Face Detection and Recognition Based E-Learning for Students Authentication: Study Literature Review

Abstract

The Authentication process is highly dependent on Face Detection and Face Recognition during learning activities. In addition, in the E-Learning learning system we must also provide accurate and accurate information. The research method used is literature study and analysis. Literature study was carried out on the face of face detection and recognition in real-Time conditions carried out by various previous studies. Furthermore, analysis was carried out in a literature study studio to find suitable methods for the E-Learning environment. From the results of existing literature studies we recommend face detection using Face Countour and the Adaboost Algorithm added to CNN (Convolutional Neural Network)to normalize the facial contour function and normalize lightning in the surrounding environment where a face detection is located. The process is carried out, we use the 3WPCA-MD(Three-Level Wavelet

A Comprehensive Survey of Context-Aware Continuous Implicit Authentication in Online Learning Environments

“…Since there are various devices available to connect to online learning platforms, however, such as smartphones, tablets, etc., a user may utilise multiple devices to perform online learning activities including exams. In these cases, the user's face may not be visible using mobile devices such as a mobile phone as the user will move their position frequently [11] and video processing may impact energy consumption [62]. Therefore, an exploration of the dynamic use of authenticators is needed to cover other types of user interaction in online learning environments.…”

Systematic Literature Review on the Accuracy of Face Recognition Algorithms

“…Ref. [13] (item 4 of Table 2) carried out studies and development of experiments in order to meet the needs of COVID-19 in the period between 2020 and 2021: control student access to virtual classrooms, typical of Distance Learning systems. The authors used detection and recognition techniques to control and authenticate the presence of these students.…”

“…The second research question developed for this SLR addresses the accuracy rates identified in algorithms for real-time facial recognition, which is highlighted below, followed by its considerations. [10] Automatic attendance monitoring system using facial recognition through feature-based methods (PCA, LDA) HR LR LR [11] Automated attendance system using image processing HR LR LR [12] Computer vision on identifying persons under real time surveillance using IOT HR HR HR [13] Face detection and recognition-based e-learning for students' authentication: study literature review HR HR LR [14] Face recognition-based attendance system using machine learning algorithms HR HR LR [15] Human identification recognition in surveillance videos HR HR LR [16] Improving the capability of real-time face masked recognition using cosine distance HR HR LR [17] LBPH based improved face recognition at low resolution HR LR LR [18] Real-time face recognition: A survey HR HR LR [19] Recognizing Very Small Face Images Using Convolution Neural Networks HR HR LR [20] The Real Time Face Recognition HR LR MR [21] Fractional Krill-Lion algorithm-based actor critic neural network for facer recognition in real time surveillance videos HR HR LR [22] Technology: Person Identification MR MR HR…”

“…It is important to highlight that the 98% accuracy is also presented by [10], [13] and [14], who built their solutions using HAAR Cascade for detection and ANN for carrying out the complementary steps. It should be noted that the 3 articles that present an accuracy of 98% are from different authors that consider different scenarios and datasets.…”

“…It should be noted that the 3 articles that present an accuracy of 98% are from different authors that consider different scenarios and datasets. [10] uses the Olivetti dataset, [13] does not present the dataset used, and [14] built his own dataset with 11 people in different directions of gaze, containing a total of 234 images of 244x244. Considering the accuracy according to a subset of selected articles, the average among the values was 93%, as shown in Figure 3.…”