Smart Attendance Monitoring System Using Face Recognition for People with Disabilities

Aim:

        The aim of the project is to develop an automated, real-time attendance system using face recognition technology to enhance accuracy, eliminate manual errors, and streamline attendance tracking in institutions.

Abstract:

          Face recognition can be considered one of the most successful biometric identification methods among several types of biometric identification including fingerprints, DNA, palm print, hand geometry, iris recognition and retina. Face recognition provides biometric identification that utilizes the uniqueness of faces for security purposes. The problem with face recognition using biometric identification is its lengthy process and the accuracy of the results. This paper proposes solutions for a faster face recognition process with accurate results. The proposed face recognition process was done using a Machine Learning. This improved face recognition approach was able to recognize multiple faces with high accuracy level.

Synopsis:

           Image processing is a technique for performing operations on an image in order to enhance it or obtain useful information. It’s a form of signal processing in which the input is an image and the output is either an image or the image’s characteristics or features. Image processing is one of the fastest-growing technologies. To detect and recognize the face using real time attendance system

Existing System:

        The existing attendance systems largely rely on traditional methods such as manual sign-ins, RFID cards, or fingerprint scanners, each with notable limitations. Manual sign-ins are time-consuming and error-prone, while RFID cards are susceptible to misuse, such as proxy attendance. Biometric systems like fingerprint scanners offer improved security but face issues related to hygiene, hardware reliability, and accessibility for individuals with disabilities. Recently, face recognition-based systems utilizing models like DNN Caffe for face detection and Open face for recognition have emerged, offering real-time accuracy of up to 92%. However, these systems are often desktop-based, dependent on controlled environments, and may struggle with varying lighting or multiple faces, limiting their robustness and scalability in real-world scenarios.

Problem Definition:

     Despite advancements in attendance monitoring systems, existing solutions often fall short in terms of efficiency, accuracy, and accessibility. Traditional methods like manual sign-ins, RFID cards, and fingerprint scanners are plagued by issues such as time consumption, error rates, and potential for misuse. While face recognition-based systems have emerged as a more accurate alternative, current implementations frequently rely on desktop-based applications that necessitate controlled environments, limiting their practicality and scalability in real-world scenarios. Moreover, these systems may not adequately address the needs of individuals with disabilities, highlighting a significant gap in accessible attendance solutions.

Proposed System:

       This research presents a novel solution to automate attendance-taking processes in various settings, particularly educational institutions, by introducing a web-based smart attendance monitoring system utilizing facial recognition technology. Addressing the inefficiencies of traditional methods like RFID cards or manual signing, the proposed system offers an efficient, accurate, and accessible means of registering attendance, with particular emphasis on inclusivity for students with disabilities. The system leverages the Local Binary Patterns Histogram (LBPH) algorithm for face recognition and OpenCV for live image capture, integrated within a web application built using Flask, HTML, CSS, JavaScript, and Bootstrap.

        This institution web portal provides a user-friendly interface for administrators and users. The system demonstrates robust performance in diverse environmental conditions, achieving reliable accuracy even in the presence of varying lighting, orientations, and backgrounds. This research contributes to the development of more efficient and inclusive attendance management systems while paving the way for further advancements and broader applications beyond education.

Advantage:

• Real-Time Attendance: The system captures and processes faces in real-time, automating attendance tracking without the need for manual intervention.
• Increased Accuracy: Using the LBPH algorithm for facial recognition ensures reliable and accurate identification, reducing errors and the possibility of proxy attendance.
• Web-Based System: By utilizing Flask, HTML, CSS, JavaScript, and Bootstrap, the system is accessible via any web browser, allowing administrators and users to easily manage and monitor attendance remotely.
• User-Friendly Interface: The web application is designed with a simple and intuitive UI, making it easy for users and administrators to interact with the system.