Face Attendance: Project No: 90

Face Attendance
Project No: 90
A Minor Project by- Our Mentor-

Aditya Agarwal (191b020) Mr. Navaljeet Singh Arora
Anshu Gupta (191b052)
Ashmit Modi (191b076)
CONTENTS :
1. Problem Statement
2. Introduction
3. Feasibility Study
4. What exactly is Facial Recognition Output
5. How Recognition Works
6. Implementation of Facial Recognition
7. Block Diagram
8. Image Acquisition
9. Image Processing
10. Extraction of Facial Features
11. How Facial Recognition System Works
12. Flowchart for Facial Recognition System
13. Implementation
14. Use Case Diagram
15. PROS AND CONS
16. Conclusion
PROBLEM STATEMENT
The main intention of this project is to solve the issues encountered in the
old attendance system while reproducing a brand new innovative smart
system that can provide convenience to the institution.
Design of an automatic class attendance system using face detection

algorithm software. The system requires a video capture device and the
running algorithm to be implemented successfully. It detects the faces and
mark attendance accordingly. This system will prevent unnecessary
wastage of time of classes that is usually wasted in form of class roll calls.
INTRODUCTION
The project “Face Attendance” mainly focuses on:
• Reducing time wastage during conventional class attendance.

• Utilizing latest trends in machine vision to implement a feasible
solution for class attendance system.
• Automating the whole process so that we have digital
environment.
• Preventing fake roll calls as one to one attendance marking is
possible only.
• Encouraging the use of technology in daily lives.
FEASIBILITY STUDY
● Financial Feasibility
○ Our application which will run on local computer therefore there will be no server cost.
○ There will be a tentative one time payment for the hardware which includes components like
microprocessor, camera..
● Tech Feasibility
○ Each of the technologies are freely available and the technical skills required are
manageable.
Time limitation of the product development and the ease of implementing using these
technologies are synchronized.
○ Optimizations are provided where needed, to support legacy machines.
○ Time to time updates to the software can be provided to the user depending on the
improvements and changes.
FEASIBILITY STUDY
Technologies And Tools Used-
● Python (Programming Language)
● Visual Studio Code Editor
● Google Colab- (it offers a virtual GPU and CPU to run heavy programs which require a large
amount of processing.)
● Yolo v5-(this model is used for real time object detection and it can also be used to train your
own model by supplying a training and validation set.)
● OpenCV- (Opencv is an open source library which is very useful for computer vision applications
such as video analysis, CCTV footage analysis and image analysis.)
TensorFlow- (TensorFlow provides a collection of workflows to develop and train models using
Python or JavaScript.)
What exactly is Facial Recognition??
• A facial recognition is a computer application for automatically identifying or

verifying a person from a digital image or a video frame from a video source.
• One of the ways to do this is by comparing selected facial features from the
image and a facial database
How Recognition Works
Before recognition, it is required to detect a face in the image captured by camera, using
the hair Cascade classifier. It can detect multiple faces in single image which means
attendance of multiple people at same time can be recorded. Having detected a face or
faces the recognizer then predicts whose face it is by using data in training Data.yml
file. This file is loaded at the start of recognition. The predict () method of LBPH Face
Recognizer in OpenCV, will take as a parameter a captured portion of the face to be
analyzed and will return its probable owner, indicating its id and how much confidence
the recognizer is in relation with this match. Note that the confidence index will return
“zero” if it will be considered a perfect match. And at last, if the recognizer could
predict a face, we put his name fetched from database using its id given by recognizer.
If person is not matched, “No match” label is put on the face.
Implementation of Facial Recognition??
• The implementation of face recognition technology includes the

following three stages :
 Image acquisition.
 Image processing.
 Facial image classification and decision making.

Block Diagram -
Image Image Extraction of

Acquisition Processing Facial features
Marking the Comparing with

attendance Database
Image Acquisition
• Facial scan technology can acquire faces from almost any static
camera or video system that generates image of sufficient quality and
resolution.
• High quality enrollment is essential to eventual verification and

identification enrollment images define the facial characteristics to be
used in all future authentication events.
Image Processing
• Images are cropped and colour images are normally converted to black
and white in order to facilitate initial comparisons based on gray scale
characteristics.
• First the presence of faces or face in a scene must be detected. Once the
face is detected, it must be localized and Normalization process may be
required to bring the dimensions of the live facial sample in alignment
with the one on the template.
Extraction of Facial Features
• All facial scan systems attempt to match visible facial features in a

fashion similar to the way people recognize one another.
• The features most often utilized in facial scan systems are those least
likely to change significantly over time: upper ridges of the eye sockets,
areas around the cheekbones, side of the mouth, nose shape, and the
position of major features relative to each other.
How Facial Recognition System Works
First the image is imported by providing the location of the image for
detecting, then that image is transformed from RGB to Grayscale because it
is easy to detect faces in the grayscale. The next step is image segmentation,
it is used for contour detection or segments the multiple objects in a single
image so that the classifier and quickly detect the objects and faces present
in the image. The next step is to use Hair-Like features algorithm. This
algorithm used for finding the location of the human faces present in a
frame or image. a rectangle box will be drawn in the area of interest where it
detects the face.
How Facial Recognition System Works
• Every face has atleast 80 distinguishable parts called nodal points.
Here are few nodal points below:
 Distance between the eyes.

 Width of the nose.
 Depth of eye sockets.
 Structure of the cheek bone.
 Length of jaw line.
Flowchart for Facial Recognition System
IMPLEMENTATION:
Each user first needs to do registration. After registration, images of user's face will be
captured by camera.
• Capturing the image data: The camera will be placed at the entrance of
organization. The camera will capture images of user entering the organization.
• Face detection: Faces will be detected in the images captured by camera. If frontal
face is visible in camera then that portion of image will be cropped and saved as
new image in dataset folder.
• Training: For face recognition, training is required. Training is done on dataset
images.
• Attendance: For recording daily attendance, start recognition button needs to be
clicked. Once the button is clicked, camera will start capturing images at the
entrance. If face appears in image, then it will be compared with dataset and if
match occurred, the name and Id will be shown for that user. Time at which face
Use Case Diagram
PROS AND CONS
Advantages of Face Detection Disadvantages of Face Detection
— Better security — Huge storage requirements

— Easy to integrate — Vulnerable detection
— Automated identification — Potential privacy issues
— Cost-effective — Data privacy breach
— Time saving — Low reliability
— Lack of regulations in the AI in Face
recognition systems
Conclusion
● “Face Attendance” goal is to solve the issues encountered in the old
attendance system while reproducing a brand new innovative smart system
that can provide convenience to the institution.
● At the end of this project we expect that our application is capable of

giving desired output to the users and is able to help them.
● The main goal of the project is to help the Student and make there life easy
by reducing time wastage from old attendance system.
● At the end of this project we expect that this project will identify the
person face and record the attendance on excel sheet.
References
● https://sourceforge.net/
● Vector Images Creator
● Wikipedia
● Geeks For Geeks
● https://medium.com/
● https://github.com/ultralytics/yolov5
Thank You!!

Face Attendance: Project No: 90

Uploaded by

Copyright:

Available Formats

Face Attendance: Project No: 90

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Face Attendance: Project No: 90

Uploaded by

Copyright:

Available Formats

Face Attendance

A Minor Project by- Our Mentor-

Design of an automatic class attendance system using face detection

The project “Face Attendance” mainly focuses on:

• Reducing time wastage during conventional class attendance.

● Python (Programming Language)

● Visual Studio Code Editor

• A facial recognition is a computer application for automatically identifying or

• The implementation of face recognition technology includes the

 Facial image classification and decision making.

Image Image Extraction of

Marking the Comparing with

• High quality enrollment is essential to eventual verification and

• All facial scan systems attempt to match visible facial features in a

• Every face has atleast 80 distinguishable parts called nodal points.

Here are few nodal points below:

 Distance between the eyes.

Advantages of Face Detection Disadvantages of Face Detection

— Better security — Huge storage requirements

● At the end of this project we expect that our application is capable of

● Vector Images Creator

● Geeks For Geeks

You might also like