, developed by the Diamonds team, utilizes artificial intelligence and computer vision to automate student attendance tracking through facial recognition. The system features a user-friendly frontend, a Flask-based backend for processing, and a database for storing student data and attendance logs. Key challenges include ensuring accuracy under varying conditions and optimizing performance for large classes, with future improvements planned for model training and cross-platform integration.

Uploaded by

horaned409
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 5

Attendance Checking System

Team Name : Diamonds


Team Members:

● U2110269 Omadbek Teshaboyev 004


● U2110270 Dostonbek Tilavov 004
● U2110036 Muzaffarbek Khursanboev 002
● U2110071 Azamatjon Xayrullayev 002
● U2110097 Sardor Alijonov 002
● U2110258 Khumoyun Sayfullayev 004

1. Problem Definition and Relevance


Problem Statement

Traditional methods of tracking student attendance are inefficient, time-consuming, and


prone to errors. These manual approaches often require significant administrative effort
and may not ensure accurate data collection. For institutions managing large classes,
ensuring attendance compliance becomes a logistical challenge.

Relevance to Artificial Intelligence Concepts

This project leverages artificial intelligence and computer vision to automate the attendance
process. By using facial recognition technologies, the system identifies and records the
attendance of students in real-time. This approach aligns with AI principles, such as pattern
recognition and deep learning for face matching, to solve a practical problem in educational
settings.

Importance of the Problem

Efficient attendance tracking can save administrative hours, enhance classroom


engagement, and provide valuable insights into student participation. The integration of AI
ensures a scalable and reliable solution, addressing the needs of modern educational
institutions striving for digital transformation.
2. Methodology and Implementation
System Design

The system consists of three primary components:

1. Frontend: A user interface allowing instructors to start and stop attendance


tracking, view recognized students, and add new students.
2. Backend: A Flask-based application handling facial recognition, attendance logging,
and database interactions.
3. Database: A SQLite or PostgreSQL database to store student data and attendance
logs.

Implementation Workflow

1. Student Enrollment:
○ Photos of students are uploaded through the frontend.
○ The backend processes and encodes these images using the
face_recognition library.
○ Encoded facial data is stored in the database.
2. Attendance Marking:
○ The instructor starts the camera feed, which captures frames in real-time.
○ Each frame is processed to detect and recognize student faces using facial
encodings.
○ Recognized students are marked present, and their attendance is logged in
the database.
3. Data Storage:
○ Student profiles include names and photo encodings.
○ Attendance logs include timestamps and recognized student names.
Let’s see how our system works in a simple graphical representation:
AI Techniques Used

● Facial Recognition: Utilized the face_recognition library for encoding and


comparing faces.
● Computer Vision: Processed video frames to extract facial features.
● Machine Learning Models: Applied pre-trained models for face detection and
encoding.

Implementation Challenges

● Accuracy: Ensuring reliable face detection and recognition under varying lighting
conditions.
● Performance: Optimizing real-time processing for large class sizes.
● Scalability: Managing a growing dataset of student profiles and attendance records.

3. Experimental Design and Results


Dataset

● Student Photos: A curated dataset containing multiple images of each student with
variations in lighting and angles.
● Test Data: Frames captured during attendance sessions, simulating real-world
classroom scenarios.

4. Creativity and Critical Thinking


Originality of the Solution

The integration of AI for automating attendance tracking is an innovative approach to


modernizing administrative tasks in education. By focusing on real-time processing and
user-friendly design, the system addresses challenges unique to large classrooms.

Addressing Challenges

● Lighting Variability: Enhanced preprocessing techniques to normalize lighting


conditions.
● Edge Cases: Added fallback mechanisms for manually verifying unrecognized
students.
● Future Scalability: Designed a modular architecture to integrate additional
features, such as emotion detection or performance analytics.

Future Improvements

● Model Training: Transition from pre-trained models to a custom-trained model


tailored for the institution’s dataset.
● Cross-Platform Integration: Extend support to mobile platforms for added
convenience.
● Data Analytics: Incorporate dashboards for visualizing attendance trends and
patterns.

You might also like