Human Face Identification Research Articles

Head rotation and the perception of eyelid height and contour

PurposeEffective visual perceptual processing is one of the many components of surgical competence. Human face identification is most efficient when viewed upright. However, it is not yet clear how this...

Human face identification after plastic surgery using SURF, Multi-KNN and BPNN techniques

Facial identification for surgical and non-surgical datasets is getting popular. The reason behind this popularity is the growing need of a robust facial recognition system which is consistent to occlusion, spoofing attacks and last but most important plastic surgery effects. Plastic therapies are undertaken by individuals to beautify their external appearance but it is also undertaken by impostors to commit crimes and falsify their true identities. This research work aims at developing a facial recognition system which can identify genuine and impostor pairs. The projected methodology optimizes face detection via Back-Propagation Neural Network (BPNN) and dimensionality reduction by means of Speeded Up Robust Features followed by Multi-K-Nearest-Neighbor technique. The novelty is the production of an innovative-fangled T-Database which trains the BPNN. Thus, BPNN converges faster and achieves higher recognition. The proposed scheme is not applied till date on a medically altered dataset. We have applied five distance metrics and integrated them to acquire T-Dataset, which is fed to the BPNN. This scheme is tested on surgical and non-surgical datasets and it is deduced that higher recognition is achieved with non-surgical databases as compared to surgical ones. For both surgical and non-surgical datasets, the computational cost attained is the modest.

Enhanced Face Detection in Videos Based on Integrating Spatial Features (LBP, CS-LBP) with CNN Technique

Face detection is a crucial aspect of computer vision and image processing, in order to enable the automatic detection and identification of human faces in video streams, face detection is an essential component of computer vision and image processing. Applications for facial recognition, video analytics, security systems, and surveillance all depend on it. Face identification techniques face many obstacles and issues, such as positional fluctuations, illumination changes, resolution and scale issues, facial emotions, and cosmetics. Robust algorithms are required for efficient face detection. This field looks at the feature extraction process using a variety of techniques. These consist of the center symmetric local binary patterns (CS_LBP) approach and the local binary patterns (LBP) method. The YouTube Face database provided the video frames that we used for our study. In order to train the convolutional neural network (CNN) to detect human faces in the video and draw a bounding box around them. The experimental results of the suggested approaches show that. The accuracy rate was 94% higher with the LBP techniques. However, the CS_LBP technique showed the best level of accuracy in both face detection and face rectangle recognition, with an accuracy rate of 95%.

A DEEP LEARNING-BASED EFFICIENT FIREARMS MONITORING TECHNIQUE FOR BUILDING SECURE SMART CITIES

Any kind of violence is a shame to the world we live in. However, violence still plays a significant role in our society today and claims many innocent lives. Using a gun is one of the traditional methods of violence. Nowadays, firearm-related fatalities are a widespread occurrence. It poses a risk to public safety and presents difficulties for law enforcement. Most of these incidents take place in cities or semi-urban regions. Today, CCTV-based surveillance is widely used by both public and commercial institutions for monitoring and prevention. However, human-based monitoring is error-prone and needs a large number of person-hours as a resource. However, automated smart surveillance is better suited for large-scale and dependable monitoring of violent actions. The primary goal of the study is to demonstrate how deep learning-based methods may be used to identify weaponry, especially rifles. This research employs many detection methods for human face and gun identification, including the newest EfficientDet-based architectures and Faster Region-Based Convolutional Neural Networks (Faster RCNN). The post-processing detection performance of weapons and human faces has been enhanced using an ensemble (stacked) strategy that employs Non-Maximum Suppression, Non-Maximum Weighted, and Weighted Box Fusion techniques. In this study, the comparative outcomes of several detection methods and their ensembles have been addressed experimentally. It facilitates the police's rapid information gathering about the situation and enables them to take prompt preventative action. Additionally, social media videos may be found using the same method for gun-based content recognition. Here, the mean average precisions for the mAP0.5, mAP0.75, and mAP[0.500.95] are 77.02%, 16.40%, and 29.73%, respectively, according to the Weighted Box Fusion-based Ensemble Detection Scheme. Out of all the options tested, the outcomes provide the best performance. The model has undergone extensive testing using movie clips and unidentified test photos. The resulting ensemble schemes are consistently better than the basic models and are adequate.

An Improved Face Recognition Method Based on Convolutional Neural Network

Face recognition using an image-processing technique is a valuable and effective approach to verifying the identity of a human being. Authorizing users based on human face identification remains one of the biggest challenges. However, with the improvement of deep learning and the creation of deep convolutional neural networks, the performance of face recognition has significantly improved. However, the outcomes from different models and networks are quite different in terms of accuracy. This paper proposes a face recognition model based on a Convolutional neural network (CNN). The recognition rate of the AT&T and AR data set on the proposed model is 99.17% and 99.12%.

FACE IDENTIFICATION USING BACK-PROPAGATION ADAPTIVE MULTIWAVENET

Face Identification is an important research topic in the field of computer vision and pattern recognition and has become a very active research area in recent decades. Recently multiwavelet-based neural networks (multiwavenets) have been used for function approximation and recognition, but to our best knowledge it has not been used for face Identification. This paper presents a novel approach for the Identification of human faces using Back-Propagation Adaptive Multiwavenet. The proposed multiwavenet has a structure similar to a multilayer perceptron (MLP) neural network with three layers, but the activation function of hidden layer is replaced with multiscaling functions. In experiments performed on the ORL face database it achieved a recognition rate of 97.75% in the presence of facial expression, lighting and pose variations. Results are compared with its wavelet-based counterpart where it obtained a recognition rate of 10.4%. The proposed multiwavenet demonstrated very good recognition rate in the presence of variations in facial expression, lighting and pose and outperformed its wavelet-based counterpart.

Digital technology and artificial intelligence issues in scientific works

The article presents the results of a study to identify trends in the coverage of digital technology and artificial intelligence in scientific papers. Semantic units reflecting aspects of digitalization, artificial intelligence, augmented reality are revealed. The main semantic units, reflecting different aspects of the research field are digitalization; artificial intelligence (additional semantic units: knowledge representation, theorem proving, computer vision, robotics, machine learning, multi-agent systems, artificial intelligence tools); neural networks (additional semantic units: learning with a teacher, learning without a teacher, input data); strong or general artificial intelligence, weak or applied artificial intelligence; Marusya voice assistant, Alisa voice assistant, Siri voice assistant, Bixby voice assistant, Google Assistant; speech recognition, fingerprint recognition, human face identification. Quantitative changes in the coverage of digital technologies, artificial intelligence, augmented reality elements in scientific papers of scientists for the period from 2016 to 2021 are presented and graphically visualized. The analysis of quantitative characteristics of materials and content component of semantic units on the indicated theme is given. The subject of the study is the publications of Russian and foreign authors, dealing with the issues of digitalization and artificial intelligence, included in the database of the Russian Institute of Scientific and Technical Information of the Russian Academy of Sciences (VINITI RAS) for the period from 2016 to 2021.

Automatic Human Face Detection and Recognition Based On Facial Features Using Deep Learning Approach

In recent years, there has been an increased emphasis placed on the identification of face traits in studies. The human face is the most significant characteristic that may be used in the process of identifying a person. Even the most genetically identical twins may be distinguished from one another by a few key facial characteristics. Therefore, to discern one from the other, a human face identification and detection system that is based on facial traits is necessary. This study suggests a technique for automated human face identification and recognition based on facial characteristics that are achieved via the use of deep learning. It would seem that deep learning, with its high rate of accuracy, would be an appropriate method to use while carrying out face recognition. Face detection and identification may be accomplished using a process known as deep learning. According to the results of the study, it is possible to conclude that the approach that was suggested is superior to other ways in terms of accuracy, precision, recall, and f1-score.

Human Face Identification Using Haar Cascade Classifier and LBPH Based on Lighting Intensity

The problem in implementing online learning during the Covid-19 era is the lack of internet access for video streaming, especially in small towns or villages. The solution idea is to minimize the video bandwidth quota by only showing emoticons. The first step of the process is the system must be able to lock the face area to be translated. This study aims to identify areas of the human face based on camera captures. The research was conducted using the Haar cascade classifier algorithm to recognize the facial area of the captured image. Then the Local Binary Pattern Histogram algorithm will recognize the identity of the face. The lighting scenario will be used as a distracting effect on the image. The results showed that based on 30 sets of images tested in bright conditions, the system was able to recognize facial identities up to 62%, normal conditions 51% and dark conditions 46%.

Application of facial recognition technology to prevent insider attacks

The article discusses the types of biometric authentication to prevent insider attacks, their comparative analysis. There are various methods of determining insider activity. Today, Data Leak Prevention (DLP) systems, which are used to prevent the leakage of confidential information from the information system, are widespread. However, these software complexes do not allow detecting a potential attacker at an early stage, as well as monitoring the connection of users, since a tight connection is formed between users and computers with access rights of their level. Biometric innovations are a solution that allows providing a sufficient level of security, user convenience and optimization of business processes. Among the main types of biometric authentication methods, static methods of human biometrics have become the most widespread. These include identification based on the papillary pattern on the fingers, the iris and retina of the eye, the pattern of hand veins, the geometry of the hands, and the face. The family of methods using dynamic characteristics include: voice identification, handwriting dynamics, heart rate, and gait. Biometric technologies consist in measuring and using unique physical or behavioral traits of people to distinguish them from each other. Biometric recognition forms a strong connection between a person and his personality as a biometric feature. It cannot be separated from a person, lost or duplicated. So, biometric recognition is a protection method more resistant to social engineering attacks compared to conservative recognition methods (passwords, tokens, etc.).Also the approach to identification of human faces and description of the system of their recognition working in a mode close to real time which allows to trace a subject’s head, and then distinguishes it, comparing initial features of a face with earlier recognized is offered.

Live video face recognition using raspberry pi

Face Detection and Recognition is a challenging area of computer vision that involves in identification of human faces. Face recognition has a lot of applications in real-time like in security, accessibility, and even in payments. Since the number of applications increases, there is a need of more efficient, reliable and low-cost face recognition system in today’s world. The aim of the paper is to develop such type of face recognition system using Raspberry Pi device. The setup consists of a Raspberry Pi 4 Model B device with a camera module attached. The camera is used to take the input images of any person and store them to train our model. The proposed model makes use of OpenCV, TheHaar Cascadeclassifiers for face detection and the HOG(Histogram of Gradient Descent) + SVM classifiers for real time face recognition. After vigorous testing the overall complexity and accuracy of the model the system is proved to be efficient and robust.

Students Attendances System Using Face Recognition

Abstract: Now a days we are living in this world where everything is automated and linked online. Internet are the things discover and it is used all over a world very beneficially.in human body face is the crucial factor for identifying each person. It can be identified by using different method like biometric for taking attendance. But in this method many more time are required to take attendance and also people are in contact with each other while marking their attendance in this pandemic situation we are introducing new technology student attendance system using face reorganization. Generally in a classroom the attendance was taken manually at ending or beginning of the class. The problem is that they required a lot of time to be taken and some manual and paper work will make a chance of mistake. To overcome from this problem we are introducing face recognition base attendance system. It is used in many application for identification of human face in a digital image or live video stream video. The proposed system make used of Haar classifier, KNN, CNN, SVM and global filters. After this recognition attendance report will be generated in excel format. The overall accuracy and complexity are calculated after testing this system it is cost efficient and need less installation time. Keywords: Face recognitions, Face detection, Haar classifier, CNN, KNN, SVM, LBPH, Automatic Attendances and image processing.

In Your Face: Person Identification Through Ratios and Distances Between Facial Features

These days identification of a person is an integral part of many computer-based solutions. It is a key characteristic for access control, customized services, and a proof of identity. Over the last couple of decades, many new techniques were introduced for how to identify human faces. This approach investigates the human face identification based on frontal images by producing ratios from distances between the different features and their locations. Moreover, this extended version includes an investigation of identification based on side profile by extracting and diagnosing the feature sets with geometric ratio expressions which are calculated into feature vectors. The last stage involves using weighted means to calculate the resemblance. The approach considers an explainable Artificial Intelligence (XAI) approach. Findings, based on a small dataset, achieve that the used approach offers promising results. Further research could have a great influence on how faces and face-profiles can be identified. Performance of the proposed system is validated using metrics such as Precision, False Acceptance Rate, False Rejection Rate, and True Positive Rate. Multiple simulations indicate an Equal Error Rate of 0.89. This work is an extended version of the paper submitted in ACIIDS 2020.

Intelligent video analytics of air objects in real time

Intelligent video analytics is a technology that combines many accurate analytical and approximate numerical methods of automated analysis of the sequence of images coming from video cameras in real time or from archival recordings. Video analytics is implemented in the form of software (software) for working with video content. The software is based on a wide range of mathematical models and methods that allow video monitoring and data mining without direct human involvement. Currently, in video surveillance systems, there are numerous examples of successfully solved problems using video analytics: - recognition of people and transport in order to count their number; - number recognition (on transport, on banknotes, documents, etc.); - detection of events (movement, movement, intersection of permissible lines and boundaries, stay in areas, throwing objects over the fence, etc.); - detection of dangerous situations (crowds, abandoned objects, fires and smoke, etc.); - recognition of dangerous objects, identification of human faces and their search in databases; - analysis of data without the direct participation of people. Extensive use of IP-cameras allows to adequately reflect the real world in a parallel - digital world, in which strict conditions (laws) of stay and behavior of different subjects of this world can be established. Video analytics, without the intervention of individual entities, allows the most effective monitoring of these conditions by different entities and, in the first stage, to issue emergency messages in case of violation. In the next stages, video analytics provides support for decision-making on measures and tools that should be applied to entities that have violated the conditions of stay and behavior, up to their implementation. Airspace monitoring systems use video cameras with rotation, tilt and zoom functions - PTZ cameras, named for their ability to rotate left and right, tilt up and down, zoom and convert images. Rotary cameras perform these actions thanks to a unique combination of pan, tilt and zoom control functions. The overall ability of the PTZ camera to approximate the image consists of the value of digital and optical zooms. Digital zoom uses electronics to enlarge and reduce the image, while optical zoom uses lens movement. The total value of the camera's zoom capability can be calculated by multiplying the digital and optical zoom values. Video analytics of air objects (SO) automates many functions of airspace monitoring, the main of which are: - detection (detection) of all software located in the controlled area of ​​air space; - tracking of selected software; - software type recognition; - forecasting software trajectories; - detection of events related to the behavior (trajectory) of the software. All functions are performed repeatedly, providing continuous refinement of hypotheses about the number, location, type of software and its intentions in the controlled area of ​​air space. Software recognition means a wide range of tasks - from binary classification of software type target / noise to the identification or verification of software on the basis of characteristics. The use of video analytics software in airspace monitoring systems makes it possible to automatically, without human intervention, in the process of video surveillance to solve problems that are usually only possible for humans. This technology is used both to ensure the safety of protected objects and to prevent software from being in a controlled area of ​​airspace. Video analytics software is used to obtain an objective assessment of the effectiveness of airspace monitoring, as it is able to produce continuous and automated collection and analysis of video data, independent of the human factor, and generate reports at the request of the user at any time .

Algorithms for face recognition drones

This paper elucidates diverse algorithms that are used in drones for face identification. Face identification is the thriving technology that utilizes image processing for the identification of human faces. The main reasons for the booming interest in face recognition include the rise in population which demands high security and surveillance systems, requisite for identity verification in the digital world, for the combat in rural areas, alleviation during disasters, and so on. The goal of this paper is to explore, compare and contrast numerous face identification algorithms such as Linear Discriminant Analysis (LDA), Local Binary Pattern Histogram (LBPH), Principal Component Analysis (PCA), Elastic Bunch Graph Matching (EBGM) and neural networks. This study would assist the technologists in the field of face recognition to frame a hybrid algorithm based on the needs of the real time applications.

Real Time Face Detection With Image Dataset Load On Haar Cascade Algorithm

Human face identification has been a difficult issue in the regions of picture preparing and patter acknowledgment.[1] Another human face location calculation by crude Haar course calculation joined with three extra feeble classifiers is proposed in this paper. The three powerless classifiers depend on skin shade histogram coordinating, eyes location and mouth identification.[2] To start with, pictures of individuals are prepared by a crude Haar course classifier, almost without wrong human face dismissal (low pace of bogus negative) yet with some off-base acknowledgment (bogus positive)[3]. Furthermore, to dispose of these wrongly acknowledged non-human faces, a frail classifier dependent on face skin shade histogram coordinating is applied and a dominant part of non-human appearances are taken out. Next, another powerless classifier dependent on eyes identification is annexed and some leftover non-human countenances are resolved and dismissed. At long last, a mouth location activity is used to the excess non-human countenances what's more, the bogus positive rate is additionally diminished [4] With the help of OpenCV,test results on pictures of individuals under various impediments and enlightenments and some level of directions and revolutions, in both preparing set show that the proposed count is successful and accomplishes cutting edge execution. Moreover, it is productive due to its effectiveness and straightforwardness of execution

ROBUST K-NEAREST NEIGHBOR CLASSIFIER AND NEAREST MEAN CLASSIFIER BASED INFORMATIVE KNOWLEDGE DISTILLATION FACE RECOGNITION

Human Face identification procedures have made tremendous progress in the last decade. Nevertheless, identifying faces with incomplete impediment is as yet challenging for the present face identifiers, and is very much required within certifiable application programs regarding reconnaissance and protection. Though great examination exertion has been dedicated to creating face de-impediment techniques, the greater part of them can just function admirably under obliged conditions. In this manuscript is proposed a Robust K-NNC (K-Nearest Neighbor Classifier) and NMC(Nearest Mean Classifier ) (RKNNC-NMC) prototype to efficiently reestablish incompletely occluded faces even in nature. This model comprises of two-stream, first introduced to perceive high-resolution faces and goal corrupted appearances with a student stream and a teacher stream, separately. A Teacher stream is signified by a Complex RKNNC-NMC for the sake of high-exactness recognition, and the student stream is signified by an a lot more straightforward RKNNC-NMC for low-unpredictability recognition. Broad examinations on synthetic and real datasets datasets of countenances with impediment plainly show the viability of RKNNC-NMC in eliminating various kinds of impediment in one’s face at different locations. The suggested technique additionally gives better behaviour gain than other de-occlusion strategies in advancing recognition execution through partially-occluded faces.

RERS-CC: Robotic facial recognition system for improving the accuracy of human face identification using HRI.

Human-Computer Interaction (HCI) is incorporated with a variety of applications for input processing and response actions. Facial recognition systems in workplaces and security systems help to improve the detection and classification of humans based on the vision experienced by the input system. In this manuscript, the Robotic Facial Recognition System using the Compound Classifier (RERS-CC) is introduced to improve the recognition rate of human faces. The process is differentiated into classification, detection, and recognition phases that employ principal component analysis based learning. In this learning process, the errors in image processing based on the extracted different features are used for error classification and accuracy improvements. The performance of the proposed RERS-CC is validated experimentally using the input image dataset in MATLAB tool. The performance results show that the proposed method improves detection and recognition accuracy with fewer errors and processing time. The input image is processed with the knowledge of the features and errors that are observed with different orientations and time instances. With the help of matching dataset and the similarity index verification, the proposed method identifies precise human face with augmented true positives and recognition rate.

Face Recognition Using Various Feature Extraction Approaches

This paper introduces an experimental study on the recognition of the person’s face by utilizing three Techniques of extraction: Principle Components Analysis (PCA), Linear Discriminant Analysis (LDA) and Contourlet- Curvelet Transform (CCT). The results of these approaches were observed and compared to discover the perfect scheme for identification of human faces. The tests have been carried out on the faces databases of (ORL),(UMIST), and (JAFFE). The results acquired by the methods were quantified by altering the ratio of train to test photos in three categories: 75/25, 55/45 and 35/65. The evaluation results showed that the CCT extraction method provides better results than the others. The highest recognition rate was recorded for the CCT approach (recognition rate=98.980%) when the (train/test) photos ratio is (75/25). Furthermore, the best recognition rates for the LDA and PCA were 96.391% and 95.127% respectively. The Matlab R2019b program was used for implementing and testing the algorithms.

Smart Door Lock/Unlock Using Raspberry Pi

This paper deals with the proposed system for smart and savvy door lock recognition system which is essentially for identification of human faces and mainly for home security. This is divided into two sub systems. First is image capturing, then comes face detection and recognition and finally automatic door access management. Open CV is mainly used for Face Recognition because it uses Eigen faces which compares the face images and produces it without losing vital face features, facial images of various persons are going to be stored in database. The purpose of the paper is to take face recognition to height which can replace the use of standard passwords, pins and patterns, adding more security to our life. The process carried out by raspberry pi is fast and makes the system work smoother.