A Mini-Project Report on
Face Recognition Based Attendance System Using Local Binary
Patterns Histogram
Submitted by
JAINAM .N. GANGAR (ROLL NO. 04)
in fulfillment of
Image Processing and Machine Vision Mini-Project
in
Electronics & Telecommunication Engineering
Guided By
Dr. Vaqar Ansari
Department of Electronics and Telecommunication Engineering
TE EXTC
St. Francis Institute of Technology, Mumbai
Autonomous
(2024-2025)
INDEX
Sr. No Name of Topic Page Number
1. INTRODUCTION
1.1 Background
1.2 Objective
1.3 Scope of the Project
2. LITERATURE REVIEW
2.1 A Face Recognition Based Automatic Attendance Management System by Combining LBP and
HOG Features
2.2 Face Recognition Based on Attendance Management System
3. METHODOLOGY
3.1 GUI Development
3.2 Student Registration
3.4 Model Training
3.5 Real-time Face Recognition
3.6 Attendance Management
3.7 Data Storage and Files
4. RESULTS
5. APPLICATION
6. CONCLUSION
1. Introduction
1.1 Background
Traditional methods of attendance marking such as manual roll calls or biometric fingerprint scanners have
several limitations—manual errors, buddy punching, time consumption, and hygiene issues. In educational
institutions and workplaces, efficient and reliable attendance management systems are needed to streamline
operations and maintain accurate records.
Face recognition is a biometric method that uses facial features for identification. With advancements in machine
learning and computer vision, face recognition has become an effective, non-intrusive method for automated
attendance systems. The Local Binary Patterns Histogram (LBPH) algorithm is especially suited for real-time
applications as it is computationally efficient and works well even with low-resolution images.
1.2 Objective
To develop a face detection and recognition-based attendance system.
To utilize the Local Binary Patterns Histogram (LBPH) for reliable face recognition.
To eliminate manual attendance marking and reduce human errors.
To provide a GUI-based interface for easy interaction and report viewing.
To store and manage attendance records efficiently.
1.3 Scope of the Project
This project aims to design and implement an automated attendance system using face recognition based on the LBPH
algorithm. The system will:
Detect and recognize faces from a live video stream or camera feed.
Mark attendance in a local database or file automatically.
Provide a GUI for easy user interaction (using Tkinter or similar libraries).
Work offline, requiring no internet connection.
The scope is limited to a local environment and does not include cloud-based attendance or mobile integration.
2. Literature Review
Project Title with authors Description Result
1—“A Face Recognition This study presents a novel The combination of LBP
Based Automatic methodology for taking and HOG features with
Attendance Management student attendance through SVM classification
System by Combining LBP face recognition techniques. It enhances the accuracy of
and HOG Features” by combines Local Binary student identification in
Pattern (LBP) and Histogram
Manjunath K. Patgar, attendance systems.
of Oriented Gradients (HOG)
Soumya Patil, Rajashekhar features to create a new
B. Shettar feature vector. A Support
Vector Machine (SVM)
classifier is implemented to
predict students based on
comparisons between query
image features and stored
images in the student
database.
2—“ Face Recognition This project utilizes the The integration of Viola-
Based on Attendance Viola-Jones algorithm for Jones and LBPH
Management System” by face detection and the algorithms provides an
Rajeev Yadav, Sumit Local Binary Pattern efficient and accurate
Chauhan, Meenu, Swati Histogram (LBPH) attendance system,
Gupta algorithm for sample minimizing manual errors.
training and face
recognition. The system
aims to automate
attendance marking,
reducing time consumption
compared to manual
methods.
3. Methodology
This project follows a structured approach to implement a Face Recognition Attendance System using Python, OpenCV,
and Tkinter. The methodology is divided into several key stages:
1. GUI Development
The user interface is built using Tkinter, Python’s standard GUI library. It provides an interactive and user-friendly
platform for:
Registering new students
Capturing facial images
Training the recognition model
Taking attendance
Viewing and exporting attendance records
2. Student Registration
The user inputs the student’s name and roll number.
Upon submission, a unique numeric ID is generated and linked to the student.
The system ensures both fields are filled and the name contains only alphabetic characters.
3. Image Capture
The application uses the OpenCV Haar Cascade Classifier to detect faces via the webcam.
When a face is detected, 60 grayscale images of the face are captured for training purposes.
These images are saved in a dedicated TrainingImage directory with filenames indicating the student’s ID and
name.
4. Model Training
Collected facial images are used to train a Local Binary Pattern Histogram (LBPH) face recognizer from
OpenCV.
Each image is associated with its corresponding student ID.
The trained model is saved as Trainner.yml for future use.
5. Real-time Face Recognition
During attendance, the webcam scans and detects faces in real time.
Detected faces are recognized using the trained LBPH model.
If the face matches an existing record, the system logs the student’s name, ID, date, and time in the attendance
sheet.
6. Attendance Management
Attendance is saved in a .csv file named after the current date and time.
The user can view the attendance records directly within the application and export them if needed.
7. Data Storage and Files
Student details are stored in StudentDetails.csv.
Attendance records are stored in the Attendance folder.
Trained facial recognition data is saved in Trainner/Trainner.yml.
4. Results
4.1 After uploding the code a page this page appear
4.2 All the data will be stored in the excel or any platform we want
5. Applications of Flower Recognition
1. Educational Institutions
Automatically records student attendance in schools, colleges, and universities, reducing manual errors
and saving time.
2. Corporate Offices
Tracks employee attendance and working hours, helping HR manage payroll and leaves efficiently.
3. Workshops & Conferences
Used to quickly verify and register attendees, improving event management.
4. Secure Entry Systems
Can be integrated with access control systems for doors and restricted areas.
6. Conclusion
1. The Face Recognition Attendance System offers an efficient, secure, and automated alternative to
traditional attendance methods.
2. By integrating technologies like OpenCV, Tkinter, and face recognition algorithms, it enhances
reliability, reduces human error, and saves valuable administrative time.
3. With wide applicability across educational and professional environments, this system exemplifies how
AI and computer vision can streamline routine tasks and improve operational efficiency.