Real-Time Smart Attendance System using Face Recognition Techniques

Application of Face Recognition Method Under Deep Learning Algorithm in Embedded Systems

The main precondition for applications such as face recognition and face de-identification for privacy protection is efficient face detection in real scenes. In this paper, we propose a hybrid cascade model for face detection in the wild. The cascaded two-stage model is based on the fast normalized pixel difference (NPD) detector at the first stage, and a deep convolutional neural network (CNN) at the second stage. The outputs of the NPD detector are characterized by a very small number of false negative (FN) and a much higher number of false positive face (FP) detections. The FP detections are typically an order of magnitude higher than the FN ones. This very high number of FPs has a negative impact on recognition and/or de-identification processing time and on the naturalness of the de-identified images. To reduce the large number of FP face detections, a CNN is used at the second stage. The CNN is applied only on vague face region candidates obtained by the NPD detector that have an NPD score in the interval between two experimentally determined thresholds. The experimental results on the Annotated Faces in the Wild (AFW) test set and the Face Detection Dataset and Benchmark (FDDB) show that the hybrid cascade model significantly reduces the number of FP detections while the number of FN detections are only slightly increased.

As we all know fingerprint recognition is one of the secure and accurate Biometric Technologies. If think about it in deep even with the Biometric system the virus can be spread during these situations. To overcome this, we need to come up with a secure and contactless way of authentication. So, let’s update to some contactless remedies like Iris authentication which are unique for every individual and they don’t need to have any physical contact. So, we can use this Iris detection for a secure and contactless authentication system. The main aim of this research is to provide contactless remedies for students in Educational institutes like Smart Locking system, Attendance management system, and Library Transaction by using their Iris authentication and Face Recognition. Coming to the outline of the attendance management system, we will first collect the data from the Kaggle repository. Next, we split the data into training and testing, then we will train the data using transfer learning techniques and test the model by using test data. Finally, we integrated the trained model with the flask. If the Iris matches then the attendance of a particular person will be posted. If not matched then we train the model by adding new person’s data. For the construction of modern electronic security systems, real-time face recognition is crucial. Face detection, feature extraction, and face recognition are the three procedures involved. After recognizing the face, it will check whether the person’s face matches the collected database. If it matches it will show the person’s name, the number of books he took, and what those books are for Library transactions and in the same way the locker will be open if the person’s data is matched. The proposed methods are secure and unique contactless ways of authentication for every individual. So, we can use these detection and authentication systems for secure and contactless applications. It can be successfully used for students in Educational institutes like Smart Locking system, Attendance management system, and Library Transaction by using their Iris authentication and Face Recognition. The Covid-19 infection in society will undoubtedly decline if the proposed argument is implemented.

In Institutions/schools attendance maintaining is one of the major work for the faculty's to check the strength of a class. The faculties are provided with paper based attendance. They separately have it for various periods of subjects known log book. They mark the attendance every time when they go to class for their periods. To avoid manual paper based attendance system nowadays smart attendance monitoring system like biometric facial recognition system is being suggested. It is enormously used in much application such as monitoring the class room using CCTV, Computer -human interaction, Accurate Attendance maintaining and in security issues. This system rectifies the problems in marking the student's entry as absent even they are inside the classroom. In the implementation process, detecting the face, identifying and marking the attendance automatically whether the student is present or not is done. Principle Component Analysis (PCA), Eigen face value detection, Convolutional Neural Network (CNN) are the methods being used in this paper to create an automatic attendance management system. This model is successfully done in comparison with database of student's face to control the movement of people with a predefined protocol.

Face recognition technology has many implementation roles in the attendance management system. Attendance systems need proper solutions to detect a face in real-time situations using a particular purpose device. Face recognition systems can differentiate human faces based on face features trained in the deep learning model. Although significant advances in face recognition can increase the variety of face conditions in detection, some challenges still exist in face recognition that makes the existing model need to be taken apart and reparametrized. Challenge comes from lighting condition, blurred condition, also face tilt position. This research design a superficial layer of convolutional neural network using a built-in Tensorflow sequential model library. Generally, a transfer learning mechanism is used in object detection, especially in face recognition. This research doesn't use transfer learning because the accuracy of an existing model like the InceptionV1 model gives good accuracy in cross-validation training but gives a significant error in testing the trained face. The attendance management system was built in Flask Web Framework because developed in a Python language environment. The accuracy of the custom model has an average of 88.23%, which is tested with 16 different students, with each student having 48 pictures.

In this paper, we present an effective facial image verification based automated attendance management system (FIV-AMS). The proposed system can be divided into three main components: face detection, image pre-processing, and face recognition. The core step of our attendance management system is the Gist feature extraction based face recognition, which can achieve three functions. Experimental results demonstrate the validity and feasibility of the proposed system by using the statical model and the dynamic model.

Face Recognition is an efficient technique and one of the most liked biometric software application for the identification and verification of specific individual in a digital image by analysing and comparing patterns. This paper presents a survey on well-known techniques of face recognition. The primary goal of this review is to observe the performance of different face recognition algorithms such as SVM (Support Vector Machine), CNN (Convolutional Neural Network), Eigenface based algorithm, Gabor Wavelet, PCA (Principle Component Analysis) and HMM (Hidden Markov Model). It presents comparative analysis about the efficiency of each algorithm. This paper also figure out about various face recognition applications used in real world and face recognition challenges like Illumination Variation, Pose Variation, Occlusion, Expressions Variation, Low Resolution and Ageing in brief. Another interesting component covered in this paper is review of datasets available for face recognition. So, must needed survey of many recently introduced face recognition aspects and algorithms are presented.

This research project aims to enhance the authentication process of identification cards within college campuses using advanced image recognition technologies, specifically Convolutional Neural Networks (CNN) and OpenCV methodologies.By integrating sophisticated object detection techniques such as Viola Jones, LBPH (Local Binary Pattern Histogram), and YOLO (You Only Look Once), along with advanced image segmentation methods, the system endeavors to accurately identify and verify individuals who comply with ID card protocols.Through extensive training on diverse datasets containing images of students both with and without ID cards, the system dynamically learns to recognize and differentiate between compliant and non-compliant scenarios.The adoption of this technology promises significant advantages, primarily in automating attendance tracking and reinforcing security measures within educational environments.By automating the attendance recording process and strengthening security protocols, the system ensures that only authorized individuals wearing valid identification cards are granted access to campus facilities.The system's seamless architecture encompasses various phases, including enrolling individual details, capturing and analyzing images, validating ID card adherence through segmentation-assisted recognition, logging attendance upon validation, and documenting violations for unauthorized entry attempts.Overall, this comprehensive framework enhances operational efficiency while creating a secure and conducive learning environment within educational institutions.

In recent years, pattern recognition has garnered widespread attention, especially in the domain of face recognition. Traditional face recognition methods have certain limitations in unconstrained environments due to factors such as lighting, facial expressions, and poses. Deep learning can be used to address these challenges. This paper proposes a comprehensive approach to face occlusion recognition based on a two-stage Convolutional Neural Network (CNN). Face verification aims at verifying whether two face images belong to the same individual, and it is a more fundamental task compared to face recognition. The process of face recognition essentially involves multiple instances of face verification, sequentially validating different individuals to ultimately determine the corresponding individual for each face. The primary steps in this research include facial detection, image preprocessing, facial landmark localization, facial landmark extraction, feature matching recognition, and 2D image-assisted 3D face reconstruction. A novel two-stage CNN was designed for facial detection and alignment. The first stage of the network is dedicated to the search for facial windows and regressing vector boundaries. The second stage utilizes 2D images to assist in 3D face reconstruction and perform secondary recognition for cases not identified in the first stage. This method demonstrated excellent performance in handling facial occlusions, achieving high accuracy on datasets such as AFW and FDDB. On the test dataset, face recognition accuracy reached 97.3%, surpassing the original network accuracy of 89.1%. This method outperforms traditional algorithms and general CNN approaches. This study achieved efficient face validation and further handling of unrecognized situations, contributing to the enhancement of face recognition system performance.

A facial recognition system is a piece of technology that can match a human face from a database of images. It is often used for robust authentication. An Attendance Management System is a tool used by businesses to track employee time and participation information. Software as a service (SaaS) allows users to access the software via the Internet as a service. Advanced and automated attendance management technologies are being used to address this issue. The problem of proxies and students being counted as present even if they are not is easily resolved with this architecture. This technology records attendance via a live video broadcast. This system's objective is to develop a facial recognition-based class attendance system because the manual technique of taking attendance currently in use is cumbersome and difficult to maintain. The creation of the database, face detection, face recognition, and attendance updating are the four stages of this system. Faces can be recognized in the live-streamed video from the classroom. The attendance will be recorded in a spreadsheet and saved to Google Drive at the end of the session.

LSCO: Light spectrum chimp optimization based spinalnet for live face detection and recognition

Gaining knowledge from health data may contribute to novel approaches or improved patient care plans. To intelligently acquire knowledge from the stroke data, machine learning (ML) technique is utilised and healthcare systems are used. Globally, security has become a major concern, and biometric technologies such as face detection and recognition technologies have been developed to solve security issues and security threats in the world. It has become possible because of developments in technology in the fields of automatic face analysis, machine learning, and pattern recognition. This chapter proposes a prototype to classify brain stroke and face recognition using ML techniques in the medical image. Face recognition and classification of stroke through ML technique like Decision Tree (DT), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Deep Learning with Convolution Neural Network (CNN) based on texture features and statistical features. A CNN model is experimentally used along with a collection of hyper-parameters for deep face recognition and stroke classification. Promising experimental results, with a total accuracy of 98.86% and 98.5%, are obtained, which demonstrates the effectiveness of deep face identification and stroke classification, respectively, in biometric systems.

Building an intelligent system similar to the human perception system in face recognition is still an active area of research, despite the advancements in technologies and face recognition research carried out when age changes. Deep learning algorithms have outperformed conventional methods in with regard to accuracy and effectiveness of recognition a variety of difficulties, including position, expression, lighting, and aging. But aging is one of the problems that affects the face the most, as it plays a significant role which directly affects facial features, so we notice some people who are very difficult to distinguish and may not be known at all because of the strong change in their features. As a result, we researched deep learning techniques generally and the convolutional neural network (CNN) specifically. This strategy is employed by a number of significant stages: The first side, includes preparing the dataset related to the subject of the study, Isolate the data between training, validation and testing. As for the second part of the work, data preprocessing, such a data augmentation, Normalization, Face detection, and resizing. After then, begin a features extraction operation by the convolution neural network (CNN) that is suggested. After all that, the classification stage begins, which was done by using the (SoftMax) function, because we have approximately (570) classes. In the testing phase, we perform the task of checking the two images entered whether they belong to the same person or not. In this paper, adopted the (Age) and (FG-Net) datasets, Finally, the verification accuracy rate for the proposed system reached 98.7 % on the (Age) dataset, and reached 99.4 % on the (FG-Net) dataset.

Proctor Nova is a computer vision based, AIpowered automated attendance management system that aims to deliver precise, real time, and touchless student presence tracking in academic settings. Conventional methods of attendance tracking, including roll calls and RFID, may take a considerable amount of time and may alsoinvolve integrity problems. In this paper, we propose a computer vision based intelligent attendance management system called Proctor Nova, which uses deep learningtechniques to accurately detect and record student attendance.The full stack tech development of the Proctor Nova system allows for seamless and simple communication between thefront end and back end, hence facilitating real-time attendance monitoring, storage, and retrieval. Furthermore,the optimized recognition process of the Proctor Novasystem is capable of detecting and recognizing multiple students simultaneously, even under varying illumination and position conditions.

In recent years, face detection and counting have undergone a remarkable transfor-mation due to the emergence of deep learning techniques, particularly Convolutional Neural Networks (CNNs). These methods have surpassed traditional computer vision approaches, benefiting from vast datasets and robust computational resources. CNN’s, the cornerstone of contemporary face recognition systems, excel in accurately identifying faces across diverse conditions and environments. The ascendancy of CNNs in face detection stems from their capacity to autonomously learn hierarchical features from raw pixel data, obviating the need for manual feature engineering. Consequently, they yield resilient systems capable of accommodating real-world variations like lighting, pose, expression, and occlusion. Their scalability enables the efficient processing of extensive image databases, rendering them invaluable for applications requiring face counting amidst crowded scenes. Nonetheless, challenges persist, particularly in deploying these systems on resources-constrained devices. The computational complexity and storage demand of deep CNNs necessitate ongoing exploration of lightweight network architectures that balances accuracy with reduced computational footprint. The historical Violajones algorithm, while foundational, has been eclipsed by the superior performance of CNNs. Deep learning’s prowess lies in its adaptability to various tasks and its capacity to continuously refine itself with more data. By learning features directly from data, CNNs excel in capturing intricate patterns crucial for precise face detection and counting. Deep learning, especially through CNNs, has revolutionized face detection and counting by delivering unparal-leled accuracy and robustness. However, ongoing efforts are crucial to address challenges in the efficiency and accessibility of these systems for broader deployment across various applications and devices.