FACE RECOGNITION BASED ON PRE-TRAINED CONVOLUTIONAL NEURAL NETWORK AND MACHINE LEARNING FOR ATTENDANCE AUTOMATION

Abstract

ABSTRACT The present invention provides the system and method which uses the face recognition functionality provided by the face recognition library, which internally utilizes deep learning for face encoding and comparison. Further, it employs deep learning model and algorithm for face recognition is based on a pre-trained neural network, typically a convolutional neural network (CNN).

Specification

Description:FORM 2
THE PATENTS ACT, 1970
(39 OF 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(See section 10; rule 13)



Title: Face Recognition Based on Pre-Trained Convolutional Neural Network and Machine Learning for Attendance Automation




APPLICANT DETAILS:
(a) NAME: GRAPHIC ERA DEEMED TO BE UNIVERSITY
(b) NATIONALITY: Indian
(c) ADDRESS: 566/6, Bell Road, Society Area, Clement Town, Dehradun - 248002,
Uttarakhand, India







PREAMBLE TO THE DESCRIPTION:
The following specification particularly describes the nature of this invention and the manner in which it is to be performed.

Face Recognition Based on Pre-Trained Convolutional Neural Network and Machine Learning for Attendance Automation

Field of Invention:
The present invention relates to system and method for an automatic attendance using Python and face Recognition.

Background of the Invention.
The following background discussion includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication expressly or implicitly referenced is prior art.
The Attendance Automation using Face Recognition has gained significant attention due to its potential to streamline and amplify traditional systems of attendance. The system uses computer vision techniques to analyze and identify individuals based on their facial features, hence, providing a seamless and contactless method for recording attendance.

The motivation behind pursuing an automatic attendance system, specifically using Face Recognition arises from the inherent limitations and challenges associated with the conventional methods. Traditional manual attendance processes are time-consuming, prone to errors, and lack the real-time monitoring capabilities which are essential for modern organizational needs. The implementation of a facial recognition-based system addresses these shortcomings by offering a swift, accurate, and flawless means of attendance tracking.

The entire recognition system revolves around developing a robust attendance tracking system using machine learning technology. Existing manual and even various biometric methods for recording attendance are significantly inefficient. For instance, Fingerprint Recognition is vulnerable to spoofing, faces difficulty with unclear fingerprint and possesses privacy concerns. Iris Recognition is invasive and requires close alignment. Not only are false rejections always a possibility, but also it is expensive and complex. Voice Recognition method is vulnerable to mimicry, and it is significantly affected by background noise. Changes in voice may as well impact accuracy. Hand Geometry and Retina Scanning shares the same case of being invasive, high cost and complexity, limited discriminatory power and possibility for false rejections.
The present invention aims to overcome these challenges by employing ML-based facial recognition algorithms. The objective is to design a solution that provides reliable, real-time, and contactless attendance tracking. The system should be user-friendly inexpensive and adaptable to different environments according to the evolving needs.

Object(s) of the present invention:
The primary objective of the present invention is to overcome the drawback associated with prior art.
An object of the present invention is to provide the face recognition functionality provided by the face recognition library, which internally utilizes deep learning for face encoding and comparison. Further, it employs deep learning model and algorithm for face recognition is based on a pre-trained neural network, typically a convolutional neural network (CNN).
Summary of the Invention:
In an embodiment, the system and method of present invention uses the face recognition functionality provided by the face recognition library, which internally utilizes deep learning for face encoding and comparison. Further, it employs deep learning model and algorithm for face recognition is based on a pre-trained neural network, typically a convolutional neural network (CNN).

Brief description of Drawings:
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. The reference numbers are used throughout the figures to describe the features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which
Figure 1: illustrates small collection of images from the LFW dataset, typically including images with varying qualities and resolutions, reflecting the actual challenges faced in real-world Face Recognition scenarios.
Figure 2: illustrates recognized images of the individuals.
Detailed description of the invention:
In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example, in the drawings and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.
The terms "comprises", "comprising", "includes", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by "comprises... a" does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
In an embodiment, the system of the present invention uses the following Algorithmic Approach:
1. Initialize Video Capture: Set up the video capture from the default camera with a specified resolution.
2. cv2 (OpenCV): OpenCV, a widely used computer vision library, serves the purpose of capturing video from the camera, image processing, and drawing rectangles and text on video frames.
2. Load Known Faces and Encodings: Load pre-existing images of known individuals and extract their face encodings using the Face Recognition library.
3. Initialize CSV File for Attendance Logging: Open a CSV file for writing attendance information, including the name and timestamp.
4. Start Separate Thread for Video Processing: Begin a separate thread to continuously process video frames for Face Recognition without blocking the main program.
5. Process Video Frames in a Loop: A frame is captured from the video feed and further resized to improve processing speed. Face locations are detected in the frame using the face_recognition library. The Face encodings are further extracted from the detected faces. The detected face encodings are compared with the known face encodings in order to find a match. If a match is found and the person is identified, their presence is marked and eventually the list of present individuals is updated in the CSV file.
6. Terminate the Program: Stop video capture and close all windows when the user presses 'q' in the video window. This algorithm utilizes Face Recognition techniques, threading for parallel processing, and CSV file handling to create a real-time attendance system based on recognized faces.
In researching and deploying CNN-based face recognition in the present invention , several key contributions have been made, including:
Development of novel CNN architectures specifically tailored for face recognition tasks, to effectively learn discriminative features from facial images, leading to improved recognition accuracy.
Implementation of data augmentation techniques to enhance the robustness of CNN-based face recognition models.
Integration of metric learning techniques into CNN architectures where faces of the same identity are clustered closer together while faces of different identities are separated.
Investigation of domain adaptation methods to improve the performance of CNN-based face recognition models when faced with domain shifts or differences between training and testing data distributions. Techniques such as adversarial training, domain adversarial neural networks (DANN), and self-training have been explored to address this challenge.

In the present invention, the LFW Database (Labeled Faces in The Wild) to implement the automation system and conduct the recognition of individuals under real-world conditions. LFW consists of more than 13,000 labeled images of faces, spanning a wide range of variations, such as pose, lighting, expression, age, and background. Due to its diverse nature, LFW poses challenges for Face Recognition algorithms, especially those designed for unconstrained environments. These factors and expressions make it a robust and standard benchmark in the field. We represented a few sample images from LFW dataset in Fig. 1.
Attendance Automation is a system that uses artificial intelligence and machine learning algorithms for attendance tracking processes. This methodology unifies various components and incudes various steps which are as follows:
Data Collection and Data Preparation
Face Detection
Feature Selection
Model Training and Evaluation
Deployment
Real Time Face Recognition
Post Processing and Logging
The present invention is utilizing the face recognition library, which internally employs a pre-trained CNN for face encoding which is a deep learning model for image-related tasks. It consists of convolutional layers that learn hierarchical features from input images. The Face Recognition process involves encoding each face image into a numerical representation using the CNN. These embeddings, capture distinctive features of each face, enabling accurate comparison between faces. The comparison is performed using a distance metric, typically Euclidean distance, or a similar measure, to determine the similarity between face encodings. Based on the computed distances, the system makes decisions about whether a given face in a video frame matches any of the known faces in the dataset. A threshold is set to determine when a match is considered valid. If the distance is below the threshold, the faces are considered a match. In mathematical terms, if (E1) and (E2) represent the face encodings of two faces, the distance metric (D) can be calculated using Euclidean distance:
D=v(?_(i=1)^n¦(E_1i-E_2i )^2 ) (1)
where (n) is the dimensionality of the face encoding.
All the various features and libraries of artificial intelligence and machine learning that are utilized for the recognition system are:



Table 1. AI-ML based features utilized in implementation.
CATEGORY FEATURES UTILIZED
Artificial Intelligence Face Recognition, Machine Learning (through face encoding and comparison), Attendance Tracking (by recognizing and matching faces).
Machine Learning Face Recognition, Attendance Tracking (using face encoding and comparison for recognition), List and Dictionary Manipulation (storing and retrieving information about recognized faces).
Deep learning Face Recognition (utilizing deep learning for face encodings), Machine Learning (facilitated through deep learning models for face comparison).
Computer Vision Image Processing (resizing and converting frames), Drawing Rectangles and Text on Faces (using OpenCV for visual feedback).
Multi-Threading Parallel Processing of Video Frames, Attendance Checking (using threading for concurrent operations).
Data Handling CSV Handling (reading and writing data to a CSV file), File Input/Output (loading face images from files).
Date and Time Handling Capturing Current Date and Time for attendance logging.
Error Handling Basic exception handling for robustness.

In the present invention, the implementation of the Attendance Automation system by utilizing artificial intelligence-based Face Recognition capabilities rather than implementing a specific machine learning algorithm from scratch in order to amplify the system's efficiency and accuracy. The proposed methodology was applied in the LFW database, which consisted of 13,000 labeled faces of individuals, hereby ensuring a diverse and unconstrained set of faces.
The present invention utilizes and applied CNN based face recognition technique using pre-defined machine learning algorithm to identify everyone for face recognition. The video capture frame used is 1280 × 720. To increase the calculation speed, the original captured frame is resized by 25% of their original form. The system effectively utilized the face recognition library and associated recognized faces with pre-loaded encodings of known individuals.
In addition, providing user interaction via the 'q' key boosts the system's simplicity. It lets users gracefully exit the live Face Recognition process. This feature guarantees an orderly end to the script. When the user wishes to exit, the system conducts a final attendance update, checking and updating any remaining entries in the csv file to accurately reflect the attendance records in the associated attendance database.
Advantages and Disadvantages of the Method of the present invention:
Using Convolutional Neural Networks (CNNs) for face recognition comes with its own set of pros and cons:
Advantages
High Accuracy: CNNs are known for their ability to learn complex patterns and features, making them effective for accurately recognizing faces.
Robustness to Variations: Variations in lighting, facial expressions, and poses can be handled efficiently by CNNs, making them suitable for real-world applications where faces may appear in different conditions.
Efficiency: CNN-based face recognition systems can process images quickly, making them suitable for real-time applications like surveillance or authentication systems.
Feature Learning: CNNs automatically learn relevant features from the data, reducing the need for manual feature engineering.
Scalability: CNN-based models can be scaled to handle large datasets and can be trained on distributed systems, enabling efficient processing of a large number of faces.

Disadvantages
Data Privacy Concerns: Face recognition systems using CNNs raise concerns about privacy and surveillance, as they can be used to track individuals without their consent.
Bias and Fairness: Ensuring fairness and mitigating biases is a significant challenge in deploying face recognition systems.
Data Security and Ethical Considerations: Storing facial data for recognition purposes raises concerns about data security and the potential for misuse or unauthorized access to sensitive information.
Resource Intensive: Training CNN models for face recognition requires significant computational resources, including powerful hardware and large datasets, which may be a barrier for smaller organizations or projects.
Result:
In the present invention the successful development of an Attendance Automation system using Face Recognition and CNN has been possible by leveraging the capabilities of the Face Recognition library. The system adeptly processes video frames sourced from a webcam, employing Convolutional Neural Network (CNN)-based facial recognition algorithms to match and associate detected faces with pre-loaded encodings of known individuals. The seamless integration of these components has resulted in an efficient and reliable solution for automating the attendance tracking process.
The present invention shows the practical application of facial recognition technology in the realm of education and other administration. As a tool designed to enhance accuracy and streamline administrative tasks, the implemented system aligns with contemporary technological advancements, offering a viable and innovative approach to attendance management. This successful development of the automation system highlights the potential of leveraging cutting-edge technologies to optimize routine processes, laying the foundation for future endeavours in the realm of automated systems and biometric applications.
Dated this the 14th day of November 2024
, Claims:FORM 2
THE PATENTS ACT, 1970
(39 OF 1970)
&
THE PATENTS RULES, 2003
COMPLETE SPECIFICATION
(See section 10; rule 13)



Title: Face Recognition Based on Pre-Trained Convolutional Neural Network and Machine Learning for Attendance Automation




APPLICANT DETAILS:
(a) NAME: GRAPHIC ERA DEEMED TO BE UNIVERSITY
(b) NATIONALITY: Indian
(c) ADDRESS: 566/6, Bell Road, Society Area, Clement Town, Dehradun - 248002,
Uttarakhand, India







PREAMBLE TO THE DESCRIPTION:
The following specification particularly describes the nature of this invention and the manner in which it is to be performed.

Face Recognition Based on Pre-Trained Convolutional Neural Network and Machine Learning for Attendance Automation

Field of Invention:
The present invention relates to system and method for an automatic attendance using Python and face Recognition.

Background of the Invention.
The following background discussion includes information that may be useful in understanding the present invention. It is not an admission that any of the information provided herein is prior art or relevant to the presently claimed invention, or that any publication expressly or implicitly referenced is prior art.
The Attendance Automation using Face Recognition has gained significant attention due to its potential to streamline and amplify traditional systems of attendance. The system uses computer vision techniques to analyze and identify individuals based on their facial features, hence, providing a seamless and contactless method for recording attendance.

The motivation behind pursuing an automatic attendance system, specifically using Face Recognition arises from the inherent limitations and challenges associated with the conventional methods. Traditional manual attendance processes are time-consuming, prone to errors, and lack the real-time monitoring capabilities which are essential for modern organizational needs. The implementation of a facial recognition-based system addresses these shortcomings by offering a swift, accurate, and flawless means of attendance tracking.

The entire recognition system revolves around developing a robust attendance tracking system using machine learning technology. Existing manual and even various biometric methods for recording attendance are significantly inefficient. For instance, Fingerprint Recognition is vulnerable to spoofing, faces difficulty with unclear fingerprint and possesses privacy concerns. Iris Recognition is invasive and requires close alignment. Not only are false rejections always a possibility, but also it is expensive and complex. Voice Recognition method is vulnerable to mimicry, and it is significantly affected by background noise. Changes in voice may as well impact accuracy. Hand Geometry and Retina Scanning shares the same case of being invasive, high cost and complexity, limited discriminatory power and possibility for false rejections.
The present invention aims to overcome these challenges by employing ML-based facial recognition algorithms. The objective is to design a solution that provides reliable, real-time, and contactless attendance tracking. The system should be user-friendly inexpensive and adaptable to different environments according to the evolving needs.

Object(s) of the present invention:
The primary objective of the present invention is to overcome the drawback associated with prior art.
An object of the present invention is to provide the face recognition functionality provided by the face recognition library, which internally utilizes deep learning for face encoding and comparison. Further, it employs deep learning model and algorithm for face recognition is based on a pre-trained neural network, typically a convolutional neural network (CNN).
Summary of the Invention:
In an embodiment, the system and method of present invention uses the face recognition functionality provided by the face recognition library, which internally utilizes deep learning for face encoding and comparison. Further, it employs deep learning model and algorithm for face recognition is based on a pre-trained neural network, typically a convolutional neural network (CNN).

Brief description of Drawings:
The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, explain the disclosed principles. The reference numbers are used throughout the figures to describe the features and components. Some embodiments of system and/or methods in accordance with embodiments of the present subject matter are now described, by way of example only, and regarding the accompanying figures, in which
Figure 1: illustrates small collection of images from the LFW dataset, typically including images with varying qualities and resolutions, reflecting the actual challenges faced in real-world Face Recognition scenarios.
Figure 2: illustrates recognized images of the individuals.
Detailed description of the invention:
In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary" is not necessarily to be construed as preferred or advantageous over other embodiments.
While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example, in the drawings and will be described in detail below. It should be understood, however, that it is not intended to limit the disclosure to the specific forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the spirit and the scope of the disclosure.
The terms "comprises", "comprising", "includes", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by "comprises... a" does not, without more constraints, preclude the existence of other elements or additional elements in the system or method.
In an embodiment, the system of the present invention uses the following Algorithmic Approach:
1. Initialize Video Capture: Set up the video capture from the default camera with a specified resolution.
2. cv2 (OpenCV): OpenCV, a widely used computer vision library, serves the purpose of capturing video from the camera, image processing, and drawing rectangles and text on video frames.
2. Load Known Faces and Encodings: Load pre-existing images of known individuals and extract their face encodings using the Face Recognition library.
3. Initialize CSV File for Attendance Logging: Open a CSV file for writing attendance information, including the name and timestamp.
4. Start Separate Thread for Video Processing: Begin a separate thread to continuously process video frames for Face Recognition without blocking the main program.
5. Process Video Frames in a Loop: A frame is captured from the video feed and further resized to improve processing speed. Face locations are detected in the frame using the face_recognition library. The Face encodings are further extracted from the detected faces. The detected face encodings are compared with the known face encodings in order to find a match. If a match is found and the person is identified, their presence is marked and eventually the list of present individuals is updated in the CSV file.
6. Terminate the Program: Stop video capture and close all windows when the user presses 'q' in the video window. This algorithm utilizes Face Recognition techniques, threading for parallel processing, and CSV file handling to create a real-time attendance system based on recognized faces.
In researching and deploying CNN-based face recognition in the present invention , several key contributions have been made, including:
Development of novel CNN architectures specifically tailored for face recognition tasks, to effectively learn discriminative features from facial images, leading to improved recognition accuracy.
Implementation of data augmentation techniques to enhance the robustness of CNN-based face recognition models.
Integration of metric learning techniques into CNN architectures where faces of the same identity are clustered closer together while faces of different identities are separated.
Investigation of domain adaptation methods to improve the performance of CNN-based face recognition models when faced with domain shifts or differences between training and testing data distributions. Techniques such as adversarial training, domain adversarial neural networks (DANN), and self-training have been explored to address this challenge.

In the present invention, the LFW Database (Labeled Faces in The Wild) to implement the automation system and conduct the recognition of individuals under real-world conditions. LFW consists of more than 13,000 labeled images of faces, spanning a wide range of variations, such as pose, lighting, expression, age, and background. Due to its diverse nature, LFW poses challenges for Face Recognition algorithms, especially those designed for unconstrained environments. These factors and expressions make it a robust and standard benchmark in the field. We represented a few sample images from LFW dataset in Fig. 1.
Attendance Automation is a system that uses artificial intelligence and machine learning algorithms for attendance tracking processes. This methodology unifies various components and incudes various steps which are as follows:
Data Collection and Data Preparation
Face Detection
Feature Selection
Model Training and Evaluation
Deployment
Real Time Face Recognition
Post Processing and Logging
The present invention is utilizing the face recognition library, which internally employs a pre-trained CNN for face encoding which is a deep learning model for image-related tasks. It consists of convolutional layers that learn hierarchical features from input images. The Face Recognition process involves encoding each face image into a numerical representation using the CNN. These embeddings, capture distinctive features of each face, enabling accurate comparison between faces. The comparison is performed using a distance metric, typically Euclidean distance, or a similar measure, to determine the similarity between face encodings. Based on the computed distances, the system makes decisions about whether a given face in a video frame matches any of the known faces in the dataset. A threshold is set to determine when a match is considered valid. If the distance is below the threshold, the faces are considered a match. In mathematical terms, if (E1) and (E2) represent the face encodings of two faces, the distance metric (D) can be calculated using Euclidean distance:
D=v(?_(i=1)^n¦(E_1i-E_2i )^2 ) (1)
where (n) is the dimensionality of the face encoding.
All the various features and libraries of artificial intelligence and machine learning that are utilized for the recognition system are:



Table 1. AI-ML based features utilized in implementation.
CATEGORY FEATURES UTILIZED
Artificial Intelligence Face Recognition, Machine Learning (through face encoding and comparison), Attendance Tracking (by recognizing and matching faces).
Machine Learning Face Recognition, Attendance Tracking (using face encoding and comparison for recognition), List and Dictionary Manipulation (storing and retrieving information about recognized faces).
Deep learning Face Recognition (utilizing deep learning for face encodings), Machine Learning (facilitated through deep learning models for face comparison).
Computer Vision Image Processing (resizing and converting frames), Drawing Rectangles and Text on Faces (using OpenCV for visual feedback).
Multi-Threading Parallel Processing of Video Frames, Attendance Checking (using threading for concurrent operations).
Data Handling CSV Handling (reading and writing data to a CSV file), File Input/Output (loading face images from files).
Date and Time Handling Capturing Current Date and Time for attendance logging.
Error Handling Basic exception handling for robustness.

In the present invention, the implementation of the Attendance Automation system by utilizing artificial intelligence-based Face Recognition capabilities rather than implementing a specific machine learning algorithm from scratch in order to amplify the system's efficiency and accuracy. The proposed methodology was applied in the LFW database, which consisted of 13,000 labeled faces of individuals, hereby ensuring a diverse and unconstrained set of faces.
The present invention utilizes and applied CNN based face recognition technique using pre-defined machine learning algorithm to identify everyone for face recognition. The video capture frame used is 1280 × 720. To increase the calculation speed, the original captured frame is resized by 25% of their original form. The system effectively utilized the face recognition library and associated recognized faces with pre-loaded encodings of known individuals.
In addition, providing user interaction via the 'q' key boosts the system's simplicity. It lets users gracefully exit the live Face Recognition process. This feature guarantees an orderly end to the script. When the user wishes to exit, the system conducts a final attendance update, checking and updating any remaining entries in the csv file to accurately reflect the attendance records in the associated attendance database.
Advantages and Disadvantages of the Method of the present invention:
Using Convolutional Neural Networks (CNNs) for face recognition comes with its own set of pros and cons:
Advantages
High Accuracy: CNNs are known for their ability to learn complex patterns and features, making them effective for accurately recognizing faces.
Robustness to Variations: Variations in lighting, facial expressions, and poses can be handled efficiently by CNNs, making them suitable for real-world applications where faces may appear in different conditions.
Efficiency: CNN-based face recognition systems can process images quickly, making them suitable for real-time applications like surveillance or authentication systems.
Feature Learning: CNNs automatically learn relevant features from the data, reducing the need for manual feature engineering.
Scalability: CNN-based models can be scaled to handle large datasets and can be trained on distributed systems, enabling efficient processing of a large number of faces.

Disadvantages
Data Privacy Concerns: Face recognition systems using CNNs raise concerns about privacy and surveillance, as they can be used to track individuals without their consent.
Bias and Fairness: Ensuring fairness and mitigating biases is a significant challenge in deploying face recognition systems.
Data Security and Ethical Considerations: Storing facial data for recognition purposes raises concerns about data security and the potential for misuse or unauthorized access to sensitive information.
Resource Intensive: Training CNN models for face recognition requires significant computational resources, including powerful hardware and large datasets, which may be a barrier for smaller organizations or projects.
Result:
In the present invention the successful development of an Attendance Automation system using Face Recognition and CNN has been possible by leveraging the capabilities of the Face Recognition library. The system adeptly processes video frames sourced from a webcam, employing Convolutional Neural Network (CNN)-based facial recognition algorithms to match and associate detected faces with pre-loaded encodings of known individuals. The seamless integration of these components has resulted in an efficient and reliable solution for automating the attendance tracking process.
The present invention shows the practical application of facial recognition technology in the realm of education and other administration. As a tool designed to enhance accuracy and streamline administrative tasks, the implemented system aligns with contemporary technological advancements, offering a viable and innovative approach to attendance management. This successful development of the automation system highlights the potential of leveraging cutting-edge technologies to optimize routine processes, laying the foundation for future endeavours in the realm of automated systems and biometric applications.
Dated this the 14th day of November 2024

Documents