Facial Recognition Based Attendance With Liveness Detection — Complete Documentation & Simulation

Overview & System Context

Facial Recognition Based Attendance With Liveness Detection: Comprehensive Web-Sourced Technical Investigation Exhaustive Research Dossier · Pure Web-Scraped Content: ~5547 Words · Real Software Screenshots: 3 1. Executive Overview & Technical Background Facial recognition systems are applications that use algorithms to compare facial images or representations to verify an identity or to identify a person from a set of known identities. One-to-one verification compares a facial image to a reference image that is linked to a claimed identity. One-to-many identification is a search of an image against a database to determine if the image matches a database ID. Development on similar systems began in the 1960s as a form of computer application.

Since their inception, facial recognition systems have seen wider uses in recent times on smartphones and in other forms of technology, such as robotics. Because computerized facial recognition involves the measurement of a human's physiological characteristics, facial recognition systems are categorized as biometrics. Although the accuracy of facial recognition systems as a biometric technology is lower than iris recognition, fingerprint image acquisition, palm recognition or voice recognition, it is widely adopted due to its contactless process. Facial recognition systems have been deployed in advanced human–computer interaction, video surveillance, law enforcement, passenger screening, decisions on employment and housing, and automatic indexing of images. Facial recognition systems are employed throughout the world today by governments and private companies. Their effectiveness varies, and some systems have previously been scrapped because of their ineffectiveness. The use of facial recognition systems has also raised controversy, with claims that the systems violate citizens' privacy, commonly make incorrect identifications, encourage gender norms and racial profiling, and do not protect important biometric data. The appearance of synthetic media such as deepfakes has also raised concerns about its security.

These claims have led to the ban of facial recognition systems in several cities in the United States. Growing societal concerns led social networking company Meta Platforms to shut down its Facebook facial recognition system in 2021, deleting the face-scan data of more than one billion users. The change represented one of the largest shifts in facial recognition usage in the technology's history. IBM also stopped offering facial recognition technology due to similar concerns.

While humans can recognize faces without much effort, facial recognition is a challenging pattern recognition problem in computing. Facial recognition systems attempt to identify a human face, which is three-dimensional and changes in appearance with lighting and facial expression, based on its two-dimensional image. To accomplish this computational task, facial recognition systems perform four steps. First face detection is used to segment the face from the image background. In the second step the segmented face image is aligned to account for face pose, image size and photographic properties, such as illumination and grayscale. The purpose of the alignment process is to enable the accurate localization of facial features in the third step, the facial feature extraction. Features such as eyes, nose and mouth are pinpointed and measured in the image to represent the face. The so established feature vector of the face is then, in the fourth step, matched against a database of faces.

Some face recognition algorithms identify facial features by extracting landmarks, or features, from an image of the subject's face. For example, an algorithm may analyze the relative position, size, and/or shape of the eyes, nose, cheekbones, and jaw. These features are then used to search for other images with matching features. Other algorithms normalize a gallery of face images and then compress the face data, only saving the data in the image that is useful for face recognition. A probe image is then compared with the face data. One of the earliest successful systems is based on template matching techniques applied to a set of salient facial features, providing a sort of compressed face representation. Recognition algorithms can be divided into two main approaches: geometric, which looks at distinguishing features, or photo-metric, which is a statistical approach that distills an image into values and compares the values with templates to eliminate variances. Some classify these algorithms into two broad categories: holistic and feature-based models. The former attempts to recognize the face in its entirety while the feature-based subdivide into components such as according to features and analyze each as well as its spatial location with respect to other features. Popular recognition algorithms include principal component analysis using eigenfaces, linear discriminant analysis, elastic bunch graph matching using the Fisherface algorithm, the hidden Markov model, the multilinear subspace learning using tensor representation, and the neuronal motivated dynamic link matching.

Modern facial recognition systems make increasing use of machine learning techniques such as deep learning. Three-dimensional face recognition technique uses 3D sensors to capture information about the shape of a face. This information is then used to identify distinctive features on the surface of a face, such as the contour of the eye sockets, nose, and chin. One advantage of 3D face recognition is that it is not affected by changes in lighting like other techniques. It can also identify a face from a range of viewing angles, including a profile view. Three-dimensional data points from a face vastly improve the precision of face recognition. 3D-dimensional face recognition research is enabled by the development of sophisticated sensors that project structured light onto the face. 3D matching technique are sensitive to expressions, therefore researchers at Technion applied tools from metric geometry to treat expressions as isometries. A new method of capturing 3D images of faces uses three tracking cameras that point at different angles; one camera will be pointing at the front of the subject, second one to the side, and third one at an angle. All these cameras will work together so it can track a subject's face in real-time and be able to face detect and recognize.

Figure 1: GitHub - 20dcs/Face-Recognition-Based-Attendance-System · GitHub A different form of taking input data for face recognition is by using thermal cameras, by this procedure the cameras will only detect the shape of the head and it will ignore the subject accessories such as glasses, hats, or makeup. Unlike conventional cameras, thermal cameras can capture facial imagery even in low-light and nighttime conditions without using a flash and exposing the position of the camera. However, the databases for face recognition are limited. Efforts to build databases of thermal face images date back to 2004. By 2016, several databases existed, including the IIITD-PSE and the Notre Dame thermal face database. Current thermal face recognition systems are not able to reliably detect a face in a thermal image that has been taken of an outdoor environment. In 2018, researchers from the U.S. Army Research Laboratory (ARL) developed a technique that would allow them to match facial imagery obtained using a thermal camera with those in databases that were captured using a conventional camera. Known as a cross-spectrum synthesis method due to how it bridges facial recognition from two different imaging modalities, this method synthesize a single image by analyzing multiple facial regions and details. It consists of a non-linear regression model that maps a specific thermal image into a corresponding visible facial image and an optimization issue that projects the latent projection back into the image space. ARL scientists have noted that the approach works by combining global information (i.e. features across the entire face) with local information (i.e. features regarding the eyes, nose, and mouth). According to performance tests conducted at ARL, the multi-region cross-spectrum synthesis model demonstrated a performance improvement of about 30% over baseline methods and about 5% over state-of-the-art methods.

The U.S. Department of State operates one of the largest face recognition systems in the world with a database of 117 million American adults, with photos typically drawn from driver's license photos. Although it is still far from completion, it is being put to use in certain cities to give clues as to who was in the photo. The FBI uses the photos as an investigative tool, not for positive identification. As of 2016, facial recognition was being used to identify people in photos taken by police in San Diego and Los Angeles (not on real-time video, and only against booking photos) and use was planned in West Virginia and Dallas.

In recent years Maryland has used face recognition by comparing people's faces to their driver's license photos. The system drew controversy when it was used in Baltimore to arrest unruly protesters after the death of Freddie Gray in police custody. Many other states are using or developing a similar system however some states have laws prohibiting its use. The FBI has also instituted its Next Generation Identification program to include face recognition, as well as more traditional biometrics like fingerprints and iris scans, which can pull from both criminal and civil databases. The federal Government Accountability Office criticized the FBI for not addressing various concerns related to privacy and accuracy. Starting in 2018, U.S. Customs and Border Protection deployed "biometric face scanners" at U.S. airports. Passengers taking outbound international flights can complete the check-in, security and the boarding process after getting facial images captured and verified by matching their ID photos stored on CBP's database. Images captured for travelers with U.S. citizenship will be deleted within up to 12-hours. The Transportation Security Administration (TSA) had expressed its intention to adopt a similar program for domestic air travel during the security check process in the future. The American Civil Liberties Union is one of the organizations against the program, concerning that the program will be used for surveillance purposes. In 2019, researchers reported that Immigration and Customs Enforcement (ICE) uses facial recognition software against state driver's license databases, including for some states that provide licenses to undocumented immigrants. In December 2022, 16 major domestic airports in the US started testing facial-recognition tech where kiosks with cameras are checking the photos on travelers' IDs to make sure that passengers are not impostors. In 2025, it was revealed that the New Orleans Police Department had rolled out what the ACLU's Freed Wessler called "the first known widespread effort by police in a major US city to use AI to identify people in live camera feeds for the purpose of making immediate arrests." in defiance of a 2022 city ordinance limiting the use of the technology. During the 2026 Delaney Hall protests, Department of Homeland Security (DHS) secretary Markwayne Mullin acknowledged facial recognition systems were used to successfully identify protesters.

In 2006, the "Skynet" (II) Project was initiated by the Chinese government to implement CCTV surveillance nationwide and as of 2018, there have been 20 million cameras, many of which are capable of real-time facial recognition, deployed across the country for this project. Some official claim that the current Skynet system can scan the entire Chinese population in one second and the world population in two seconds.

2. System Architecture & Core Working Principles In 2017, the Qingdao police was able to identify twenty-five wanted suspects using facial recognition equipment at the Qingdao International Beer Festival, one of which had been on the run for 10 years. The equipment works by recording a 15-second video clip and taking multiple snapshots of the subject. That data is compared and analyzed with images from the police department's database and within 20 minutes, the subject can be identified with a 98.1% accuracy. In 2018, Chinese police in Zhengzhou and Beijing were using smart glasses to take photos which are compared against a government database using facial recognition to identify suspects, retrieve an address, and track people moving beyond their home areas.

As of late 2017, China has deployed facial recognition and artificial intelligence technology in Xinjiang. Reporters visiting the region found surveillance cameras installed every hundred meters or so in several cities, as well as facial recognition checkpoints at areas like gas stations, shopping centers, and mosque entrances. In May 2019, Human Rights Watch reported finding Face++ code in the Integrated Joint Operations Platform (IJOP), a police surveillance app used to collect data on, and track the Uighur community in Xinjiang. Human Rights Watch released a correction to its report in June 2019 stating that the Chinese company Megvii did not appear to have collaborated on IJOP, and that the Face++ code in the app was inoperable.

In February 2020, following the Coronavirus outbreak, Megvii applied for a bank loan to optimize the body temperature screening system it had launched to help identify people with symptoms of a Coronavirus infection in crowds. In its loan application documents, Megvii stated that it needed to improve the accuracy of identifying masked individuals. Many public places in China are implemented with facial recognition equipment, including railway stations, airports, tourist attractions, expos, and office buildings. In October 2019, a professor at Zhejiang Sci-Tech University sued the Hangzhou Safari Park for abusing private biometric information of customers. The safari park uses facial recognition technology to verify the identities of its Year Card holders. An estimated 300 tourist sites in China have installed facial recognition systems and use them to admit visitors. This case is reported to be the first on the use of facial recognition systems in China. In August 2020, Radio Free Asia reported that in 2019 Geng Guanjun, a citizen of Taiyuan City who had used the WeChat app by Tencent to forward a video to a friend in the United States was subsequently convicted on the charge of the crime "picking quarrels and provoking troubles".

The Court documents showed that the Chinese police used a facial recognition system to identify Geng Guanjun as an "overseas democracy activist" and that China's network management and propaganda departments directly monitor WeChat users. In 2019, Protestors in Hong Kong destroyed smart lampposts amid concerns they could contain cameras and facial recognition system used for surveillance by Chinese authorities. Human rights groups have criticized the Chinese government for using artificial intelligence facial recognition technology in its suppression against Uyghurs, Christians and Falun Gong practitioners.

Even though facial recognition technology (FRT) is not fully accurate, it is being increasingly deployed for identification purposes by the police in India. FRT systems generate a probability match score, or a confidence score between the suspect who is to be identified and the database of identified criminals that is available with the police. The National Automated Facial Recognition System (AFRS) is already being developed by the National Crime Records Bureau (NCRB), a body constituted under the Ministry of Home Affairs. The project seeks to develop and deploy a national database of photographs which would comport with a facial recognition technology system by the central and state security agencies. The Internet Freedom Foundation has flagged concerns regarding the project. The NGO has highlighted that the accuracy of FRT systems are "routinely exaggerated and the real numbers leave much to be desired. The implementation of such faulty FRT systems would lead to high rates of false positives and false negatives in this recognition process." Under the Supreme Court of India's decision in Justice K.S. Puttaswamy vs Union of India (22017 10 SCC 1), any justifiable intrusion by the State into people's right to privacy, which is protected as a fundamental right under Article 21 of the Constitution, must confirm to certain thresholds, namely: legality, necessity, proportionality and procedural safeguards. As per the Internet Freedom Foundation, the National Automated Facial Recognition System (AFRS) proposal fails to meet any of these thresholds, citing "absence of legality," "manifest arbitrariness," and "absence of safeguards and accountability." While the national level AFRS project is still in the works, police departments in various states in India are already deploying facial recognition technology systems, such as: TSCOP + CCTNS in Telangana, Punjab Artificial Intelligence System (PAIS) in Punjab, Trinetra in Uttar Pradesh, Police Artificial Intelligence System in Uttarakhand, AFRS in Delhi, Automated Multimodal Biometric Identification System (AMBIS) in Maharashtra, FaceTagr in Tamil Nadu. The Crime and Criminal Tracking Network and Systems (CCTNS), which is a Mission Mode Project under the National e-Governance Plan (NeGP), is viewed as a system which would connect police stations across India, and help them "talk" to each other. The project's objective is to digitize all FIR-related information, including FIRs registered, as well as cases investigated, charge sheets filed, and suspects and wanted persons in all police stations. This shall constitute a national database of crime and criminals in India. CCTNS is being implemented without a data protection law in place. CCTNS is proposed to be integrated with the AFRS, a repository of all crime and criminal related facial data which can be deployed to purportedly identify or verify a person from a variety of inputs ranging from images to videos. This has raised privacy concerns from civil society organizations and privacy experts. Both the projects have been censured as instruments of "mass surveillance" at the hands of the state. In Rajasthan, 'RajCop,' a police app has been recently integrated with a facial recognition module which can match the face of a suspect against a database of known persons in real-time.

Rajasthan police is in currently working to widen the ambit of this module by making it mandatory to upload photographs of all arrested persons in CCTNS database, which will "help develop a rich database of known offenders." Helmets fixed with camera have been designed and being used by Rajasthan police in law and order situations to capture police action and activities of "the miscreants, which can later serve as evidence during the investigation of such cases." PAIS (Punjab Artificial Intelligence System), App employs deep learning, machine learning, and face recognition for the identification of criminals to assist police personnel. The state of Telangana has installed 8 lakh CCTV cameras, with its capital city Hyderabad slowly turning into a surveillance capital. A false positive happens when facial recognition technology misidentifies a person to be someone they are not, that is, it yields an incorrect positive result. They often results in discrimination and strengthening of existing biases. For example, in 2018, Delhi Police reported that its FRT system had an accuracy rate of 2%, which sank to 1% in 2019. The FRT system even failed to distinguish accurately between different sexes. The government of Delhi in collaboration with Indian Space Research Organisation (ISRO) is developing a new technology called Crime Mapping Analytics and Predictive System (CMAPS). The project aims to deploy space technology for "controlling crime and maintaining law and order." The system will be connected to a database containing data of criminals. The technology is envisaged to be deployed to collect real-time data at the crime scene. In a reply dated November 25, 2020 to a Right to Information request filed by the Internet Freedom Foundation seeking information about the facial recognition system being used by the Delhi Police (with reference number DEPOL/R/E/20/07128), the Office of the Deputy Commissioner of Police cum Public Information Officer: Crime stated that they cannot provide the information under section 8(d) of the Right to Information Act, 2005. A Right to Information (RTI) request dated July 30, 2020 was filed with the Office of the Commissioner, Kolkata Police, seeking information about the facial recognition technology that the department was using. The information sought was denied stating that the department was exempted from disclosure under section 24(4) of the RTI Act.

At the American football championship game Super Bowl XXXV in January 2001, police in Tampa Bay, Florida used Viisage face recognition software to search for potential criminals and terrorists in attendance at the event. 19 people with minor criminal records were potentially identified. Face recognition systems have also been used by photo management software to identify the subjects of photographs, enabling features such as searching images by person, as well as suggesting photos to be shared with a specific contact if their presence were detected in a photo. By 2008 facial recognition systems were typically used as access control in security systems. The United States' popular music and country music celebrity Taylor Swift surreptitiously employed facial recognition technology at a concert in 2018. The camera was embedded in a kiosk near a ticket booth and scanned concert-goers as they entered the facility for known stalkers. On August 18, 2019, The Times reported that the UAE-owned Manchester City hired a Texas-based firm, Blink Identity, to deploy facial recognition systems in a driver program. The club has planned a single super-fast lane for the supporters at the Etihad stadium. However, civil rights groups cautioned the club against the introduction of this technology, saying that it would risk "normalising a mass surveillance tool". The policy and campaigns officer at Liberty, Hannah Couchman said that Man City's move is alarming, since the fans will be obliged to share deeply sensitive personal information with a private company, where they could be tracked and monitored in their everyday lives. In 2019, casinos in Australia and New Zealand rolled out facial recognition to prevent theft, and a representative of Sydney's Star Casino said they would also provide 'customer service' like welcoming a patron back to a bar. In August 2020, amid the COVID-19 pandemic in the United States, American football stadiums of New York and Los Angeles announced the installation of facial recognition for upcoming matches. The purpose is to make the entry process as touchless as possible. Disney's Magic Kingdom, near Orlando, Florida, likewise announced a test of facial recognition technology to create a touchless experience during the pandemic; the test was originally slated to take place between March 23 and April 23, 2021, but the limited timeframe had been removed as of late April 2021. Media companies have begun using face recognition technology to streamline their tracking, organizing, and archiving pictures and videos.

Facial recognition technologies encounter significant challenges when identifying individuals with disabilities. For instance, systems have been shown to perform worse when recognizing individuals with Down syndrome, often leading to increased false match rates. This is due to distinct facial structures associated with the condition that are not adequately represented in training datasets. More broadly, facial recognition systems tend to overlook diverse physical characteristics related to disabilities. The lack of representative data for individuals with varying disabilities further emphasizes the need for inclusive algorithmic designs to mitigate bias and improve accuracy. Additionally, facial expression recognition technologies often fail to accurately interpret the emotional states of individuals with intellectual disabilities. This shortcoming can hinder effective communication and interaction, underscoring the necessity for systems trained on diverse datasets that include individuals with intellectual disabilities. Furthermore, biases in facial recognition algorithms can lead to discriminatory outcomes for people with disabilities. For example, certain facial features or asymmetries may result in misidentification or exclusion, highlighting the importance of developing accessible and fair biometric systems.

Figure 2: GitHub - kby-ai/FaceRecognition-Android: This is a demonstration of ... Critics of the technology complain that the London Borough of Newham scheme has, as of 2004, never recognized a single criminal, despite several criminals in the system's database living in the Borough and the system has been running for several years. "Not once, as far as the police know, has Newham's automatic face recognition system spotted a live target." This information seems to conflict with claims that the system was credited with a 34% reduction in crime (hence why it was rolled out to Birmingham also). An experiment in 2002 by the local police department in Tampa, Florida, had similarly disappointing results. A system at Boston's Logan Airport was shut down in 2003 after failing to make any matches during a two-year test period. In 2014, Facebook stated that in a standardized two-option facial recognition test, its online system scored 97.25% accuracy, compared to the human benchmark of 97.5%. Systems are often advertised as having accuracy near 100%; this is misleading as the outcomes are not universal. The studies often use samples that are smaller and less diverse than would be necessary for large scale applications. Because facial recognition is not completely accurate, it creates a list of potential matches. A human operator must then look through these potential matches and studies show the operators pick the correct match out of the list only about half the time. This causes the issue of targeting the wrong suspect.

Berkeley, California Oakland, California Boston, Massachusetts – June 30, 2020 Brookline, Massachusetts Cambridge, Massachusetts Northampton, Massachusetts Springfield, Massachusetts Somerville, Massachusetts Portland, Oregon – September 2020 The West Lafayette, Indiana City Council passed an ordinance banning facial recognition surveillance technology. On October 27, 2020, 22 human rights groups called upon the University of Miami to ban facial recognition technology. This came after the students accused the school of using the software to identify student protesters. The allegations were, however, denied by the university. A state police reform law in Massachusetts will take effect in July 2021; a ban passed by the legislature was rejected by governor Charlie Baker. Instead, the law requires a judicial warrant, limit the personnel who can perform the search, record data about how the technology is used, and create a commission to make recommendations about future regulations. Reports in 2024 revealed that some police departments, including San Francisco Police Department, had skirted bans on facial recognition technology that had been enacted in their respective cities.

Lists List of computer vision topics List of emerging technologies Outline of artificial intelligence 3. Software Implementation, Frameworks & Protocols A comprehensive Python-based attendance management system that uses facial recognition technology to automatically track attendance with fraud prevention and liveness detection.

Facial recognition technology can be an efficient and touch-free biometric technology for automating attendance in academic and organizational environments. The paper presents a comprehensive Facial Recognition Attendance System with Integrated Liveness Detection and Real-Time Reporting. The system is developed using Python and OpenCV library. The system utilizes a webcam for facial images, Haar Cascade for face detection, and LBPH for face recognition. The attendance data is stored in SQLite and displayed using a Flask-based web interface. The liveness detection component eliminates spoofing attacks by images or videos by detecting eye blinks and movements through frame differencing and motion analysis.

The system follows a modular approach for data collection, model training, real-time face recognition along with liveness detection, and automatic attendance recording. Experiments were conducted on a wide range of users in different poses and lighting conditions. The facial recognition accuracy was 96.3%, liveness detection precision was 94.5%, and average face recognition time was 1.28 seconds. The system can run on normal desktop/laptop computers without a GPU and can be suitable for small and medium-scale organizations. The facial recognition-based attendance system is a cost- effective and efficient solution that can replace existing manual and RFID-based solutions. The system can record secure and touch-free automatic attendance data in real-time. The system can be further extended to use deep learning techniques and can be integrated with other tools and technologies.

Traditional attendance systems—manual registers, RFID, QR codes, or contact-based biometrics—are either time-consuming, error-prone, or raise hygiene concerns. Manual and semi-automated methods are vulnerable to proxy attendance, lost or shared tokens, and lack real-time analytics. Contactless solutions, especially facial recognition, offer convenience and hygiene but are susceptible to spoofing without liveness detection. The proposed system is a Facial Recognition Attendance System with Integrated Liveness Detection and Real-Time Reporting , implemented using Python, OpenCV, Flask, and SQLite. It uses webcams for face capture, Haar Cascade for detection, LBPH for recognition, and motion/eye-blink analysis for liveness verification. Attendance records are stored in SQLite and displayed via a Flask web interface, enabling real-time monitoring, reporting, and export. The system is lightweight, contactless, easy to deploy on standard hardware, and designed to scale for classrooms or office environments.

Traditional attendance systems—manual registers, RFID, QR codes, or contact-based biometrics—are either time-consuming, error-prone, or raise hygiene concerns. Manual and semi-automated methods are vulnerable to proxy attendance, lost or shared tokens, and lack real-time analytics. Contactless solutions, especially facial recognition, offer convenience and hygiene but are susceptible to spoofing without liveness detection.

Figure 3: GitHub - shrutij02/Face-Recognisation-Attendance-System: It is a Face ... The proposed system is a Facial Recognition Attendance System with Integrated Liveness Detection and Real-Time Reporting , implemented using Python, OpenCV, Flask, and SQLite. It uses webcams for face capture, Haar Cascade for detection, LBPH for recognition, and motion/eye-blink analysis for liveness verification. Attendance records are stored in SQLite and displayed via a Flask web interface, enabling real-time monitoring, reporting, and export. The system is lightweight, contactless, easy to deploy on standard hardware, and designed to scale for classrooms or office environments.

Facial Recognition Attendance System with Liveness De- tection and Real-Time Reporting provides a safe and efficient means of attendance tracking. It uses a facial recognition system with liveness detection, ensuring minimal errors and proxy attendance, and provides a seamless experience for users. Results of experiments on the system indicate high recog- nition accuracy, effective spoof detection, and fast response times, making it a promising system for attendance tracking. Possible enhancements could include deep learning algo- rithms like FaceNet and ArcFace, liveness detection with texture and depth information, cloud deployment for a multi- site system, and a mobile app for remote attendance tracking and alerts.

[1] P. Viola and M. Jones, “Rapid object detection using a boosted cascade of simple features,” Proceedings of the IEEE Ahonen, A. Hadid, and M. Pietika¨inen, “Face description with local binary patterns: Application to face recognition,” IEEE 182, no. 40, pp. 25–30, 2018. [5] J. Galbably and S. Marcel, “Face anti-spoofing: A holistic approach to presentation attack pp. 66–70, 2019. [7] A. Singh, P. Kumar, and S. Chauhan, “Automated attendance system using Python and OpenCV,” “Cloud-integrated biometric attendance sys- tem using facial recognition,” Journal of Emerging Technologies and Innovative 2021. [10] S. Zafeiriou, C. Zhang, and Z. Zhang, “A survey on face detection in the wild: Past, present and future,” Computer MIT Press, 2016. [12] D. Yi, Z. Lei, and S. Z. Li, “Deep metric learning for face verification,” IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 41–48, 2014. [13] F. Schroff, D. Kalenichenko, and J. Philbin, “FaceNet: A unified embedding for face recognition and clustering,” Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 815–823, 2015. [14] S. Mishra and A. Sharma, “Performance evaluation of liveness 68, no. 9, pp. 45–52, 2020. [15] K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” arXiv preprint arXiv:1409.1556, 2015. [16] S. Mehta and R. Gupta, “Smart attendance system using machine 101–107, 2023.

4. Practical Deployment, Analysis & Case Studies Copyright © 2026 Ms. Neelam, N. Sowjanya, K. Sharvani, V. Varshini. This is an open access article distributed under the provided the original work is properly cited. Smart Attendance System with Face Recognition, Liveness Detection & Secure Verification “Was the real student physically present, and was the scan genuine for this class session?” SmartAttend fixes this by combining identity verification, anti-spoofing, session-aware attendance, and structured logging.

This is the current applicable SmartAttend architecture: Hugging Face Space hosting, Streamlit application runtime, local model training, Neon PostgreSQL, S3-backed face assets, and the live CNN-based attendance verification pipeline. This diagram shows the cloud architecture version of SmartAttend if the platform were implemented fully on AWS, with Route 53, ALB, EC2, RDS, S3, Lambda, SageMaker, monitoring, and security services.

Confusion matrix generated from the same evaluation run. Each cell shows the count and row-normalized percentage. 5. Performance Evaluation & Extended Technical Observations Use requirements-local.txt whenever you want TensorFlow training, MTCNN, or the full Docker/runtime environment. These defaults are intended for local development only. Override them in .env or hosted secrets for any real deployment.

The Postgres smoke test in tests/test_postgres_backend.py runs when SMARTATTEND_DATABASE_URL is set. This repository is intended to store source code and project structure. Personal face images, trained local models, SQLite databases, and generated artifacts are excluded from version control by default. If SMARTATTEND_DATABASE_URL is set, the app uses Postgres instead of the local SQLite file.

Enrolled face assets are uploaded to S3 and can be loaded back from S3 for runtime fallback recognition. This project can grow from a classroom demo into a more production-oriented biometric attendance platform. Harvested Online Documentation & Reference Sources • https://en.wikipedia.org/wiki/Facial%20recognition%20system • https://github.com/Mobel28/Smart_Face_Attendance • https://www.ijraset.com/research-paper/facial-recognition-attendance-system-with-integrated-liveness-detection • https://github.com/mitraboga/SmartAttend/