Software Requirements Specification

for

< Face recognition using employee management application >

Version <1.0>

Prepared by

Group Name:
Purva Jage TY ECS A2 [email protected]
Jidnyasa kalaskar TY ECS A2 [email protected]
Mrunal deshpande TY ECS A2 [email protected]
 Contents

1 INTRODUCTION 1
2 OVERALL DESCRIPTION 2
3 SPECIFIC REQUIREMENTS 5
4 OTHER NON-FUNCTIONAL REQUIREMENTS 6
5 DATA DICTIONARY 9
6 DATA LOG 10
 1 Introduction

1.1 Product Scope

Face recognition technology is a biometric technology, which is based on the identification of facial features of
a person. People collect the face images, and the recognition equipment automatically processes the images.
The paper introduces the related researches of face recognition from different perspectives. The paper describes
the development stages and the related technologies of face recognition. We introduce the research of face
recognition for real conditions, and we introduce the general evaluation standards and the general databases of
face recognition. We give a forward-looking view of face recognition. Face recognition has become the future
development direction and has many potential application prospects. Face recognition in a broad sense includes
related technologies for building a face recognition system. It includes face detection, face position, identity
recognition, image preprocessing, etc.

1.2 References and Acknowledgments

[1] K. T. Talele, S. Kadam, A. Tikare, Efficient Face Detection using Adaboost, “IJCA Proc on International Conference
in
Computational Intelligence”, 2012.
[2] T. Mita, T. Kaneko, O. Hori, Joint Haar-like Features for Face Detection, “Proceedings of the Tenth IEEE
International
Conference on Computer Vision”, 1550- 5499/05 ©2005 IEEE.
[3] T. Ahonen, A. Hadid, M. Peitikainen , Face recognition with local binary patterns. “In Proc. of European Conference
of Computer Vision”, 2004.
[4] M. A. Turk and A.P. Pentland, Face recognition using eigenfaces, “Proceedings of the IEEE”, 586-591, 1991.
[5] J Lu, K. N. Plataniotis, A. N. Venetsanopoulos, Face recognition using LDA-based algorithms, “IEEE Neural
Networks
Transaction”, 2003.
[6] L. Wiskott, M. Fellous, N. Krger, and C. Malsburg,Face recognition by elastic bunch graph matching, “IEEE Trans”,
on PAMI, 19:775–779, 1997.
 2 Overall Description
2.1 Product Overview
This Project deals with face recognition with employee management application o enhance the security and
convenience of the login process for employees and administrators. Face recognition technology offers a
significant improvement over traditional methods by reducing the risk of password theft and unauthorized
access, providing a more secure authentication mechanism. Additionally, the system aims to enable the
creation and management of various admin profiles with specific access rights and responsibilities. It will
provide a comprehensive suite of employee management tools, including salary management, record
updates, and data entry functionalities. Face recognition technology addresses these security concerns by
providing a robust and reliable method of authentication. The implementation of the new system will
involve several potential solutions and alternatives. Advanced face recognition technology using machine
learning algorithms will be employed to accurately identify users. A hybrid authentication system will
combine face recognition with traditional login methods to provide flexible options.

2.2 Product Functionality

This system will integrate face recognition for secure login , main traditional authentication as an alternative
method .this login system will be made using open-cv library using python where first we have login page
where we can use username password also we can login using face recognize with dataset in database and then
login . Also there one function where we can register for new admin where we can create admin login with new
username, password and with their face dataset. and after login it will open employee application where features
like we can add new employee data also their salary management ,we can update past employee data .HR will
benefit from streamlined process and reduced administrative burden . Security and privacy will be prioritized
with machine learning algorithm for user recognition. This system will also manage various admin profiles with
specific access right. Thus, it is a secure and efficient system incorporating face recognition technology for
login and robust employee’s management. This will resolve inefficiency from manual login .This project aims
to create a secure, efficient and user friendly employee management application using face recognition to
enhance security and streamline HR process.
 2.3 Design and Implementation Constraints

Fig: Architectural Diagram

This diagram represents the process flow for a face recognition system, which could be applied to an employee
management system. Here’s a step-by-step explanation of each component:

1. Video Input: The process begins with video footage, likely from a surveillance camera or a live video
feed. This video contains the faces of employees that need to be recognized.
2. Sequence of Images: The video is split into a sequence of individual frames (images). This step involves
extracting frames from the continuous video stream, which can then be processed individually.
3. Pre-processing: In this stage, each image is prepared for analysis. Pre-processing may include tasks like
noise reduction, normalization, resizing, and adjusting the brightness or contrast to enhance the quality of
the image. This step ensures that the images are in an optimal state for face detection.
4. Face Detection: The system then identifies and locates faces within each image. Face detection
algorithms, such as Haar cascades or deep learning-based methods, are used to find the position of faces
in the images.
5. Feature Extraction: Once a face is detected, the system extracts distinguishing features from the face.
These features could include the distance between the eyes, the shape of the nose, or the texture of the
skin. This process converts the face into a numerical representation that can be analyzed.
6. Face Classification: The extracted features are then compared to a database of known faces (e.g.,
employee records). The system classifies the face as belonging to a specific employee based on the
features. This step determines the identity of the person in the image.
7. Database Interaction: The classified face is cross-referenced with a database that contains employee
information. This database might store information such as the employee's name, ID, department, and
other relevant details.
8. Face Tracking: After classification, the system tracks the recognized face across subsequent frames in
the video. This ensures that the employee is continuously monitored as they move through the frame.
 Fig: Use Case Diagram

The actor means the farmer first login the account, for login it will verify password this condition
means include stage of use case diagram and if password is wrong then it will extend the condition.
After that framer select the image and upload the image. Admin receives the images and process the
image to upload the image at the server. farmer can view the message, that message include amount
of pesticide affected, disease name, crop name and unique ID. Identifying the amount of fertilization
required for Rice crops using Image processing System is developed in java built using the Android
Studio Platform. The questions and other data to be stored in database using xampp.

2.4 Assumptions and Dependencies-

Identifying the amount of fertilization required for face recognition in employee management system must
need image from client side. It is developed in python language and the OS required is Windows 11 (64bit).
This applies to only windows users.
 3 Specific Requirements
3.1 External Interface Requirements

3.2
3.2.1 User Interfaces

OS : Windows 11(64 bit)

3.2.2 Hardware Interfaces

Processor : Above 1.5GHZ

Hard Disk : 80GB
RAM : 2GB

3.2.3 Software Interfaces

Language : HTML , CSS , java-script , node.js ,python ,SQL

OS : Windows 11 (64 bit)
IDE : Visual stdio code (vs code)

3.3 Functional Requirements

Video Capture and Processing: The system should capture video footage from cameras placed at strategic
locations (e.g., entrances, exits). The system should extract individual frames from the video stream for further
processing.

Image Pre-processing: The system should preprocess images to enhance quality, including resizing, noise
reduction, and normalization.

Face Detection: The system should accurately detect faces in each frame. It should handle varying lighting
conditions, facial orientations, and occlusions (e.g., glasses, masks).

Face Classification: The system should classify detected faces by comparing them to a database of known
employees. It should handle variations in appearance (e.g., changes in hairstyle, facial hair).

Database Management: The system should store and retrieve employee information from a secure database. It
should update the database with new employee information as needed.

Face Tracking: The system should continuously track recognized faces across multiple frames. It should handle
real-time tracking with minimal delay.

Alerts and Notifications: The system should generate alerts for unrecognized individuals or security breaches.
Notifications should be sent to relevant personnel in real-time.
 4 Other Non-functional Requirements
4.1 Performance Requirements
Non-functional requirements are requirements which specify criteria that can be used to judge the operation of
a system, rather than specific behaviors. This should be contrasted with functional requirements that specify
specific behavior or functions. Typical non-functional requirements are reliability, scalability, and cost. Non-
functional requirements are often called the ileitis of a system. Other terms for non-functional requirements are
"constraints", "quality attributes" and "quality of service requirements". Non-Functional Requirements are the
characteristics or attributes of the system that are necessary for the smooth operation of the system. Those
Requirements are listed below.

 The system should perform the process accurately and precisely to avoid problems.
 The system should be easy to modify for any updates. Any errors or bugs that are identified should be easy to
mend.
 The system should be secure and maintain the privacy of the employees.
 The system should be easy to understand and use.
 Execution of the operation should be fast

4.2 Safety and Security Requirements

 Data protection
 Authentication and authorization
 Access control
 Incident response
 Audit and logging

4.3 Software Quality Attributes

● AVAILABILITY: The system should consistently recognize faces with high accuracy under
varying conditions\
● Data Protection: The system should ensure that sensitive data, such as facial recognition templates
and employee information, are securely stored and transmitted.
● CORRECTNESS: The system should recommend the correct detection of face from
database.
● MAINTAINABILITY: The administrators will keep a track of all User ID registration and
data set of images respectively.
● Accuracy: The system should achieve high accuracy in face recognition, with low false acceptance
and false rejection rates.
● Scalability: The system should efficiently manage a growing database of employee records,
ensuring that performance does not degrade as the number of records increases.
 5 Other Requirements
6. PRELIMINARY BUDGET/ESTIMATION
Initially, we need a working model in which the system should require python, visual Studio, SQL
workbench knowledge to maintain. If any problem is acquired in server-side, it requires code
knowledge to solve. Client-side problems should be fixed with an update and it also requires code
knowledge and network knowledge. The cost should be low because a free availability of software
package.

7. PRELIMINARY TIMELINE

Week 1: Project kickoff, requirement gathering, and initial system design.

Week 2: Set up video capture, image pre-processing, and face detection modules.
Week 3: Implement feature extraction and face classification modules.
Week 4: Integrate database for employee data storage and retrieval.
Week 5: Develop and integrate face tracking and user interface.
Week 6: System testing, debugging, and final deployment preparation.

8. SOFTWARE HARDWARE REQUIREMENTS.

● Hardware: Processor above 1.5GHZ Hard Disk : 80GB RAM : 2GB
● User Interface : OS: Windows 11 (64 bit)
● Software: Visual stdio code( vs code)

9. OPERATIONAL SCENARIO

User Registration: The system provides an option to register new admins. The registration process includes
entering a username, password, and capturing a face dataset using the camera via Open-CV. The captured face
images are processed and stored in the database, associated with the admin’s credentials. Users (admins or HR
personnel) can log in using their username and password, which are authenticated against the stored credentials in
the database.

Face Recognition Login: Users can opt for face recognition-based login. The system captures a live image using
the camera and compares it with the stored face dataset using Open-CV and machine learning algorithms. If a
match is found, the user is authenticated and granted access to the system.

Access Control: The system manages multiple admin profiles, each with specific access rights. Admins can
view, add, or modify employee data and manage salary records based on their assigned privileges.

Employee Management: After successful login, admins can access the employee management application. They
can add new employee details, including personal information, job title, department, and salary. The system
stores the data in a secure database for future reference. Admins can search for existing employees using their ID
or name and update their records as needed (e.g., promotion, salary changes, department transfer).

Salary Management: The system includes features for salary management, allowing admins to enter, update,
and view salary information for each employee. Salary records can be tracked over time, providing insights into
payroll trends and budgeting.

System Security and Privacy: The system uses machine learning algorithms to enhance the accuracy of face
recognition. It continually improves recognition accuracy by learning from new data. All sensitive data, including
user credentials, employee records, and salary information, is encrypted to ensure security and privacy.

10 . FUTURE SCOPE

The future scope of the face recognition-based employee management system includes several key enhancements
and expansions. Integrating advanced deep learning models like CNNs can significantly improve face recognition
accuracy, even in challenging conditions. The system could also benefit from multi-factor authentication (MFA)
by combining face recognition with other biometric methods like fingerprint or voice recognition. Expanding its
features, the system could automatically track attendance, manage visitors, and incorporate shift and task
management, streamlining HR operations further. Additionally, mobile app development and cloud integration
would enhance accessibility and scalability, allowing remote access and supporting a larger user base.

Security and compliance are critical areas for future development. Implementing AI-powered fraud detection,
block-chain technology for secure data storage, and ensuring GDPR compliance would strengthen the system's
security and data privacy. Integrating the system with other enterprise systems like HRMS or ERP, along with
supporting multi-language capabilities, would facilitate global deployment. Furthermore, advanced data analytics
and predictive analytics could provide valuable insights into employee performance and HR trends, while
ensuring ethical AI practices would maintain fairness and avoid bias in employee management.
 Appendix A – Data Dictionary

An application of face recognition in employee management system has been implemented. By this method,
we can detect face for login also using traditional login method by username and password, inserting the
employee record, managing employee record, managing employee salary .As a part of Future Enhancement
the complete process described in this project can be automated so that the result can be delivered in a very
short time.
 Appendix B - Group Log
Opening: Meeting was called by our group leader on 9 August 2024

Present: All Members Are present.

Approval of Minutes:
An application of detecting the face recognition in employee management and providing the
necessary suggestions for the disease has been implemented. This Project deals with face
recognition with employee management application o enhance the security and convenience of the
login process for employees and administrators. Face recognition technology offers a significant
improvement over traditional methods by reducing the risk of password theft and unauthorized
access, providing a more secure authentication mechanism. Additionally, the system aims to enable
the creation and management of various admin profiles with specific access rights and
responsibilities. Hence the project is approved and it will ensure that the product must be launched
at minimum cost and easy to handle the environment. The efforts taken by all members are equal.

Minutes approved by : Mrunal deshpande

Minutes Submitted by:Purva Jage
Minutes approved by: Jidnyasa kalsekar

Conclusion:
Hence the detailed documentation of our project based on SRS is successfully performed.