Features For Face Recognition Research Articles

Best of two worlds: Efficient, usable and auditable biometric ABC on the blockchain

In García-Rodríguez et al. 2024, two generic constructions for biometric-based non-transferable Attribute Based Credentials (biometric ABC) are presented, which offer different trade-offs between efficiency and trust assumptions. In this paper, we focus on the second scheme denoted as BioABC-ZK that tries to remove the strong (and unrealistic) trust assumption on the Reader R, and we show that BioABC-ZK has a security flaw for a colluding R and Verifier V. Besides, BioABC-ZK lacks GDPR-compliance, which requires secure processing of biometrics, for instance in form of Fuzzy Extractors, as opposed to (i) storing the reference biometric template aBio in the user’s mobile phone and (ii) processing of biometrics using an external untrusted R, whose foreign manufacturers are unlikely to adjust their products according to GDPR.The contributions of this paper are threefold. First, we review efficient biometric ABC schemes to identify the privacy-by-design criteria for them. In view of these principles, we propose a new architecture for biometric ABC of Sarier 2021 by adapting the recently introduced core/helper setting. Briefly, a user in our modified setting is composed of a constrained core device (a SIM card) inside a helper device (a smart phone with dual SIM and face recognition feature), which – as opposed to García-Rodríguez et al. 2024 – does not need to store aBio. This way, the new design provides Identity Privacy without the need for an external R and/or a dedicated hardware per user such as a biometric smart card reader or a tamper proof smart card as in current hardware-bound credential systems. Besides, the new system maintains minimal hardware requirements on the SIM card – only responsible for storing ABC and helper data –, which results in easy adoption and usability without loosing efficiency, if deep face fuzzy vault and our modified ABC scheme are employed together. As a result, a total overhead of 500 ms to a showing of a comparable non-biometric ABC is obtained instead of the 2.1 s in García-Rodríguez et al. 2024 apart from the removal of computationally expensive pairings. Finally, as different from García-Rodríguez et al. 2024, auditing is achieved via Blockchain instead of proving in zero-knowledge the actual biometric matching by the user to reveal malicious behavior of R and V.

Facial length and angle feature recognition for digital libraries.

With the continuous progress of technology, facial recognition technology is widely used in various scenarios as a mature biometric technology. However, the accuracy of facial feature recognition has become a major challenge. This study proposes a face length feature and angle feature recognition method for digital libraries, targeting the recognition of different facial features. Firstly, an in-depth study is conducted on the architecture of facial action networks based on attention mechanisms to provide more accurate and comprehensive facial features. Secondly, a network architecture based on length and angle features of facial expressions, the expression recognition network is explored to improve the recognition rate of different expressions. Finally, an end-to-end network framework based on attention mechanism for facial feature points is constructed to improve the accuracy and stability of facial feature recognition network. To verify the effectiveness of the proposed method, experiments were conducted using the facial expression dataset FER-2013. The experimental results showed that the average recognition rate for the seven common expressions was 97.28% to 99.97%. The highest recognition rate for happiness and surprise was 99.97%, while the relatively low recognition rate for anger, fear, and neutrality was 97.18%. The data has verified that the research method can effectively recognize and distinguish different facial expressions, with high accuracy and robustness. The recognition method based on attention mechanism for facial feature points has effectively optimized the recognition process of facial length and angle features, significantly improving the stability of facial expression recognition, especially in complex environments, providing reliable technical support for digital libraries and other fields. This study aims to promote the development of facial recognition technology in digital libraries, improve the service quality and user experience of digital libraries.

SMART BABY MONITORING SYSTEM USING YOLO V8 ALGORITHM

The Smart Baby Monitoring System using the YOLO V8 algorithm is designed to enhance infant monitoring by leveraging advanced computer vision techniques. This project utilizes YOLO (You Only Look Once) version 8, a state-of-the-art object detection algorithm, implemented with Python and frameworks like Tensor Flow or PyTorch, to detect and track objects in real-time video feeds. The system incorporates features for facial recognition to identify known caregivers and alert mechanisms for unusual activities or emergencies. The user interface provides real-time alerts, visualizations, and historical data analysis for caregivers via a web or mobile application. By leveraging YOLO V8's efficiency in object detection and Python's capabilities for data processing and integration, this system aims to enhance safety, improve care giving efficiency, and provide peace of mind to parents and caregivers.

VigilEye: Machine learning-powered driver fatigue recognition for safer roads

In an era where autonomous vehicles are on the horizon, the importance of human vigilance during driving cannot be understated. One of the paramount challenges road safety advocates face is driver fatigue, a silent culprit behind many tragic accidents. Our project seeks to address this issue by merging facial feature recognition with cutting-edge machine learning techniques, harnessing tools such as OpenCV and Dlib. This approach is centred around 68 precise facial feature detectors, adept at capturing specific markers like the status of a driver's eyes. Once data is acquired, our algorithms scrutinize it for fatigue indicators. Offering both cost and user benefits, our non-intrusive system swiftly alerts drivers, through auditory or tactile means, upon detecting drowsiness. Our system achieved a remarkable 94 % efficiency in timely and accurate fatigue detection through exhaustive testing across varied scenarios, underscoring its potential to revolutionize road safety.

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.

Human Eye Ball Gazing and Face Based Ultra Digital Security System using AI

Abstract: The "Eye Ball Gazing and Face-Based Ultra Digital Security System" invents a remarkable surveillance mechanism by fusing recognition of faces with eye ball movement monitoring. It gathers and safely retains people's unique visages and eyeball peering patterns uponparticipation. It sets up an authentication system with multiple factors that bolsters security and cuts the chance of unlicensed entry if access is requested. This novel solution to the continually evolving requirements of technological safety distinguishes real-time eye-ball peering information with recorded sequences, besides ensuring human facial features. Sophisticated facial identification and eye motion monitoring techniques are put together in the "Eye Ball Gazing and Face-Based Ultra Digital Security System" to produce an effective validation structure in the realm of digital safety. When a person signs up, the tool confidentially saves distinct facial traits and eyeball staring movements. Upon access request, the documented data is cross-referenced with actual time eyeball gazing sequences, and recognition offacial features is utilized to confirm ID in addition.The simultaneous use of both of these methods oflogin minimizes the possibility of inappropriate entry and improves confidentiality, which requiresa multi-step verification procedure. In the current age of technology, this groundbreaking solution guarantees top-notch security and accessibility control.

Face to face: human recognition of Asian elephant facial features

Face to face: human recognition of Asian elephant facial features

Understanding of facial features in face perception: insights from deep convolutional neural networks.

Face recognition has been a longstanding subject of interest in the fields of cognitive neuroscience and computer vision research. One key focus has been to understand the relative importance of different facial features in identifying individuals. Previous studies in humans have demonstrated the crucial role of eyebrows in face recognition, potentially even surpassing the importance of the eyes. However, eyebrows are not only vital for face recognition but also play a significant role in recognizing facial expressions and intentions, which might occur simultaneously and influence the face recognition process. To address these challenges, our current study aimed to leverage the power of deep convolutional neural networks (DCNNs), an artificial face recognition system, which can be specifically tailored for face recognition tasks. In this study, we investigated the relative importance of various facial features in face recognition by selectively blocking feature information from the input to the DCNN. Additionally, we conducted experiments in which we systematically blurred the information related to eyebrows to varying degrees. Our findings aligned with previous human research, revealing that eyebrows are the most critical feature for face recognition, followed by eyes, mouth, and nose, in that order. The results demonstrated that the presence of eyebrows was more crucial than their specific high-frequency details, such as edges and textures, compared to other facial features, where the details also played a significant role. Furthermore, our results revealed that, unlike other facial features, the activation map indicated that the significance of eyebrows areas could not be readily adjusted to compensate for the absence of eyebrow information. This finding explains why masking eyebrows led to more significant deficits in face recognition performance. Additionally, we observed a synergistic relationship among facial features, providing evidence for holistic processing of faces within the DCNN. Overall, our study sheds light on the underlying mechanisms of face recognition and underscores the potential of using DCNNs as valuable tools for further exploration in this field.

Integration of Machine Learning and Iot based Multi-Layer Wireless Sensor Networks for Seamless Smart Home Automation

The integration of machine learning algorithms with Internet of Things -based multi-layer wireless sensor networks offers a transformative solution to modern smart home automation and security. This paper seeks to explore both the Sensor Data Processing and Machine Learning Components used. In essence, the machine learning model leverages aggregate sensor data to improve the efficiency and safety of modern living environments. Through attention to detail during the preprocessing and feature engineering of sensor data, the system analyzed learned patterns of household activity, including motion intensity, door/window interactions, and normal occupancy. Subsequently, the features were utilized as input variables in a number of models, including Convolutional Neural Networks , Support Vector Machines, Recurrent Neural Networks, and K-Nearest Neighbors. By simulating both vacation and occupant mode, the models processed the available data using to detect potential threats or other deficiencies in the patterns. Overall the results led by the model suggest that the Convolutional Neural Network model is the best amongst all of the aforementioned algorithms. It demonstrated the best accuracy out of all the other models due to the advanced image processing and facial recognition features, solidified by its 98.56% accuracy rate in recognizing a potential intruder. Other models were also effective or reasonably accurate, with the following results: SVMs – 95.45%; RNNs – 93.4%; and KNNs – 91.23%. The evaluation process also involves the calculation of precision, recall, and F1 score, which also indicates the overall strength of the model. The aggregation of these results implies a considerable potential for internet-of-things systems in combination with machine learning methods to cultivate smarter and safer living environments.

Effective driver distraction warning system incorporating fast image recognition methods

Modern cars are equipped with advanced automatic technology featuring various safety measures for car occupants. However, the growing density of vehicles, especially in areas where infrastructure development lags, poses potential dangers, particularly accidents caused by driver subjectivity. These incidents may occur due to driver distraction or the presence of high-risk obstacles on the road. This article presents a comprehensive solution to assist drivers in mitigating these risks. Firstly, the study introduces a novel method to enhance the recognition of a driver's facial features by analyzing benchmarks and the whites of the eyes to assess the distraction level. Secondly, a domain division method is proposed to identify obstacles and lanes in front of the vehicle, enabling the assessment of the danger level. This information is promptly relayed to the driver and relevant individuals, such as the driver's manager or supervisor. An experimental device has also been developed to evaluate the effectiveness of the algorithms, solutions, and processing capabilities of the system.

Pilot facial feature recognition and fatigue classification method under high exposure environment

To improve the recognition efficiency of pilot fatigue detection in high exposure environment, a facial feature recognition and fatigue classification method for pilots is proposed. Firstly, the high exposure images are pre-processed with frequency domain light normalization; secondly, a human face detector is trained based on YOLOv5s network model and detects the face, eyes and mouth; again, the fatigue feature values of eyes and mouth are obtained by fusing PERCLOS fatigue detection algorithm; finally, a fatigue classifier is built by RBF-ELM neural network and the fatigue parameters of eyes, mouth and yawning The fatigue parameters of the eye, mouth and yawn features were input to the classifier for fatigue classification. The experimental results show that the fatigue detection speed of the proposed method is up to 310 FPS when computed with GPU, which has higher recognition rate and better robustness compared with the classical PCA, CNN and DCT methods. The method can effectively improve the accuracy of pilot facial feature recognition and eye localization in high exposure environment, and has high practicality for non-contact pilot fatigue detection.

Leveraging a Two-Level Attention Mechanism for Deep Face Recognition with Siamese One-Shot Learning

Discriminative feature embedding is used for largescale facial recognition. Many image-based facial recognition networks use CNNs like ResNets and VGG-nets. Humans prioritise different elements, but CNNs treat all facial pictures equally. NLP and computer vision use attention to learn the most important part of an input signal. The inter-channel and inter-spatial attention mechanism is used to assess face image component significance in this study. Channel scalars are calculated using Global Average Pooling in face recognition channel attention. A recent study found that GAP encodes low-frequency channel information first. We compressed channels using discrete cosine transform (DCT) instead of scalar representation to evaluate information at frequencies other than the lowest frequency for the channel attention mechanism. Later layers can acquire the feature map after spatial attention. Channel and spatial attention increase CNN facial recognition feature extraction. Channel-only, spatial-only, parallel, sequential, or channel-after-spatial attention blocks exist. Current face recognition attention approaches may be outperformed on public datasets (Labelled Faces in the Wild).

Identifying People’s Faces in Smart Banking Systems Using Artificial Neural Networks

Due to the exponential rise of ICT technologies, the digital banking industry has made tremendous advancements in user-friendly, effective, and quick financial transactions. Numerous new banking services, products, and business opportunities have resulted as a result. Smart facial authentication is a cutting-edge technology used in mobile banking. Users can utilize this technology to verify their identification by using the facial recognition feature of the camera on their mobile device. This method makes use of complex algorithms that can analyze a person’s face and extract the distinctive characteristics that can be seen there. The attributes of the images of distinct persons are then categorized using learning algorithms and the K-means clustering method. An artificial neural network (ANN), adaptive neural fuzzy inference system (ANFIS), and decision tree (DT) computer system are used to authenticate persons. In this inquiry, the face is used. Additionally, the Wild Horse Optimizer (WHO) method has been used to enhance the precision and optimization of machine learning systems by weighting cluster features. Fuzzy logic is used to make decisions about authentication based on the results of machine learning algorithms. The best feature from a broad dataset is selected using a technique based on evolutionary algorithms. The simulation findings for diverse users have a precision of about 99.78% for user authentication of test samples. Notably, the suggested method reduced the FAR, FRR, and ERR errors by 0.23, 1.13, and 1.1, respectively. It has been proven that using people’s image data may enhance the quality of everyday cameras, and it is anticipated that this work will be applied to mobile banking applications to ensure the verification of rightful owners.

Fusion of periocular and forehead features for masked face recognition

Fusion of periocular and forehead features for masked face recognition

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

Prediction of Criminal Suspect Characteristics with Application of Wavelet Neural Networks

Abstract Crime incidents grow at a certain rate every year and become more complicated day by day, but at this stage, the development of the field of crime analysis and prediction is still lagging, so this paper applies a wavelet neural network to predict the characteristics of criminal suspects. Analyze the applicability of the WNN model, explore the principle of criminal suspect feature prediction, and study the basis of wavelet neural network analysis. Establish the face feature recognition framework, use the Morlet function and Mexican Hat function pair to optimize and improve the wavelet neural network, and construct the model evaluation index for evaluating the model prediction effect. Preprocessing the suspect feature point data by using the grayscale reflection in Haar features. Simulation experiments are used to analyze the performance of different algorithms and the prediction effect of criminal suspect features on wavelet neural networks. The proposed algorithm in this study is superior and has a lesser number of parameters than ResNet. From the loss curves of different algorithms, the algorithm proposed in this study has a faster-descending loss curve and a smaller loss rate in the epoch value of [100, 200] interval. The overall range of the evaluation indexes of the algorithms proposed in this study is above 88%, and the highest accuracy rate can reach 94.234%, which is a good performance of the algorithms and accurate prediction.

Classifying Face Features For Better Recognition And Detection

Recognition of facial features is in high demand currently because of its value in individual proof of identity, wherein a short input picture or a glance can assist in recognizing an individual using a database of images. This type of identity isn't commonly used in India, although it is necessary. Fingerprint identity systems ought to utilise facial recognition to render the system frictionless and more secure. As a result, these researchers attempted to assess the suitability of two separate face recognition computational methods, facet, which came, and facial features, in this work. The traits are retrieved and then prepared before being turned to a list and then compared with the area of interest to determine the individual in question [5]. The characteristics considered were the Euclidean gap between the pupils, the contours of the nostrils, plus the lip-to-lip length. This initiative will assist in guarding factories wherein trespassing is possible, identifying people in crowds, tracing those who have vanished, and keeping tabs upon some disruptive elements of the community. It's used for a wide range of applications, including legislative bodies and vaults at financial institutions. At the exact same period of time the identification and detection percentages with the three distinct criteria for lateral recognition of faces, opacity identification, and face dramatic emotion are contrasted using the contrast test, and the adequacy for both methods is improved [6]. These results demonstrate the fact that every instance can be assessed individually. Conventional detectors may "perceive" an object or message, turn it into an electrical signal, store it, and then utilise a conversion circuitry to turn the electricity into an amount or another observable screen format.

Image encryption algorithm based on face recognition, facial features recognition and bitonic sequence

Image encryption algorithm based on face recognition, facial features recognition and bitonic sequence

Feature Selection From MagFace Face Recognition Model With Optimization Algorithms

In recent years, many studies have been carried out in the field of artificial intelligence in the literature with the development of equipment. Face recognition algorithms have an important place among these developments. Among the face recognition algorithms, the most successful ones are usually deep learning approaches. Models such as SphereFace, CosFace, ArcFace, and MagFace are important deep learning models in the literature. Despite their success, deep learning models are often computationally costly. Therefore, advanced methods are needed to reduce the computational load for these models. One of the most valid methods for this is to choose the most valuable one among embedding features for face recognition. Thus, cost can be reduced, and accuracy values can be increased even more. In this study, the most valuable of the 512 embedded features in the MagFace model was tried to be obtained by using PSO, GA, SCA, and DE optimization algorithms. As a result, accuracy values of 99.83%, 98.57%, and 98.65% were reached for 193, 252, and 280 features selected in the LFW, CFP, and AGEDB datasets, respectively.

Create and implement a new method for robust video face recognition using convolutional neural network algorithm

Biometric applications have massive demand in today's era. The areas of applications are mostly linked with the security of the system. Biometric features are regarded as the primary resource for security purposes due to their own distinctiveness and non-volatile essence. System authentication using biometrics is considered to be a sophisticated technology. Noise effect inducts variation in the biometric subject that causes an adverse impact on establishing the recognition. The proposed model supported the development of an effective method for performing facial biometric feature recognition. The model's goal is to reduce the number of false approvals and refusals. The proposed algorithm has been applied over a video dataset containing surveillance video frames that captures facial subjects dynamically. The first step is pre-processing of the video frames that have been carried out in the proposed model. Then, the Viola-Jones algorithm was applied to detect the facial subjects in the video frames. Feature extraction from the facial subject has been accomplished by applying a deep reinforcement learning algorithm. Further, the proposed model applied a convolutional neural network (CNN) algorithm to perform feature recognition of facial identity accurately. The proposed technique aims to maintain a huge recognition rate of dynamic facial subjects under various unprecedented noise variations. In the classification algorithm, the recognition accuracy is found to be 98.85%.