Testing novel facial recognition technology to identify dogs during vaccination campaigns.

A lack of methods to identify individual animals can be a barrier to zoonoses control. We developed and field-tested facial recognition technology for a mobile phone application to identify dogs, which we used to assess vaccination coverage against rabies in rural Tanzania. Dogs were vaccinated, registered using the application, and microchipped. During subsequent household visits to validate vaccination, dogs were registered using the application and their vaccination status determined by operators using the application to classify dogs as vaccinated (matched) or unvaccinated (unmatched), with microchips validating classifications. From 534 classified dogs (251 vaccinated, 283 unvaccinated), the application specificity was 98.9% and sensitivity 76.2%, with positive and negative predictive values of 98.4% and 82.8% respectively. The facial recognition algorithm correctly matched 249 (99.2%) vaccinated and microchipped dogs (true positives) and failed to match two (0.8%) vaccinated dogs (false negatives). Operators correctly identified 186 (74.1%) vaccinated dogs (true positives), and 280 (98.9%) unvaccinated dogs (true negatives), but incorrectly classified 58 (23.1%) vaccinated dogs as unmatched (false negatives). Reduced application sensitivity resulted from poor quality photos and light-associated color distortion. With development and operator training, this technology has potential to be a useful tool to identify dogs and support research and intervention programs.

Exploring artificial intelligence from a clinical perspective: A comparison and application analysis of two facial age predictors trained on a large-scale Chinese cosmetic patient database.

BACKGROUND: Age prediction powered by artificial intelligence (AI) can be used as an objective technique to assess the cosmetic effect of rejuvenation surgery. Existing age-estimation models are trained on public datasets with the Caucasian race as the main reference, thus they are impractical for clinical application in Chinese patients. METHODS: To develop and select an age-estimation model appropriate for Chinese patients receiving rejuvenation treatment, we obtained a face database of 10 529 images from 1821 patients from the author's hospital and selected two representative age-estimation algorithms for the model training. The prediction accuracies and the interpretability of calculation logic of these two facial age predictors were compared and analyzed. RESULTS: The mean absolute error (MAE) of a traditional support vector machine-learning model was 10.185 years; the proportion of absolute error ≤6 years was 35.90% and 68.50% ≤12 years. The MAE of a deep-learning model based on the VGG-16 framework was 3.011 years; the proportion of absolute error ≤6 years was 90.20% and 100% ≤12 years. Compared with deep learning, traditional machine-learning models have clearer computational logic, which allows them to give clinicians more specific treatment recommendations. CONCLUSION: Experimental results show that deep-learning exceeds traditional machine learning in the prediction of Chinese cosmetic patients' age. Although traditional machine learning model has better interpretability than deep-learning model, deep-learning is more accurate for clinical quantitative evaluation. Knowing the decision-making logic behind the accurate prediction of deep-learning is crucial for deeper clinical application, and requires further exploration.

A face recognition algorithm based on the combine of image feature compensation and improved PSO.

Face recognition systems have been widely applied in various scenarios in people's daily lives. The recognition rate and speed of face recognition systems have always been the two key technical factors that researchers focus on. Many excellent recognition algorithms achieve high recognition rates or good recognition speeds. However, more research is needed to develop algorithms that can effectively balance these two indicators. In this study, we introduce an improved particle swarm optimization algorithm into a face recognition algorithm based on image feature compensation techniques. This allows the system to achieve high recognition rates while simultaneously enhancing the recognition efficiency, aiming to strike a balance between the two aspects. This approach provides a new perspective for the application of image feature compensation techniques in face recognition systems. It helps achieve a broader range of applications for face recognition technology by reducing the recognition speed as much as possible while maintaining a satisfactory recognition rate. Ultimately, this leads to an improved user experience.

Self-helped detection of obstructive sleep apnea based on automated facial recognition and machine learning.

PURPOSE: The diagnosis of obstructive sleep apnea (OSA) relies on time-consuming and complicated procedures which are not always readily available and may delay diagnosis. With the widespread use of artificial intelligence, we presumed that the combination of simple clinical information and imaging recognition based on facial photos may be a useful tool to screen for OSA. METHODS: We recruited consecutive subjects suspected of OSA who had received sleep examination and photographing. Sixty-eight points from 2-dimensional facial photos were labelled by automated identification. An optimized model with facial features and basic clinical information was established and tenfold cross-validation was performed. Area under the receiver operating characteristic curve (AUC) indicated the model's performance using sleep monitoring as the reference standard. RESULTS: A total of 653 subjects (77.2% males, 55.3% OSA) were analyzed. CATBOOST was the most suitable algorithm for OSA classification with a sensitivity, specificity, accuracy, and AUC of 0.75, 0.66, 0.71, and 0.76 respectively (P < 0.05), which was better than STOP-Bang questionnaire, NoSAS scores, and Epworth scale. Witnessed apnea by sleep partner was the most powerful variable, followed by body mass index, neck circumference, facial parameters, and hypertension. The model's performance became more robust with a sensitivity of 0.94, for patients with frequent supine sleep apnea. CONCLUSION: The findings suggest that craniofacial features extracted from 2-dimensional frontal photos, especially in the mandibular segment, have the potential to become predictors of OSA in the Chinese population. Machine learning-derived automatic recognition may facilitate the self-help screening for OSA in a quick, radiation-free, and repeatable manner.

A computerized facial approximation method for Homo sapiens based on facial soft tissue thickness depths and geometric morphometrics.

Facial approximation (FA) provides a promising means of generating the possible facial appearance of a deceased person. It facilitates exploration of the evolutionary forces driving anatomical changes in ancestral humans and can capture public attention. Despite the recent progress made toward improving the performance of FA methods, a limited understanding of detailed quantitative craniofacial relationships between facial bone and soft tissue morphology may hinder their accuracy, and hence subjective experience and artistic interpretation are required. In this study, we explored craniofacial relationships among human populations based upon average facial soft tissue thickness depths (FSTDs) and covariations between hard and soft tissues of the nose and mouth using geometric morphometrics. Furthermore, we proposed a computerized method to assign the learned craniofacial relationships to generate a probable facial appearance of Homo sapiens, reducing human intervention. A smaller resemblance comparison (an average Procrustes distance was 0.0258 and an average Euclidean distance was 1.79 mm) between approximated and actual faces and a greater recognition rate (91.67%) tested by a face pool indicated that average dense FSTDs contributed to raising the accuracy of approximated faces. Results of partial least squares (PLS) analysis showed that nasal and oral hard tissues have an effect on their soft tissues separately. However, relatively weaker RV correlations (<0.4) and greater approximation errors suggested that we need to be cautious about the accuracy of the approximated nose and mouth soft tissue shapes from bony structures. Overall, the proposed method can facilitate investigations of craniofacial relationships and potentially improve the reliability of the approximated faces for use in numerous applications in forensic science, archaeology, and anthropology.

DF-UDetector: An effective method towards robust deepfake detection via feature restoration.

The abuse of deepfakes, a rising face swap technique, causes severe concerns about the authenticity of visual content and the dissemination of misinformation. To alleviate the threats imposed by deepfakes, a vast body of data-centric detectors has been deployed. However, the performance of these methods can be easily defected by degradations on deepfakes. To improve the performance of degradation deepfake detection, we creatively explore the recovery method in the feature space to preserve the artifacts for detection instead of directly in the image domain. In this paper, we propose a method, namely DF-UDetector, against degradation deepfakes by modeling the degraded images and transforming the extracted features to a high-quality level. To be specific, the whole model consists of three key components: an image feature extractor to capture image features, a feature transforming module to map the degradation features into a higher quality, and a discriminator to determine whether the feature map is of high quality enough. Extensive experiments on multiple video datasets show that our proposed model performs comparably or even better than state-of-the-art counterparts. Moreover, DF-UDetector outperforms by a small margin when detecting deepfakes in the wild.

The emerging scientific public sphere in China's digital economy: Weibo discussions on facial recognition technology.

The present study investigates the Chinese public's perception toward the widely adopted (and often accused of misuse) technology of face recognition. Through topic modeling and a social network analysis of 151,654 Weibo posts, we examine the "content dimension" and the "actor dimension" of civic discussions on facial recognition technology. Our results demonstrate that there is rising social concern and skepticism directed at the commercial use of this biodata-collected technology in China's cyberspace, despite the state's adoption, supervision, and regulation of facial recognition technology being broadly granted. Moreover, while our findings illustrate an extent of openness and equality within the public debates on facial recognition technology, they also show the Chinese government becoming an important "interlocutor" within the said debates, with discursive engagement from industry and academia largely marginalized. Drawing on the results, we suggest that further investigation into the formation of China's scientific public sphere should be located within the broader context of China's vision of a centrally planned digital economy.

The role of ideological dimensions in shaping acceptance of facial recognition technology and reactions to algorithm bias.

Facial recognition technology has been introduced into various aspects of social life, yet it has raised concerns over its infringement of civil liberties and biases against minorities. This study investigates how three ideological dimensions-social dominance orientation, right-wing authoritarianism, and libertarianism-shape facial recognition acceptance. First, two surveys of crowdsourced workers (N = 891 and 587) demonstrated that the acceptance of facial recognition applications is positively associated with right-wing authoritarianism and negatively with libertarianism, whereas social dominance orientation shows little influence. Second, an experiment (N = 496) exposed participants to information about demographic biases in facial recognition applications. This message produced more opposition to facial recognition and this effect largely was not moderated by the three ideological dimensions. In summary, individuals' endorsement of various ideologies predicts their acceptance of facial recognition technology, but messages about algorithm biases in facial recognition can still shape their attitudes regardless of the preexisting ideologies.

Simulated automated facial recognition systems as decision-aids in forensic face matching tasks.

Automated Facial Recognition Systems (AFRS) are used by governments, law enforcement agencies, and private businesses to verify the identity of individuals. Although previous research has compared the performance of AFRS and humans on tasks of one-to-one face matching, little is known about how effectively human operators can use these AFRS as decision-aids. Our aim was to investigate how the prior decision from an AFRS affects human performance on a face matching task, and to establish whether human oversight of AFRS decisions can lead to collaborative performance gains for the human-algorithm team. The identification decisions from our simulated AFRS were informed by the performance of a real, state-of-the-art, Deep Convolutional Neural Network (DCNN) AFRS on the same task. Across five pre-registered experiments, human operators used the decisions from highly accurate AFRS (> 90%) to improve their own face matching performance compared with baseline (sensitivity gain: Cohen's d = 0.71-1.28; overall accuracy gain: d = 0.73-1.46). Yet, despite this improvement, AFRS-aided human performance consistently failed to reach the level that the AFRS achieved alone. Even when the AFRS erred only on the face pairs with the highest human accuracy (> 89%), participants often failed to correct the system's errors, while also overruling many correct decisions, raising questions about the conditions under which human oversight might enhance AFRS operation. Overall, these data demonstrate that the human operator is a limiting factor in this simple model of human-AFRS teaming. These findings have implications for the "human-in-the-loop" approach to AFRS oversight in forensic face matching scenarios. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Sistema inteligente para la medición del comportamiento humano en relación al cumplimiento del protocolo de bioseguridad Covid-19 implementando tecnología de IoB / Smart system for measuring human behavior in relation to compliance with the Covid-19 biosafety protocol, implementing IoB technology

Este proyecto de investigación 2021 desarrollado por la Escuela de Ingeniería en Computación de ITCA-FEPADE, tuvo como objetivo usar las tecnologías para ayudar a mejorar el comportamiento de la comunidad educativa en pandemia Covid-19. Es un sistema inteligente para la medición del comportamiento humano con relación al cumplimiento del protocolo de bioseguridad Covid-19, implementando tecnologías de Internet del Comportamiento IoB, Internet de las Cosas IoT, Business Intelligence, Big Data y reconocimiento facial. La primera fase consistió en la toma de requerimientos y el estudio de investigaciones previas. Posteriormente se diseñó la interfaz del aplicativo que interpreta los datos colectados y la estructura de un dispensador inteligente de alcohol gel para ser impreso en 3D. Finalmente se realizó la programación del sistema y del circuito que conforman el dispositivo. Como resultado se construyó un dispositivo inteligente que mide y alerta la temperatura, dispensa alcohol gel y toma de fotografía para reconocimiento facial en la portación correcta de mascarilla. Incorpora un sistema informático que procesa los datos colectados que son utilizados por la aplicación de Inteligencia de Negocios para analizar el comportamiento de las personas ante el cumplimiento del protocolo de bioseguridad para Covid-19. El resultado del proyecto es un dispositivo inteligente y automatizado, que dotará a la institución de una herramienta innovadora de bajo costo para medir el comportamiento de la población que hace uso de las instalaciones de ITCA-FEPADE Sede Central y contribuirá a prevenir contagios por Covid-19, dando mayor seguridad a un retorno presencial al campus.

This research project was carried out in 2021 by the Escuela de Ingeniería en Computación of ITCA-FEPADE and aimed to use technologies to improve the behavior of the educational community in the context of Covid-19 pandemic. A smart system was development for measuring human behavior in relation to compliance with the Covid-19 biosafety protocol, implementing Internet of Behavior (IoB), Internet of Things (IoT), Business Intelligence, Big Data and facial recognition technologies. The first phase consisted on the identification of requirements and previous investigations. Subsequently, the application interface that interprets the collected data and the structure of a smart hand sanitizer dispenser to be printed in 3D was designed. Finally, the programming of the system and the circuit that make up the device was carried out. As a result, a smart device that measures and alerts the body temperature, dispenses hand sanitizer and applies facial recognition for the detection of proper face mask wearing was built. The device also incorporates a computer system that processes the collected data that to analyze the behavior of people in compliance with the biosafety protocol for Covid-19 through the Business Intelligence application. The result of the project was a smart and automated device that will provide the institution an innovative, low-cost tool to measure the behavior of the population that makes use of the ITCA-FEPADE Sede Central facilities and will contribute to preventing Covid-19 infections by giving greater safety to a face-to-face return to the facilities.

Design of International Chinese Education Promotion Platform Based on Artificial Intelligence and Facial Recognition Technology.

With the continuous development of today's society, digital image processing technology has been applied in more and more fields, among which authentication in digital image processing technology has become a hot field. In the process of identity verification, the face is used as the basis of feature recognition because the method of using the face as a feature basis is more easily accepted by the public and the operation is simple and the feasibility is stronger. In the online education model, observing and comparing students' facial emotions through the platform and analyzing students' learning goals, learning effects, learning emotions, and contradictions and conflicts arising in the process of cooperation have become an effective teaching evaluation system. Up to now, China has developed into the second largest economy in the world. The global "Chinese fever" has brought China's culture into a new stage of development. Countries in the world learn Chinese culture by developing Chinese language courses. By building a Chinese learning intelligent system with a B/S structure, this system can effectively evaluate the teaching process. It can be seen from the test results that the platform meets the basic requirements of functional design.

Facial approximation for identification purposes: soft tissue thickness in a Caucasian population. Sex and age-related variations.

The aim of this study was to collect soft tissue thickness (STT) values of an Italian population from 12 bone landmarks, to improve the facial approximation process for identification purposes. 100 Italian adults (50 males and 50 females), who had undergone head CT for clinical purposes, were analysed in order to expand the database of the Italian population. Average values, standard deviation and range were collected according to gender and age and the obtained values were statistically analysed in order to evaluate any possible significant difference. Only one landmark was statistically significant associated with sex, females showed significantly higher values for para-zygomaxillary. Two landmarks were statistically significant associated with age, upper incisor and pogonion. The obtained results were compared with the existing literature. Such information can be useful in the forensic craniofacial reconstruction process and can facilitate choosing the most suitable STT values according to osteological analysis of the human remains.

Face Presentation Attack Detection Using Deep Background Subtraction.

Currently, face recognition technology is the most widely used method for verifying an individual's identity. Nevertheless, it has increased in popularity, raising concerns about face presentation attacks, in which a photo or video of an authorized person's face is used to obtain access to services. Based on a combination of background subtraction (BS) and convolutional neural network(s) (CNN), as well as an ensemble of classifiers, we propose an efficient and more robust face presentation attack detection algorithm. This algorithm includes a fully connected (FC) classifier with a majority vote (MV) algorithm, which uses different face presentation attack instruments (e.g., printed photo and replayed video). By including a majority vote to determine whether the input video is genuine or not, the proposed method significantly enhances the performance of the face anti-spoofing (FAS) system. For evaluation, we considered the MSU MFSD, REPLAY-ATTACK, and CASIA-FASD databases. The obtained results are very interesting and are much better than those obtained by state-of-the-art methods. For instance, on the REPLAY-ATTACK database, we were able to attain a half-total error rate (HTER) of 0.62% and an equal error rate (EER) of 0.58%. We attained an EER of 0% on both the CASIA-FASD and the MSU MFSD databases.

Internet of Things with Deep Learning-Based Face Recognition Approach for Authentication in Control Medical Systems.

Internet of Things (IoT) with deep learning (DL) is drastically growing and plays a significant role in many applications, including medical and healthcare systems. It can help users in this field get an advantage in terms of enhanced touchless authentication, especially in spreading infectious diseases like coronavirus disease 2019 (COVID-19). Even though there is a number of available security systems, they suffer from one or more of issues, such as identity fraud, loss of keys and passwords, or spreading diseases through touch authentication tools. To overcome these issues, IoT-based intelligent control medical authentication systems using DL models are proposed to enhance the security factor of medical and healthcare places effectively. This work applies IoT with DL models to recognize human faces for authentication in smart control medical systems. We use Raspberry Pi (RPi) because it has low cost and acts as the main controller in this system. The installation of a smart control system using general-purpose input/output (GPIO) pins of RPi also enhanced the antitheft for smart locks, and the RPi is connected to smart doors. For user authentication, a camera module is used to capture the face image and compare them with database images for getting access. The proposed approach performs face detection using the Haar cascade techniques, while for face recognition, the system comprises the following steps. The first step is the facial feature extraction step, which is done using the pretrained CNN models (ResNet-50 and VGG-16) along with linear binary pattern histogram (LBPH) algorithm. The second step is the classification step which can be done using a support vector machine (SVM) classifier. Only classified face as genuine leads to unlock the door; otherwise, the door is locked, and the system sends a notification email to the home/medical place with detected face images and stores the detected person name and time information on the SQL database. The comparative study of this work shows that the approach achieved 99.56% accuracy compared with some different related methods.

Sistema inteligente para la medición del comportamiento humano en relación al cumplimiento del protocolo de bioseguridad Covid-19 implementando tecnología de IoB: aplicación en ITCA-FEPADE Sede Central / Smart system for measuring human behavior in relation to compliance with the Covid-19 biosafety protocol, implementing IoB technology: application at ITCA-FEPADE

Este proyecto fue desarrollado por la Escuela de Ingeniería en Computación de ITCA-FEPADE y tuvo como objetivo usar las tecnologías para ayudar a mejorar el comportamiento de la comunidad educativa en pandemia Covid-19. Es un sistema inteligente para la medición del comportamiento humano con relación al cumplimiento del protocolo de bioseguridad Covid-19, implementando tecnologías de Internet del Comportamiento IoB, Internet de las Cosas IoT, Business Intelligence, Big Data y reconocimiento facial. La primera fase consistió en la toma de requerimientos e investigaciones previas. Posteriormente se diseñó la interfaz del aplicativo que interpreta los datos colectados y la estructura de un dispensador inteligente de alcohol gel para ser impreso en 3D. Finalmente se realizó la programación del sistema y del circuito que conforman el dispositivo. Como resultado se construyó un dispositivo inteligente que mide y alerta la temperatura, dispensa alcohol gel y toma de fotografía para reconocimiento facial en la portación correcta de mascarilla.

This research project was carried out in 2021 by the Escuela de Ingeniería en Computación of ITCA-FEPADE and aimed to use technologies to improve the behavior of the educational community in the context of Covid-19 pandemic. A smart system was development for measuring human behavior in relation to compliance with the Covid-19 biosafety protocol, implementing Internet of Behavior (IoB), Internet of Things (IoT), Business Intelligence, Big Data and facial recognition technologies. The first phase consisted on the identification of requirements and previous investigations. Subsequently, the application interface that interprets the collected data and the structure of a smart hand sanitizer dispenser to be printed in 3D was designed. Finally, the programming of the system and the circuit that make up the device was carried out. As a result, a smart device that measures and alerts the body temperature, dispenses hand sanitizer and applies facial recognition for the detection of proper face mask wearing was built.

Fabrication of 3D Models for Microtia Reconstruction Using Smartphone-Based Technology.

OBJECTIVE: Microtia reconstruction is technically challenging due to the intricate contours of the ear. It is common practice to use a two-dimensional tracing of the patient's normal ear as a template for the reconstruction of the affected side. Recent advances in three-dimensional (3D) surface scanning and printing have expanded the ability to create surgical models preoperatively. This study aims to describe a simple and affordable process to fabricate patient-specific 3D ear models for use in the operating room. STUDY DESIGN: Applied basic research on a novel 3D optical scanning and fabrication pathway for microtia reconstruction. SETTING: Tertiary care university hospital. METHODS: Optical surface scanning of the patient's normal ear was completed using a smartphone with facial recognition capability. The Heges application used the phone's camera to capture the 3D image. The 3D model was digitally isolated and mirrored using the Meshmixer software and printed with a 3D printer (MonopriceTM Select Mini V2) using polylactic acid filaments. RESULTS: The 3D model of the ear served as a helpful intraoperative reference and an adjunct to the traditional 2D template. Collectively, time for imaging acquisition, editing, and fabrication was approximately 3.5 hours. The upfront cost was around $210, and the recurring cost was approximately $0.35 per ear model. CONCLUSION: A novel, low-cost approach to fabricate customized 3D models of the ear is introduced. It is feasible to create individualized 3D models using currently available consumer technology. The low barrier to entry raises the possibility for clinicians to incorporate 3D printing into various clinical applications.

Tecnología de reconocimiento facial y sus riesgos en los derechos humanos / Facial recognition technology and its risks to human rights / A tecnologia de reconhecimento facial e seus riscos para os direitos humanos

El desarrollo de tecnologías dinamizadas por la inteligencia artificial (IA) representa un desafío adaptativo para ciencias tradicionales y rígidas como el derecho. Debido a las características de los diversos métodos o procedimientos usados de forma automatizada, se presenta una relación antagónica entre implementación de herramientas de reconocimiento facial y los derechos considerados garantías constitucionales y fundamentales en el sistema de derechos humanos. El objetivo es describir el funcionamiento de los sistemas de visión involucrados en la IA, presente principalmente en las herramientas de reconocimiento facial, examinando la manera como se relacionan con el derecho penal y reconociendo los riesgos a los derechos humanos en este proceso. Para ello, se usó una metodología cualitativa-inductiva, realizando análisis de fuentes primarias y secundarias, estudios de caso y legislaciones de diversas jurisdicciones relacionadas con reconocimiento facial y su aplicación en las etapas de indagación e investigación en el proceso penal. Como resultado se obtuvo que en dichas etapas existe un riesgo a las garantías de un debido proceso y de no discriminación.

The development of technologies powered by artificial intelligence (AI) represents an adaptive challenge for traditional and rigid sciences such as law. Due to the characteristics of the various methods or procedures used in an automated way, there is an antagonistic relationship between the implementation of facial recognition tools and the rights considered constitutional and fundamental guarantees in the human rights system. The objective is to describe the functioning of the vision systems involved in AI, mainly present in facial recognition tools, examining how they relate to criminal law and recognizing the risks to human rights in this process. For this purpose, a qualitative-inductive methodology was used, analyzing primary and secondary sources, case studies and legislation from various jurisdictions related to facial recognition and its application in the investigation and inquiry stages of the criminal process. As a result, it was obtained that in such stages there is a risk to the guarantees of due process and non-discrimination.

O desenvolvimento de tecnologias impulsionadas pela inteligência artificial (IA) representa um desafio adaptativo para as ciências tradicionais e rígidas, como o direito. Devido às características dos vários métodos ou procedimentos utilizados de forma automatizada, existe uma relação antagônica entre a implementação de ferramentas de reconhecimento facial e os direitos considerados garantias constitucionais e fundamentais no sistema de direitos humanos. O objetivo é descrever o funcionamento dos sistemas de visão envolvidos na IA, principalmente presentes nas ferramentas de reconhecimento facial, examinando como eles se relacionam com o direito penal e reconhecendo os riscos aos direitos humanos neste processo. Para este fim, foi utilizada uma metodologia qualitativa-indutora, analisando fontes primárias e secundárias, estudos de casos e legislação de várias jurisdições relacionadas ao reconhecimento facial e sua aplicação nas fases de investigação e inquérito de processos criminais. Como resultado, foi obtido que nestas etapas há um risco para as garantias de um processo justo e não-discriminação.

Effective Face Detector Based on YOLOv5 and Superresolution Reconstruction.

The application of face detection and recognition technology in security monitoring systems has made a huge contribution to public security. Face detection is an essential first step in many face analysis systems. In complex scenes, the accuracy of face detection would be limited because of the missing and false detection of small faces, due to image quality, face scale, light, and other factors. In this paper, a two-level face detection model called SR-YOLOv5 is proposed to address some problems of dense small faces in actual scenarios. The research first optimized the backbone and loss function of YOLOv5, which is aimed at achieving better performance in terms of mean average precision (mAP) and speed. Then, to improve face detection in blurred scenes or low-resolution situations, we integrated image superresolution technology on the detection head. In addition, some representative deep-learning algorithm based on face detection is discussed by grouping them into a few major categories, and the popular face detection benchmarks are enumerated in detail. Finally, the wider face dataset is used to train and test the SR-YOLOv5 model. Compared with multitask convolutional neural network (MTCNN), Contextual Multi-Scale Region-based CNN (CMS-RCNN), Finding Tiny Faces (HR), Single Shot Scale-invariant Face Detector (S3FD), and TinaFace algorithms, it is verified that the proposed model has higher detection precision, which is 0.7%, 0.6%, and 2.9% higher than the top one. SR-YOLOv5 can effectively use face information to accurately detect hard-to-detect face targets in complex scenes.

Public attitudes towards the use of automatic facial recognition technology in criminal justice systems around the world.

Automatic facial recognition technology (AFR) is increasingly used in criminal justice systems around the world, yet to date there has not been an international survey of public attitudes toward its use. In Study 1, we ran focus groups in the UK, Australia and China (countries at different stages of adopting AFR) and in Study 2 we collected data from over 3,000 participants in the UK, Australia and the USA using a questionnaire investigating attitudes towards AFR use in criminal justice systems. Our results showed that although overall participants were aligned in their attitudes and reasoning behind them, there were some key differences across countries. People in the USA were more accepting of tracking citizens, more accepting of private companies' use of AFR, and less trusting of the police using AFR than people in the UK and Australia. Our results showed that support for the use of AFR depends greatly on what the technology is used for and who it is used by. We recommend vendors and users do more to explain AFR use, including details around accuracy and data protection. We also recommend that governments should set legal boundaries around the use of AFR in investigative and criminal justice settings.