Face Detection Research Articles

Attendance System Using Face Recognition and Detection

This study proposes the implementation of an attendance system using face recognition and detection technology. The system aims to provide a convenient and accurate method for recording attendance in various settings, such as classrooms or workplaces. By leveraging facial recognition algorithms, the system can identify individuals and automatically mark their attendance, reducing the need for manual record-keeping and minimizing errors. The integration of detection technology ensures reliability by distinguishing between live faces and photographs, enhancing the security and integrity of the attendance tracking process." Keywords—Face recognition, Attendance, Detection-based, Automating attendance, Real-time monitoring, Convolutional Neural Network (CNN)

Detection of Drowsy Drivers in Video Sequences via LSTM with CNN Features

Fatigued driving is one of the main causes of traffic accidents. This paper developed a method for sleep drive detection that makes use of the convolutional neural network (CNN), recurrent neural network (RNN), short-term neural network (LSTM), cascade, and cam switching algorithms. Using CNN, the algorithm initially extracts the driver's face traits. The RNN that predicts the driver's degree of tiredness is then fed these features. The technology tracks the driver's eyes and eyelids using algorithms called Cascades and Cam shifts. The accuracy of the sleepiness prediction is increased further with the usage of this data. Using datasets of video recordings of attentive and somnolent drivers, the system was assessed. The outcomes demonstrated how well the algorithm could identify sleepy drivers. This system may be able to stop sleepy driving-related accidents. Ten thousand videos of awake and sleepy drivers were used to train the algorithm. Drivers can be observed in real time by the system. If the system detects that the driver is sleepy, it has the ability to sound an alarm. The technology can be used to stop driving when sleepy from causing accidents. Keywords: Convolution neural network, Recurrent neural networks, long short-term memory, eye tracking, face detection, drowsy driver detection, deep learning, computer vision, machine learning, and deep learning.

DRIVER DROWSINESS DETECTION SYSTEM

The proposed system utilizes facial landmark detection and eye aspect ratio calculation to detect drowsiness in real-time from a webcam feed. It employs the dlib library for face detection and facial landmark prediction. The eye aspect ratio (EAR) is computed from the distances between specific points on the eyes. When the EAR falls below a predefined threshold for a certain number of consecutive frames, it triggers an alert indicating potential drowsiness. The alert includes visual cues on the video feed, an auditory alert using the playsound library, and even sends an instant WhatsApp message using pywhatkit to notify a designated contact about the drowsiness. This system serves as a useful tool for monitoring driver fatigue or alertness in various contexts, promoting safety and awareness. Its capacity to swiftly identify and alert users to the onset of drowsiness represents a significant leap forward in safety technology. By mitigating the risk of accidents stemming from fatigue-induced impairments, this project underscores the pivotal role of computer vision in real-time human behavior monitoring, offering a versatile and invaluable tool for fostering safety and awareness across various domains. Keywords: Drowsiness Detection; Python; Whatsapp messaging; Webcam feed; Computer Vision; Alert System; Real-time monitoring; Eye-Aspect Ratio; Frame Processing; Facial Recognition.

Enhancing Fashion Recommendations with Facial Recognition: A Gender and Age Prediction Perspective

This research paper presents a real-time system for age and gender estimation integrated into a fashion recommendation context. Leveraging deep learning models for facial detection and classification, alongside a Random Forest-based recommender system for fashion items, the system provides personalized recommendations based on user age, gender, and preferences. The methodology involves detecting faces in video streams, extracting facial regions, and preprocessing them for age and gender estimation using pre-trained CNN models. Fashion recommendations are then generated by assigning weighted scores to items based on various attributes and training a Random Forest regressor. Implementation details, including the use of Python, OpenCV, and machine learning libraries, are discussed. Evaluation metrics for age and gender detection models, as well as recommendation system performance, are outlined. The paper concludes with future directions and challenges, emphasizing enhancements in age and gender estimation accuracy, integration with e-commerce platforms, and the importance of data privacy and computational resources. Keywords — Age and gender estimation, Facial detection, Deep learning, Fashion recommendation, Random Forest.

Intelligent Bus Tracking System with Attendance based on Facial Recognition

The Intelligent Bus Tracking System is a cutting-edge solution that integrates machine learning tools and face detection technology to revolutionize transportation services within academic institutions. Leveraging the power of artificial intelligence, this system enhances the accuracy, efficiency, and security of bus tracking while introducing innovative features such as facial recognition for identification to Student Attendance.(Saad et al., 2018) The bus tracking system is a comprehensive solution designed to enhance the efficiency and safety of transportation services within academic institutions. This system leverages modern technologies, including GPS and mobile communication to provide real time tracking and monitoring of buses operating within the academic campus. The primary goal is to optimize the transportation experience for students, faculties and staff while also improving overall operational management.(Sharif et al., 2018) Keywords: GPS, Tracking system, Attendance system Face Recognition, Machine Learning,

A survey on disguise face recognition

ABSTRACT Human face is one of the physiological traits used in biometric system and gained a significant attention in recent years due to the advancement in technology. It has been remarkable progress in face recognition system since 1960 owing to advances in 3D-face modeling and analysis, face detection, and tracking. The reason for this progress is to provide security in surveillance systems, criminal identification, border control, security access, and many more. Despite this, proposed techniques are not robust enough for many challenging issues like variations in pose, illumination, expression, and disguise. This paper provides a survey on some of the well-known deep learning methodologies focused on these issues of face recognition. Furthermore, the performance of these methodologies is also studied in terms of accuracy, computational cost, and robustness. In addition to this, it also summarizes and outlines the importance of disguise face datasets. Finally, open challenges involved in deep learning framework, disguise face dataset, and the impact of disguise co-variate on the current face recognition system are discussed for future research.

Digital Voting Application using Blockchain Technology

Building a secure electronic voting system that offers the fairness and privacy of current voting schemes, while providing the transparency and flexibility offered by electronic systems has been a challenge for a long time. The development of a robust and secure evoting system is crucial to ensure the integrity and authenticity of electoral processes. In this context, the integration of blockchain technology with face detection and Aadhar card verification presents an innovative solution. This system combines the power of blockchain's immutability and transparency with biometric authentication through face recognition and Aadhar card validation. By leveraging blockchain, the system can maintain a tamper-proof ledger of votes, ensuring their verifiability and integrity. The incorporation of face detection and Aadhar card verification enhances security by ensuring that only eligible voters can participate, thereby reducing the risk of fraudulent voting. This abstract introduces a novel e-voting system that promises to enhance the trust and reliability of the electoral process through blockchain technology, face detection, and Aadhar card authentication. Key Words: Blockchain, Electronic Voting System and Evoting, face recognisition.

A behavioral advantage for the face pareidolia illusion in peripheral vision

Investigation of visual illusions helps us understand how we process visual information. For example, face pareidolia, the misperception of illusory faces in objects, could be used to understand how we process real faces. However, it remains unclear whether this illusion emerges from errors in face detection or from slower, cognitive processes. Here, our logic is straightforward; if examples of face pareidolia activate the mechanisms that rapidly detect faces in visual environments, then participants will look at objects more quickly when the objects also contain illusory faces. To test this hypothesis, we sampled continuous eye movements during a fast saccadic choice task—participants were required to select either faces or food items. During this task, pairs of stimuli were positioned close to the initial fixation point or further away, in the periphery. As expected, the participants were faster to look at face targets than food targets. Importantly, we also discovered an advantage for food items with illusory faces but, this advantage was limited to the peripheral condition. These findings are among the first to demonstrate that the face pareidolia illusion persists in the periphery and, thus, it is likely to be a consequence of erroneous face detection.

Learning of the same task subserved by substantially different mechanisms between patients with body dysmorphic disorder and healthy individuals.

It has remained unclear whether individuals with psychiatric disorders involving altered visual processing employ similar neuronal mechanisms during perceptual learning of a visual task. We investigated this question by training patients with body dysmorphic disorder, a psychiatric disorder characterized by distressing or impairing preoccupation with nonexistent or slight defects in one's physical appearance, and healthy controls on a visual detection task for human faces with low spatial frequency components. Brain activation during task performance was measured with functional magnetic resonance imaging before the beginning and after the end of behavioral training. Both groups of participants improved performance on the trained task to a similar extent. However, neuronal changes in the fusiform face area were substantially different between groups such that activation for low spatial frequency faces in the right fusiform face area increased after training in body dysmorphic disorder patients but decreased in controls. Moreover, functional connectivity between left and right fusiform face area decreased after training in patients but increased in controls. Our results indicate that neuronal mechanisms involved in perceptual learning of a face detection task differ fundamentally between body dysmorphic disorder patients and controls. Such different neuronal mechanisms in body dysmorphic disorder patients might reflect the brain's adaptations to altered functions imposed by the psychiatric disorder.

Exploration of factors affecting webcam-based automated gaze coding

Online experiments have been transforming the field of behavioral research, enabling researchers to increase sample sizes, access diverse populations, lower the costs of data collection, and promote reproducibility. The field of developmental psychology increasingly exploits such online testing approaches. Since infants cannot give explicit behavioral responses, one key outcome measure is infants’ gaze behavior. In the absence of automated eyetrackers in participants’ homes, automatic gaze classification from webcam data would make it possible to avoid painstaking manual coding. However, the lack of a controlled experimental environment may lead to various noise factors impeding automatic face detection or gaze classification. We created an adult webcam dataset that systematically reproduced noise factors from infant webcam studies which might affect automated gaze coding accuracy. We varied participants’ left-right offset, distance to the camera, facial rotation, and the direction of the lighting source. Running two state-of-the-art classification algorithms (iCatcher+ and OWLET) revealed that facial detection performance was particularly affected by the lighting source, while gaze coding accuracy was consistently affected by the distance to the camera and lighting source. Morphing participants’ faces to be unidentifiable did not generally affect the results, suggesting facial anonymization could be used when making online video data publicly available, for purposes of further study and transparency. Our findings will guide improving study design for infant and adult participants during online experiments. Moreover, training algorithms using our dataset will allow researchers to improve robustness and allow developmental psychologists to leverage online testing more efficiently.

Improved DSFD Algorithm for Balancing Speed and Accuracy

Aiming at the mismatch between speed and accuracy of DSFD face detection algorithm, a lightweight network method based on improved DSFD is proposed. First, the backbone of the algorithm is replaced with EfficientNet B1, which greatly reduces parameters and computation. Then the feature pyramid network in feature enhance module is changed to BiFPN to further enhance the feature fusion. Finally, to improve the efficiency, dilated convolution layers in feature enhancement module are removed, and the convolution layers of BiFPN is replaced by ACBlock. The improved algorithm was evaluated on WIDER FACE and the effectiveness of the proposed methods are evaluated through ablation experiments. The detection speed of the improved algorithm is increased by twice. Compared with two popular algorithms, the improved algorithm achieves higher accuracy.

Face Recognition Based Attendance System

Abstract: In the field of image analysis and computer vision, one of the most arduous tasks presently considered is Face recognition. The biometric system which basically works on the principle of face recognition is used for the identification or verification of a person from a digitalized image preferably used in surveillance, security and attendance purpose. Face Recognition is becoming more popular than other biometric verification methods due to its simplicity, non-invasiveness, and lack of touch. The system’s major goal is to identify and recognize faces in a real-time environment, match them with data in the database, and record their attendance. This is intended to make the time-consuming manual attendance process more efficient. The main building block on which all automated systems concerned with human faces are designed is face detection. In many person-system user interfaces, precise face identification is important; the real implication is the precise approach to face identification.

Rancang Bangun Sistem Keamanan Helm dan Berkendara Berbasis Mikrokontroler

As a two-wheeled vehicle user, a problem that often occurs in the community is the loss of helmets when placed in the parking lot. This can happen due to lack of attention from security personnel at the parking location. Riders who do not use helmets can endanger themselves in the event of an accident. In addition to the use of helmets, speed in driving is one factor that needs to be considered because it has the potential to endanger yourself or others. This study aims to anticipate the occurrence of helmet theft and also provide safety in driving using survey research methods to determine the percentage of ease of use by users. Where the system designed consists of 4 functions, namely, detection of helmet location using the MQTT protocol where if the helmet position with the vehicle has a large distance of 40m then the helmet is detected to have been stolen so that it will issue a warning in the form of sound. The second system is vehicle speed detection using anemometer sensors, if the vehicle is detected to have a large speed of 50km / h then the helmet will issue a sound warning so that the driver can reduce driving speed. The third system is face detection around the helmet using ESP32-Cam, where if the helmet detects an unknown face through the face recognition feature with a distance of 15cm to 60cm from the helmet, the ESP32-Cam will take pictures. The last system is taking pictures periodically to find out the situation around the helmet. Based on research using a questionnaire with 30 samplers, a percentage of 74.95% was obtained, which means that the helmet is easy to use.

Artificial Intelligence (AI): Evolution, Methodologies, and Applications

Abstract: Artificial intelligence, also known as AI, is a technology that enables computers and machines to emulate human intelligence and problem-solving abilities. Computers can perform a wide range of advanced functions thanks to the use of artificial intelligence (AI) technologies. These functions include the ability of machines to see, comprehend, and translate spoken and written language, analyzing data, making recommendations, and more. Artificial intelligence is considered a field of computer science that encompasses other areas like machine learning and deep learning, data analytics, linguistics, software engineering, and so on. These disciplines often involve the development of AI algorithms that are based on the decision-making processes of the human brain, that has the ability to learn and memorize from existing data and allows more precise classifications or predictions over a period of time. AI is the foundation for innovation in modern computing, discovering the value for both individuals and businesses. For illustration, AI is used to extricate content and information from pictures and documents, turns unstructured content into business-ready structured data, and unlocks valuable insights. AI has the ability to perform tasks that would otherwise require human intelligence or intervention, when combined with other technologies such as sensors, and robotics. It is used in many areas of life, including education, finance, healthcare, and manufacturing. Here are some examples of AI in different areas: Facial detection and recognition, Text editors, Digital assistants, Self-driving cars, and many more.

Automated Facial Authentication Attendance System

Abstract: This research paper introduces a novel approach to automate attendance tracking in educational institutions through the implementation of a Face Recognition-based attendance system using Python. Traditionally, attendance management has relied on manual processes, prone to errors and time-consuming activities such as roll-call or name calling. The primary objective of this project is to revolutionize attendance management by developing an automated system that utilizes facial recognition technology. By leveraging modern advancements in computer vision, this system aims to streamline the attendancetaking process, enhancing efficiency and accuracy while reducing administrative burdens.Implemented within the classroom environment, the system captures student information including name, roll number,admission number, class, department, and photographs for training purposes. Utilizing OpenCV for image extraction and processing.The workflow involves initial face detection using a Haarcascade classifier, followed by facial recognition utilizing the LBPH (Local Binary Pattern Histogram) Algorithm. Upon recognition, the system cross-references the captured data with an established dataset to automatically mark attendance. Furthermore, to facilitate easy record-keeping, an Excel sheet is dynamically generated and updated at regular intervals with attendance information, ensuring seamless integration with existing administrative processes. This research provides a practical solution for attendance management and also helps in broader discourse on leveraging emerging technologies for optimizing educational and organizational workflows

Real Time Emotion Based Music Player

Abstract: In this paper, we present the development and implementation of an Emotion-based Music Player System utilizing facial emotion data, Convolutional Neural Networks (CNN), Flask, OpenCV for face detection, and Spotify API for music playlist integration. The system aims to provide users with personalized music recommendations based on their current emotional state, detected through real-time analysis of facial expressions. The proposed system consists of several key components, including data collection, preprocessing, CNN algorithm implementation for emotion classification, integration with Flask for web application development, and real-time emotion detection using OpenCV. The trained CNN model is capable of accurately classifying emotions such as anger, disgust, fear, happiness, neutrality, sadness, and surprise. Results from the implementation demonstrate the system's effectiveness in accurately detecting emotions from facial expressions and providing corresponding music recommendations. The CNN model achieved a final accuracy of 62.44% after 10 epochs of training. Realtime emotion detection using OpenCV successfully identifies facial expressions, allowing for dynamic adjustments to the music playlist. Overall, the Emotion-based Music Player System presents a novel approach to enhancing user experience by leveraging facial emotion data and advanced machine learning techniques to deliver personalized music recommendations tailored to individual emotional states.

A Benchmark of Facial Recognition Pipelines and Co-Usability Performances of Modules

Researchers from leading technology companies, prestigious universities worldwide, and the open-source community have made substantial strides in the field of facial recognition studies in recent years. Experiments indicate that facial recognition approaches have not only achieved but surpassed human-level accuracy. A contemporary facial recognition process comprises four key stages: detection, alignment, representation, and verification. Presently, the focus of facial recognition research predominantly centers on the representation stage within the pipelines. This study conducted experiments exploring alternative combinations of nine state-of-the-art facial recognition models, six cutting-edge face detectors, three distance metrics, and two alignment modes. The co-usability performances of implementing and adapting these modules were assessed to precisely gauge the impact of each module on the pipeline. Theoretical and practical findings from the study aim to provide optimal configuration sets for facial recognition pipelines.

Advancing face detection efficiency: Utilizing classification networks for lowering false positive incidences

The advancement of convolutional neural networks (CNNs) has markedly progressed in the field of face detection, significantly enhancing accuracy and recall metrics. Precision and recall remain pivotal for evaluating CNN-based detection models; however, there is a prevalent inclination to focus on improving true positive rates at the expense of addressing false positives. A critical issue contributing to this discrepancy is the lack of pseudo-face images within training and evaluation datasets. This deficiency impairs the regression capabilities of detection models, leading to numerous erroneous detections and inadequate localization. To address this gap, we introduce the WIDERFACE dataset, enriched with a considerable number of pseudo-face images created by amalgamating human and animal facial features. This dataset aims to bolster the detection of false positives during training phases. Furthermore, we propose a new face detection architecture that incorporates a classification model into the conventional face detection model to diminish the false positive rate and augment detection precision. Our comparative analysis on the WIDERFACE and other renowned datasets reveals that our architecture secures a lower false positive rate while preserving the true positive rate in comparison to existing top-tier face detection models.

Spatiotemporal change characteristics of vegetation coverage in Shangwan Mine of China's Shendong Mining Area.

The coal mining might cause the disturbance to the vegetation and the disturbance impacts might exist the differences for different areas, and few literatures compared and analyzed different disturbed areas based on the location of the mining face, and paid attention to the post mining self-healing effects of vegetation. Here, this paper selected the GaoFen multispectral images during 2017-2021 to study different areas of Shangwan Mine which includes the old mining area more than 5 years after mining, the new working face underground mined in 2018 and 2019, the natural growth control area and the open-pit mining affected area. The spatiotemporal changes of the surface fraction vegetation coverage (FVC) were analyzed in each area and the correlation between vegetation coverage and climatic factors was studied. The results showed that: (1) The overall vegetation coverage showed a moderate decrease trend in fluctuation from 2017 to 2021. The Open-pit mining affected areas showed the largest decline, reaching 68.3%. The FVC in the underground mining areas had a downward trend, but self-healing effect after mining was also observed. (2) The overall FVC in the study area was positively correlated with the number of precipitation days. (3) There were differences in the sensitivity to mining disturbance for different landform in the underground mining areas. (4) Although the FVC in the Old mining areas had recovered to the level of Natural growth control area, but the annual fluctuation was larger, which might mean lower ecological stability.

Facial Expression Recognition Using Convolutional Neural Network

Understanding others' intentions through nonverbal cues like facial emotions is crucial in human communication. To design and train Deep Learning Models, this paper describes in detail how Convolutional Neural Network Models are developed using tf. Keras. The aim is to Sort facial photos into one of the seven face detection classifiers, our model is developed in such a manner that it learns hidden nonlinearity from the entered facial images, which is vital for discriminating the form of emotion someone is expressing. The model proposed on the Lenet-5 architecture by Yann LeCun uses the subsampling, feature map, and activation function (ReLu) in between the convolutional layer and fully connected layer for the output soft-max activation function will be used. The FER-2013 dataset, which consists of 35,887 structured 48x48 pixel grayscale images, was used to train the CNN models. The training dataset has 28,709 elements, while the testing dataset has 3,589 elements, and while validation has 3,589 elements. Train and test are the two folder names used to organize the FER dataset. separated even further into distinct files, each holding a different kind of FER dataset class. To mitigate the overfitting of the dropout, batch normalization and the model are employed. Since this is a multiclass classification problem, we are utilizing the Soft-max activation function and the Rectified linear unit for non-linear operation (ReLu). We are training a categorical cross- entropy and matrix for accuracy based on the parameters to assess the constructed CNN model's performance by examining the training epoch history and we have used optimizer Adam (Adaptive Moment Estimation) with the learning rate of 0.0001. We obtained the accuracy of the LeNet-5 model on training at 95.49% and testing at 49.47% [13].