Scribd
Upload
13 views1 page

Frasabst3 1

Uploaded by

Vijaykumar Boddupally
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as ODT, PDF, TXT or read online on Scribd
13 views1 page

Frasabst3 1

Uploaded by

Vijaykumar Boddupally
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as ODT, PDF, TXT or read online on Scribd
You are on page 1/ 1

FACE RECOGNITION ATTENDENCE SYSTEM

USING MATLAB
Abstract
Traditional attendance systems often rely on manual processes, which can be time-
consuming and prone to errors. To overcome these limitations, this project proposes the
development of a Face Recognition Attendance System (FRAS) utilizing MATLAB, CNN
(convolution neural network) and Image Processing techniques. The FRAS employs facial
recognition algorithms to automatically identify and authenticate individuals based on their facial
features captured by a camera. The system preprocesses and analyzes facial images to extract
unique facial patterns, which are then compared with pre-stored templates in a database.
The FRAS employs facial recognition algorithms to automatically identify and authenticate
individuals based on their facial features captured by a webcam. The system processes facial
images by detecting faces using the cascade object detector and preprocess them by resizing them
for standardization before saving them for further use. For training, the system employs deep
learning techniques using the AlexNet convolutional neural network. AlexNet, known for its deep
architecture and ability to learn complex features, is pretrained on a large dataset and fine-tuned for
this specific application through transfer learning. This modification involves replacing the final
layers to classify the captured images accurately into predefined categories. During the testing
phase, the trained network is loaded, and the system continuously captures images from the
webcam, detects faces, and classifies them in real time.
Additionally, the system logs attendance records by updating an array when a face is
recognized. The attendance data, including names, mobile numbers, emails, and attendance status,
is saved to an OpenOffice Excel file, which is programmed to record attendance by the current date
and open automatically for review. By integrating sophisticated computer vision, deep learning, and
image acquisition techniques, the FRAS achieves high accuracy and robustness in recognizing
individuals. We expect the system to achieve an accuracy of 80%. This project aims to streamline
attendance management processes in educational institutions and workplaces by offering a reliable,
efficient, and user-friendly solution based on advanced facial recognition technology.

Guide: Batch:
Sri.s Praveen kumar B.Sreeja 22JJ1A0412
Assistant Proofessor ECE B.Vijay 22JJ1A0413
G.Lahari 22JJ1A0425

You might also like