Facial Information Research Articles

No evidence of spatial representation of age, but \u201cown-age bias\u201d like face processing found in chimpanzees

Previous studies have revealed that non-human primates can differentiate the age category of faces. However, the knowledge about age recognition in non-human primates is very limited and whether non-human primates can process facial age information in a similar way to humans is unknown. As humans have an association between time and space (e.g., a person in an earlier life stage to the left and a person in a later life stage to the right), we investigated whether chimpanzees spatially represent conspecifics’ adult and infant faces. Chimpanzees were tested using an identical matching-to-sample task with conspecific adult and infant face stimuli. Two comparison images were presented vertically (Experiment 1) or horizontally (Experiment 2). We analyzed whether the response time was influenced by the position and age category of the target stimuli, but there was no evidence of correspondence between space and adult/infant faces. Thus, evidence of the spatial representation of the age category was not found. However, we did find that the response time was consistently faster when they discriminated between adult faces than when they discriminated between infant faces in both experiments. This result is in line with a series of human face studies that suggest the existence of an “own-age bias.” As far as we know, this is the first report of asymmetric face processing efficiency between infant and adult faces in non-human primates.

Visual adaptation and 7T fMRI reveal facial identity processing in the human brain under shallow interocular suppression

Face identity is represented at a high level of the visual hierarchy. Whether the human brain can process facial identity information in the absence of visual awareness remains unclear. In this study, we investigated potential face identity representation through face-identity adaptation with the adapting faces interocularly suppressed by Continuous Flash Suppression (CFS) noise, a modified binocular rivalry paradigm. The strength of interocular suppression was manipulated by varying the contrast of CFS noise. While obeservers reported the face images subjectively unperceived and the face identity objectively unrecognizable, a significant face identity aftereffect was observed under low but not high contrast CFS noise. In addition, the identity of face images under shallow interocular suppression can be decoded from multi-voxel patterns in the right fusiform face area (FFA) obtained with high-resolution 7T fMRI. Thus the comined evidence from visual adaptation and 7T fMRI suggest that face identity can be represented in the human brain without explicit perceptual recognition. The processing of interocularly suppressed faces could occur at different levels depending on how “deep” the information is suppressed.

Multiple feature fusion‐based video face tracking for IoT big data

With the advancement of Internet of Things (IoT) and artificial intelligence technologies, and the need for rapid application growth in fields, such as security entrance control and financial business trade, facial information processing has become an important means for achieving identity authentication and information security. However, in the process of acquiring facial feature information, face information is easily affected by factors, such as object occlusion, lighting changes, and similar backgrounds. In this paper, we propose a multifeature fusion algorithm based on integral histograms and a real-time update tracking particle filtering (PF) module. First, edge features and colour features are extracted, weighting methods are used to weight the colour histogram and edge features to describe facial features, and fusion of colour features and edge features is made adaptive by using fusion coefficients to improve face tracking reliability. Then, the integral histogram is integrated into the PF algorithm to simplify the calculation steps of complex particles and improve operational efficiency. Finally, the tracking window size is adjusted in real-time according to the change in the average distance from the particle centre to the edge of the current model and the initial model to reduce the drift problem and achieve stable tracking with significant changes in the target dimension. The results show that the algorithm improves video tracking accuracy, simplifies particle operation complexity, improves the speed, and has good anti-interference ability and robustness compared with extracting a single feature.

Classification images reveal uniform decay of facial feature information in visual working memory

Classification images reveal uniform decay of facial feature information in visual working memory

Application of Empirical Mode Decomposition for Decoding Perception of Faces Using Magnetoencephalography.

Neural decoding is useful to explore the timing and source location in which the brain encodes information. Higher classification accuracy means that an analysis is more likely to succeed in extracting useful information from noises. In this paper, we present the application of a nonlinear, nonstationary signal decomposition technique—the empirical mode decomposition (EMD), on MEG data. We discuss the fundamental concepts and importance of nonlinear methods when it comes to analyzing brainwave signals and demonstrate the procedure on a set of open-source MEG facial recognition task dataset. The improved clarity of data allowed further decoding analysis to capture distinguishing features between conditions that were formerly over-looked in the existing literature, while raising interesting questions concerning hemispheric dominance to the encoding process of facial and identity information.

High prevalence of protozoan infections: a permanent cycle in a brazilian semi-arid peripheric area

In regions where sanitary conditions are poor, prophylactic administration of antiparasitic drugs is common and affects the prevalence of intestinal parasites, in spite of the environmental maintenance of their life cycle. The purpose of this study was to evaluate the prevalence of parasitic infections, patient lifestyles, health conditions and environmental sources of contamination. One hundred seventy two children and adolescents, 5 to 15 years of age of both sexes were analyzed. Data were obtained through epidemiological questionnaires, parasitological examinations using Paratest®, IgG testing for Entamoeba histolytica, and analysis of sources of contamination in living areas. The study detected a prevalence of 45.9% (79/172) parasitic infections, of which 62.0% (49/79) Entamoeba histolytica/E. dispar complex; 46.8% (37/79) Entamoeba coli; 27.8% (22/79) Giardia intestinalis; 12.7% (10/79) Endolimax nana; 10.1% (8/79) Hymenolepis nana; 8.9% (7/79) Ascaris lumbricoides and 2.5% (2/79) Trichuris trichiura. Out of the 49 samples positive for Entamoeba histolytica complex, there was only one case of antibodies to E. histolytica. The children’s life habits demonstrated inadequate food hygiene practices. These insufficient sanitary parameters revealed a general lack of information in face of an alarming situation regarding sewage and other sources of environmental contamination in 20% of the areas. The high prevalence of protozoan infections despite chemoprophylaxis, with environmental sources of contamination/risk, inadequate health conditions and the general apathy of the population suggest the ineffectiveness of current preventive practices. Thus, it is advisable that control actions include protozoa as therapeutic targets and, above all, health education as a routine practice to prevent the long-term continuance of this vicious cycle. KEY WORDS: Parasitic infections; chemoprophylaxis; environmental sources.

Effects of dataset characteristics on the performance of fatigue detection for crane operators using hybrid deep neural networks

Fatigue of operators due to intensive workloads and long working time is a significant constraint that leads to inefficient crane operations and increased risk of safety issues. It can be potentially prevented through early warnings of fatigue for further appropriate work shift arrangements. Many deep neural networks have recently been developed for the fatigue detection of vehicle drivers through training and processing the facial image or video data from the public driver's datasets. However, these datasets are difficult to directly use for the fatigue detections under crane operation scenarios due to the variations of facial features and head movement patterns between crane operators and vehicle drivers. Furthermore, there is no representative and public dataset with the facial information of crane operators under construction scenarios. Therefore, this study aims to explore and analyse the features of multi-sources datasets and the corresponding data acquisition methods which are suitable for crane operators' fatigue detection, further providing collection guidelines of crane operators dataset. Variations on public datasets such as real or pretend facial expression, the segment level of human-verified labelling, camera positions, acquisition scenarios, and illumination conditions are analysed. A hybrid learning architecture is proposed by combining convolutional neural networks (CNN) and long short-term memory (LSTM) for fatigue detection. In order to establish a unified evaluation criterion, the effort of the study includes relabelling three public vehicle drivers datasets, NTHU-DDD, UTA-RLDD, and YawnDD, with human-verified labels at the frame and minute segment levels, and training the corresponding hybrid fatigue detection models accordingly. The average detection accuracies and losses are identified for the trained models of UTA-RLDD, NTHU-DDD, and YawnDD individually. The trained models are used to evaluate the fatigue status of facial videos from licensed crane operators under simulated crane operation scenarios. The results suggest the necessary considerations of different influential factors for establishing a large and public fatigue dataset for crane operators.

An empirical study of the impact of masks on face recognition

Face recognition has a wide range of applications like video surveillance, security, access control, etc. Over the past decade, the field of face recognition has matured and grown at par with the latest advancements in technology, particularly deep learning. Convolution Neural Networks have surpassed human accuracy in Face Recognition on popular evaluation tests such as LFW. However, most existing models evaluate their performance with an assumption of the availability of full facial information. The COVID-19 pandemic has laid forth challenges to this assumption, and to the performance of existing methods and leading-edge algorithms in the field of face recognition. This is in the wake of an explosive increase in the number of people wearing face masks. The reduced amount of facial information available to a recognition system from a masked face impacts their discrimination ability. In this context, we design and conduct a series of experiments comparing the masked face recognition performances of CNN architectures available in literature and exploring possible alterations in loss functions, architectures, and training methods that can enable existing methods to fully extract and leverage the limited facial information available in a masked face. We evaluate existing CNN-based face recognition systems for their performance against datasets composed entirely of masked faces, in contrast to the existing standard evaluations where masked or occluded faces are a rare occurrence. The study also presents evidence denoting an increased impact of network depth on performance compared to standard face recognition. Our observations indicate that substantial performance gains can be achieved by the introduction of masked faces in the training set. The study also inferred that various parameter settings determined suitable for standard face recognition are not ideal for masked face recognition. Through empirical analysis we derived new value recommendations for these parameters and settings.

The Autistic Brain Can Process Local but Not Global Emotional Information in Faces and Music

Tieshan complex body (TCB) is located in Zhenghe County on the border of Zhejiang and Fujian, covering an area of about 5.7 km2. Tieshan complex body (TCB) is the most developed metasomatised area in the southeast of China, which was misunderstood as a syenite intrusion.Much Study has carried on at Shizigang in the southwest of the TCB. The alkali metasomatites are composed of feldspar, pyroxene, amphibole, biotite and melanite et al. Potassic feldspars in Complex body have four kinds of forms and can be separated into three stages: (1) one in facial alkali alteration and one in alkali alteration with melanites, (2) one in light alkali feldspar veins, and (3) one in dark alkali feldspar veins and.Pyroxenes had three kinds of forms: some in breccias, some in feldspar and some accompanied with amphiboles. Amphiboles had two kinds of forms: in breccias and scatter in feldspars in the veins, its mineral compositions are composed of basaltic hornblende, ferrous pargasite, actinolite and ferroactinolite, all belong to calcic amphibole subgroup. Biotites are scattered in breccias and in the veins or which is the product of metasomatised pyroxenes. The compositions of biotites show low-Ti and Fe, but high-Mg, which were the thermal products of a higher oxygen fugacity. Melanites occurred as layers and belts, which were metasomatised by feldspars and epidotes and amphiboles and carbonates and sericites and diopsides, their ingredients are solid solution series between andradite and Grossular and reflect the melanites were formed in the relative oxidative, alkaline environment.X-ray powder diffraction and infrared spectrum analyses of K-feldspar from early alkali feldspar provide degrees of ordering of 0.71–0.80, structural parameters of 1.27–1.61, triclinicities of 0.23–0.29, T1 (o) + T1 (m) of 0.86–0.90 degrees of ordering of 0.67–0.88 from late K-feldspar, its structural parameters of 1.10–1.91, triclinicities of 0.30–0.70, T1 (o) + T1(m) of 0.84–0.93. Both two kinds of alkali feldspars are microcline, most adularia. Their structure temperatures vary from 200 to 370 °C which are the highest temperatures at which K-feldspars were formed. Thus, it is concluded the K-feldspars in Tieshan is originated from thermal fluid, and the fluid was potassium-rich and a little rich in sodium at the later stage.The 39Ar-40Ar age of feldspars shows 118.68 ± 7.70 Ma and 114.61 ± 6.74 Ma, which represent the ages of early stage facial alkali alteration and late stage dark alkali feldspar veins respectively. It is obvious that an original granites were formed at about 250 to 255 Ma, but all the rocks were considered to be strongly metasomatised by alkali fluid later, most occurred during 108–126 Ma in Yanshanism. Metasomatism of the TCB reflected that complex history of the region. The metasomatised rocks include fenite and amphibole feldsparite. Fenite, especially apatite-rich fenite is associated with REE mineralization, which is helpful to understand the mechanism of a large scale of rare earth deposits in the region.

Head pose estimation: A survey of the last ten years

Head pose is an important cue in computer vision when using facial information. Over the last three decades, methods for head pose estimation have received increasing attention due to their application in several image analysis tasks. Although many techniques have been developed in the years to address this issue, head pose estimation remains an open research topic, particularly in unconstrained environments. In this paper, we present a comprehensive survey focusing on methods under both constrained and unconstrained conditions, focusing on the literature from the last decade. This work illustrates advantages and disadvantages of existing algorithms, starting from seminal contributions to head pose estimation, and ending with the more recent approaches which adopted deep learning frameworks. Several performance comparison are provided. This paper also states promising directions for future research on the topic.

Do facially disfiguring features influence attention and perception of faces? Evidence from an antisaccade task.

Facial disfigurements can influence how observers attend to and interact with the person, leading to disease-avoidance behaviour and emotions (disgust, threat, fear for contagion). However, it is unclear whether this behaviour is reflected in the effect of the facial stigma on attention and perceptual encoding of facial information. We addressed this question by measuring, in a mixed antisaccade task, observers’ speed and accuracy of orienting of visual attention towards or away from peripherally presented upright and inverted unfamiliar faces that had either a realistic looking disease-signalling feature (a skin discolouration), a non-disease-signalling control feature, or no added feature. The presence of a disfiguring or control feature did not influence the orienting of attention (in terms of saccadic latency) towards upright faces, suggesting that avoidance responses towards facial stigma do not occur during covert attention. However, disfiguring and control features significantly reduced the effect of face inversion on saccadic latency, thus suggesting an impact on the holistic processing of facial information. The implications of these findings for the encoding and appraisal of facial disfigurements are discussed.

Fear-specific leftward bias in gaze direction judgment

Previous studies have shown that humans have a left spatial attention bias in cognition and behaviour. However, whether there exists a leftward perception bias of gaze direction has not been investigated. To address this gap, we conducted three behavioural experiments using a forced-choice gaze direction judgment task. The point of subjective equality (PSE) was employed to measure whether there was a leftward perception bias of gaze direction, and if there was, whether this bias was modulated by face emotion. The results of experiment 1 showed that the PSE of fearful faces was significantly positive as compared to zero and this effect was not found in angry, happy, and neutral faces, indicating that participants were more likely to judge the gaze direction of fearful faces as directed to their left-side space, namely a leftward perception bias. With the response keys counterbalanced between participants, experiment 2a replicated the findings in experiment 1. To further investigate whether the gaze direction perception variation was contributed by emotional or low-level features of faces, experiment 2b and 3 used inverted faces and inverted eyes, respectively. The results revealed similar leftward perception biases of gaze direction in all types of faces, indicating that gaze direction perception was biased by emotional information in faces rather than low-level facial features. Overall, our study demonstrates that there a fear-specific leftward perception bias in processing gaze direction. These findings shed new light on the cerebral lateralization in humans.

Where did you take those photos? Tourists’ preference clustering based on facial and background recognition

The Internet and social media have become major channels for communicating destination image. Pictorial destination image, as shaped by user-generated photos posted on social media, is a key factor in potential tourists' perceptions and decision making. Over 50% of photos contain tourists' facial information. This paper proposes a novel approach to analyzing tourists' travel patterns and their preferences based on facial and photo content recognition techniques. Photos containing tourists' faces were filtered, and different tourist groups were classified by age and gender. Findings indicate that the grouped tourists expressed varying preferences in terms of photographed points of interest and backgrounds. These phenomena were explained based on the notion of tourists’ gaze and several psychological theories. • Proposed a novel destination image comparison method based on facial information. • Uses a total of 8704 photos to study the TDI differences among tourists toward Beijing. • A machine learning based sentiment and object recognition to analyze tourism photos. • Proved that tourists of varying profiles chose different backgrounds for their photos.

Faceknow: Facial Expression Recognition by a Global-Local Network with a Sub-Images-Related Contextual Attention Mechanism

Recognizing health status through human faces is a challenging research topic. Among them, facial recognition expressions can indirectly reflect the inner health status, which has very significant commercial and research value. Most research work on facial expression recognition uses traditional methods, and the accuracy of traditional methods highly depends on feature extraction. Deep learning has already promoted the research on facial expression recognition. This paper proposes a dual-branch network that uses global facial information and local information obtained by using the attention mechanism to merge and identify human facial emotional information. Use of shared pre-training module to extract low-level semantic information of global and also local images. The dual-branch network architecture utilizes the attention module to capture the relationship between different sub-images to fuse the local features of the face. Experimental results demonstrate that the accuracy of the CK+ Dataset reaches 95.96%, which is improved compared to other existing methods.

Face Recognition Depends on Specialized Mechanisms Tuned to View-Invariant Facial Features: Insights from Deep Neural Networks Optimized for Face or Object Recognition.

Face recognition is a computationally challenging classification task. Deep convolutional neural networks (DCNNs) are brain-inspired algorithms that have recently reached human-level performance in face and object recognition. However, it is not clear to what extent DCNNs generate a human-like representation of face identity. We have recently revealed a subset of facial features that are used by humans for face recognition. This enables us now to ask whether DCNNs rely on the same facial information and whether this human-like representation depends on a system that is optimized for face identification. In the current study, we examined the representation of DCNNs of faces that differ in features that are critical or non-critical for human face recognition. Our findings show that DCNNs optimized for face identification are tuned to the same facial features used by humans for face recognition. Sensitivity to these features was highly correlated with performance of the DCNN on a benchmark face recognition task. Moreover, sensitivity to these features and a view-invariant face representation emerged at higher layers of a DCNN optimized for face recognition but not for object recognition. This finding parallels the division to a face and an object system in high-level visual cortex. Taken together, these findings validate human perceptual models of face recognition, enable us to use DCNNs to test predictions about human face and object recognition as well as contribute to the interpretability of DCNNs.

A Study on Intelligent Obscured Face Image Completion System Based on GAN Network

Image recognition and processing is an important part of modern information technology. However, in real life, the face will inevitably be blocked by hats, masks, or face photos are damaged, scratches, and images are added mosaic and other reasons, resulting in face image masking, increasing face information recognition and processing difficulties. Image completion is a kind of technology to restore the missing information of obscured image. By supplementing the information of missing area, it can reduce the difficulty of image recognition and simplify the processing of face information.So it has important research significance for the restoration of shaded image. The traditional image completion technology produces the face of poor natural degree. At present, most of the popular completion methods combine depth learning, and the repair methods based on generating anti-network GAN are the representatives of them.But the stability of the network is poor, so it is difficult to train pictures with large sheltered area or poor image quality.Some methods are not effective in the completion of arbitrary shaded areas. Therefore, this study focuses on the improvement of the stability of the generated adversarial network and the maintenance of the global and local semantic consistency between the completion image and the real image. The main work includes: (1) Sets a special network structure of global discriminator and local discriminator. When the input is arbitrarily shaded, the completion image can maintain the consistency of global and local semantics. (2) The least square loss function is used to improve the stability of the GAN network. So it performs great when the input image has large area masking or low visualization degree. (3) ADAM algorithm is used to accelerate the training of neural network. (4) Based on the completion model, a human-computer interaction software is designed and developed, which includes data set selection, image selection, image completion, result evaluation and so on. The system is applied to the removal of facial structures such as wrinkles and spots. Compared with some existing software, the system can effectively remove the selected facial structures without image distortion. Based on the design of special network structure, the system improves the supervision ability of global and local completion, the stability of GAN network and enhances its training ability in large area masking. The system is intelligent and has strong completion ability for arbitrary masking and large area masking. The research results of this paper effectively restore the information loss caused by image masking and prepare favorable conditions for subsequent image recognition and processing.

A novel constrained dense convolutional autoencoder and DNN-based semi-supervised method for shield machine tunnel geological formation recognition

Accurately acquiring the geological information of the tunnel face will help to set the optimal operational parameters, so that the shield machine can achieve better tunneling performance. The design of the shield machine prevents the operator from observing the surrounding environment directly, and the soft methods which can utilize machine parameters to recognize geological conditions indirectly are becoming a research hotspot. However, current soft methods are all supervised methods which can only use the few machine data with geological type labels, and the unlabeled machine data that is much more than the labeled machine data is wasted. To make the most of all the collected in-situ data to boost the performance of the geological formation recognition model, a novel constrained dense convolutional autoencoder and DNN-based semi-supervised method is proposed. To begin with, 177 machine parameters related to geological conditions are selected and preprocessed. Then, a novel geological feature extractor is obtained via the proposed constrained dense convolutional autoencoder and the unlabeled data. Eventually, a DNN-based geological feature classifier is trained on the basis of the established feature extractor and the labeled machine data, which is capable of recognizing geological formation of the tunnel face. In-situ data collected from a Singapore project (stacked twin bored tunnels) was used to prove the superiority of the proposed method. The results show the constrained dense convolutional autoencoder can extract geological-related features accurately, and the proposed method outperforms other supervised soft methods. Its classification performance in one tunnel is 23.98%, 17.47%, 1.93%, and 18.52% higher than the random forest-based, decision tree-based, KNN-based, and SVM-based methods, respectively. Its classification performance in another tunnel is 33.54%, 33.75%, 42.87%, 43.58%, 33.75%, 49.91%, 37.77%, and 27.04% higher than the random forest-based, SVM-based, decision tree-based, DNN-based, KNN-based, CNN-based, ResNet-based, and DenseNet-based methods, respectively. Thus, the novel semi-supervised method has significantly better generalizability than the currently adopted supervised soft methods.

Zombie Firms, Corporate Restructuring and Relationship Banking: Credit Guidance as a Key to Tackle Zombie Lending?

Abstract Economists have examined the rise of so-called zombie firms in recent years. Such firms remain in financial distress for a prolonged period while financial creditors keep them alive through continued lending. Based on signaling theory, we investigate zombie firms in the context of corporate restructuring and relationship banking. Combining a theoretical approach with a multiple case study on German medium-sized firms facing private workouts, we derive the following main propositions: (i) Banks face information asymmetry and may have incentives for loan extension (i.e., rescheduled installments and additional collateral) when deciding about restructuring financing. In the case of financing unviable restructuring strategies, this can lead to the emergence of zombie firms. (ii) For this reason and in contrast to recent research, not only weakly capitalized but also healthy banks may face such incentives and might end up in financing zombie firms. (iii) Relationship banking reduces bank information asymmetry. Thus, it may enable banks to detect clients’ distress situations in the early stages and to support resolving them. Hence, guiding and inspecting banks (i.e., credit guidance) to carry out supportive relationship banking might be a key to preventing the emergence of zombie firms. The propositions bear several implications relevant to academic research, bank management and banking regulation.

Monetary and fiscal policy interactions in a frictional model of fiat money, nominal public debt and banking

In this paper, we study the interactions between fiscal and monetary policy in a frictional economy where fiat money, bank deposits and short-term and long-term nominal government bonds coexist. Since agents face information frictions and bankers have limited commitment, bank deposits need to be collateralized with nominal public debt. These bank deposits can only be used as payment instruments in some states, while fiat money is always accepted. Within this frictional environment, we study monetary and fiscal policy interactions under different policy stances. When the monetary authority follows an active policy regime, a unique stationary equilibrium exists regardless of how the supply of the various nominal government bonds is specified. Under this policy regime, we also find that consumption inequality increases when the central bank pursues an expansionary monetary policy. In contrast, when the fiscal authority pursues active policies, real indeterminacies can exist. However, when the fiscal authority issues sufficiently few long-term (or short-term) bonds, a unique steady state exists. We also identify cases where an expansionary fiscal policy leads to a decline in consumption inequality between money transactions and deposit-backed transactions. Finally, regardless of the policy regime chosen by the government, financial innovations alter the relative demand for public debt and do not always lead to an increase in welfare. The financial innovations alter the underlying monetary and fiscal policy interactions and consumption inequality.

Enhancing Neural Sign Language Translation by highlighting the facial expression information

Neural Sign Language Translation (SLT), which is an important cross-modal task to bridge the communication gap between the deaf and the hearing people, has attracted great attention in the field of artificial intelligence, computer vision, and multimedia, etc. Although some great progress has been achieved recently, current neural SLT models still suffer from translation errors caused by under-consideration of non-manual features such as facial expressions, which can carry critical information during communication among the deaf. This paper aims to enhance the traditional neural SLT models by highlighting the facial expression information in the CNN-based sign video representing part. Two novel schemes have been proposed. The first scheme is based on a Multi-stream Architecture, which extracts and represents the facial expression information in an additional stream and aggregates it with the information from the main stream. The second scheme is a pre-trained scheme based on Regions of Interest (RoIs), which first trains a multi-region detection module for recognizing the features of faces and bodies and then transfers the pre-trained parameters to the module in SLT model. To validate the proposed models, we conducted the experiments upon the publicly available SLT benchmark dataset: RWTH-PHOENIX-Weather-2014T. Experimental results showed that both the above-mentioned schemes can improve the performance of SLT models. Especially, the RoIs-based scheme can achieve an improvement up to 1.6+ BLEU-4 score gains, while the multi-stream scheme quantitatively analyzed the importance of the face mainly through flexible components, providing a sufficient theoretical basis for the RoIs-based scheme.