Facial Information Research Articles

The role of discriminability in face perception: Interference processing of expression, gender, and gaze.

Eye gaze plays a fundamental role in social interaction and facial recognition. However, interference processing between gaze and other facial variants (e.g., expression) and invariant information (e.g., gender) remains controversial and unclear, especially the role of facial information discriminability in interference. A Garner paradigm was used to conduct two experiments. This paradigm allows simultaneous investigation of the mutual influence of two kinds of facial information in one experiment. In Experiment 1, we manipulated facial expression discriminability and investigated its role in interference processing of gaze and facial expression. The results show that individuals were unable to ignore expression when classifying gaze with both high and low discriminability but could ignore gaze when classifying expression with high discriminability only. In Experiment 2, we manipulated gender discriminability and investigated its function in interference processing of gaze and gender. Participants were unable to ignore gender when classifying gaze with both high and low discriminability but could ignore gaze when classifying gender with low discriminability only. The results indicate that gaze categorization is affected by facial expression and gender regardless of facial information discriminability, whereas interference of gaze on facial expression and gender depends on the degree of discriminability. The present study provides evidence that the processing of gaze and other variant and invariant information is interdependent.

Adaptive Multilayer Perceptual Attention Network for Facial Expression Recognition

In complex real-world situations, problems such as illumination changes, facial occlusion, and variant poses make facial expression recognition (FER) a challenging task. To solve the robustness problem, this paper proposes an adaptive multilayer perceptual attention network (AMP-Net) that is inspired by the facial attributes and the facial perception mechanism of the human visual system. AMP-Net extracts global, local, and salient facial emotional features with different fine-grained features to learn the underlying diversity and key information of facial emotions. Different from existing methods, AMP-Net can adaptively guide the network to focus on multiple finer and distinguishable local patches with robustness to occlusion and variant poses, improving the effectiveness of learning potential facial diversity information. In addition, the proposed global perception module can learn different receptive field features in the global perception domain, and AMP-Net also supplements salient facial region features with high emotion correlation based on prior knowledge to capture key texture details and avoid important information loss. Many experiments show that AMP-Net achieves good generalizability and state-of-the-art results on several real-world datasets, including RAF-DB, AffectNet-7, AffectNet-8, SFEW 2.0, FER-2013, and FED-RO, with accuracies of 89.25%, 64.54%, 61.74%, 61.17%, 74.48%, and 71.75%, respectively. All codes and training logs are publicly available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/liuhw01/AMP-Net</uri> .

TH-224. Differential impact of different types of dementia on perception and cerebral coding of emotional facial information: An event-related oscillations study

TH-224. Differential impact of different types of dementia on perception and cerebral coding of emotional facial information: An event-related oscillations study

Face-Information Sampling in Super-Recognizers

Perceptual processes underlying individual differences in face-recognition ability remain poorly understood. We compared visual sampling of 37 adult super-recognizers—individuals with superior face-recognition ability—with that of 68 typical adult viewers by measuring gaze position as they learned and recognized unfamiliar faces. In both phases, participants viewed faces through “spotlight” apertures that varied in size, with face information restricted in real time around their point of fixation. We found higher accuracy in super-recognizers at all aperture sizes—showing that their superiority does not rely on global sampling of face information but is also evident when they are forced to adopt piecemeal sampling. Additionally, super-recognizers made more fixations, focused less on eye region, and distributed their gaze more than typical viewers. These differences were most apparent when learning faces and were consistent with trends we observed across the broader ability spectrum, suggesting that they are reflective of factors that vary dimensionally in the broader population.

Face detection for rail transit passengers based on single shot detector and active learning

COVID-19 spreads rapidly among people, so that more and more people are wearing masks in rail transit stations. However, the current face detection algorithms cannot distinguish between a face wearing a mask and a face not wearing a mask. This paper proposes a face detection algorithm based on single shot detector and active learning in rail transit surveillance, effectively detecting faces and faces wearing masks. Firstly, we propose a real-time face detection algorithm based on single shot detector, which improves the accuracy by optimizing backbone network, feature pyramid network, spatial attention module, and loss function. Subsequently, this paper proposes a semi-supervised active learning method to select valuable samples from video surveillance of rail transit to retrain the face detection algorithm, which improves the generalization of the algorithm in rail transit and reduces the time to label samples. Extensive experimental results demonstrate that the proposed method achieves significant performance over the state-of-the-art algorithms on rail transit dataset. The proposed algorithm has a wide range of applications in rail transit stations, including passenger flow statistics, epidemiological analysis, and reminders of passenger who do not wear masks. Simultaneously, our algorithm does not collect and store face information of passengers, which effectively protects the privacy of passengers.

Preference for horizontal information in faces predicts typical variations in face recognition but is not impaired in developmental prosopagnosia

Face recognition is strongly influenced by the processing of orientation structure in the face image. Faces are much easier to recognize when they are filtered to include only horizontally oriented information compared with vertically oriented information. Here, we investigate whether preferences for horizontal information in faces are related to face recognition abilities in a typical sample (Experiment 1), and whether such preferences are lacking in people with developmental prosopagnosia (DP; Experiment 2). Experiment 1 shows that preferences for horizontal face information are linked to face recognition abilities in a typical sample, with weak evidence of face-selective contributions. Experiment 2 shows that preferences for horizontal face information are comparable in control and DP groups. Our study suggests that preferences for horizontal face information are related to variations in face recognition abilities in the typical range, and that these preferences are not aberrant in DP.

Maturational trajectory of fusiform gyrus neural activity when viewing faces: From 4 months to 4 years old.

Infant and young child electrophysiology studies have provided information regarding the maturation of face-encoding neural processes. A limitation of previous research is that very few studies have examined face-encoding processes in children 12–48 months of age, a developmental period characterized by rapid changes in the ability to encode facial information. The present study sought to fill this gap in the literature via a longitudinal study examining the maturation of a primary node in the face-encoding network—the left and right fusiform gyrus (FFG). Whole-brain magnetoencephalography (MEG) data were obtained from 25 infants with typical development at 4–12 months, and with follow-up MEG exams every ∼12 months until 3–4 years old. Children were presented with color images of Face stimuli and visual noise images (matched on spatial frequency, color distribution, and outer contour) that served as Non-Face stimuli. Using distributed source modeling, left and right face-sensitive FFG evoked waveforms were obtained from each child at each visit, with face-sensitive activity identified via examining the difference between the Non-Face and Face FFG timecourses. Before 24 months of age (Visits 1 and 2) the face-sensitive FFG M290 response was the dominant response, observed in the left and right FFG ∼250–450 ms post-stimulus. By 3–4 years old (Visit 4), the left and right face-sensitive FFG response occurred at a latency consistent with a face-sensitive M170 response ∼100–250 ms post-stimulus. Face-sensitive left and right FFG peak latencies decreased as a function of age (with age explaining greater than 70% of the variance in face-sensitive FFG latency), and with an adult-like FFG latency observed at 3–4 years old. Study findings thus showed face-sensitive FFG maturational changes across the first 4 years of life. Whereas a face-sensitive M290 response was observed under 2 years of age, by 3–4 years old, an adult-like face-sensitive M170 response was observed bilaterally. Future studies evaluating the maturation of face-sensitive FFG activity in infants at risk for neurodevelopmental disorders are of interest, with the present findings suggesting age-specific face-sensitive neural markers of a priori interest.

A Study on the Application of Walking Posture for Identifying Persons with Gait Recognition

In terms of gait recognition, face recognition is currently the most commonly used technology with high accuracy. However, in an image, there is not necessarily a face. Therefore, face recognition cannot be used if there is no face at all. However, when we cannot obtain facial information, we still want to know the person’s identity. Thus, we must use information other than facial features to identify the person. Since each person’s behavior will be somewhat different, we hope to learn the difference between one specific human body and others and use this behavior to identify the human body because deep learning technology advances this idea. Therefore, we used OpenPose along with LSTM for personal identification. We found that using people’s walking posture is feasible for identifying their identities. Presently, the environment for making judgments is limited, in terms of height, and there will be restrictions on distance. In the future, using various angles and distances will be explored. This method can also solve the problem of half-body identification and is also helpful for finding people.

Application of Mobile Virtual Reality Technology Combined with Neural Network in Facial Expression Recognition.

In recent years, in the field of virtual reality, in more and more scenes, users interact with hardware or programs through facial expressions. In order to give full play to the advantages of program interaction between virtual reality devices and users, this paper proposes a mobile virtual reality expression recognition system combined with convolution neural network. Based on the optimized AlexNet network, an expression recognition algorithm is constructed and combined with LBP feature mapping technology to improve the performance of the algorithm. At the same time, according to the nature and characteristics of mobile virtual reality devices, the user face information acquisition algorithm is optimized. The performance test results of the expression recognition system show that the recognition accuracy of the system is higher than that of the traditional convolution neural network expression recognition algorithm, and the maximum difference is greater than 10%. At the same time, the average running speed of the whole system is about 37 ms, which can meet the accuracy and real-time requirements of expression recognition in virtual reality interaction. The experimental results show that the expression recognition system proposed in this paper can be applied to mobile virtual reality devices. At the same time, it also provides new ideas for industry researchers to optimize the identification function.

Development of an intention estimation model based on gaze and face information for electric wheelchair operation support

AbstractIn recent years, various user interfaces have been developed to meet the diverse needs of physically disabled persons. In this paper, we developed a method to identify gazing and facial movements based on gaze time and eye/face information and developed an electric wheelchair that can be operated with the user's natural gazing and facial movements. This intention estimation model is composed of 1DCNN and LSTM layers. First, 1DCNN is used to extract features from gaze and face information, and then the extracted features are input to LSTM to estimate the user's intentions regarding movement. The evaluation experiments suggest that the combination of gaze and face information improves the estimation accuracy and contributes to the classification. Furthermore, it was confirmed that adding a convolutional filter layer to the LSTM layer improved the accuracy.

SMaTE: A Segment-Level Feature Mixing and Temporal Encoding Framework for Facial Expression Recognition.

Despite advanced machine learning methods, the implementation of emotion recognition systems based on real-world video content remains challenging. Videos may contain data such as images, audio, and text. However, the application of multimodal models using two or more types of data to real-world video media (CCTV, illegally filmed content, etc.) lacking sound or subtitles is difficult. Although facial expressions in image sequences can be utilized in emotion recognition, the diverse identities of individuals in real-world content limits computational models of relationships between facial expressions. This study proposed a transformation model which employed a video vision transformer to focus on facial expression sequences in videos. It effectively understood and extracted facial expression information from the identities of individuals, instead of fusing multimodal models. The design entailed capture of higher-quality facial expression information through mixed-token embedding facial expression sequences augmented via various methods into a single data representation, and comprised two modules: spatial and temporal encoders. Further, temporal position embedding, focusing on relationships between video frames, was proposed and subsequently applied to the temporal encoder module. The performance of the proposed algorithm was compared with that of conventional methods on two emotion recognition datasets of video content, with results demonstrating its superiority.

Machine Learning-Driven Enterprise Human Resource Management Optimization and Its Application.

With the advent of the Internet era, the frequency and proportion of candidates obtaining recruitment information through the Internet is getting higher and higher, and the amount of human resource information, such as talent information and job information, has also increased unprecedentedly, which makes human resource services face information overload. Especially with the gradual increase of the amount of information, this method is not enough for the acquisition and classification of massive data. After that, experts developed search engines to deal with the retrieval problem, and the first ones were Google and Baidu. As long as the search engine is clear about the direction of the search, it is indeed very convenient for the retrieval of massive data. However, in many cases, most users cannot clearly recognize the content they need or how to accurately express their needs. Faced with this problem, people propose recommender systems to solve the problem of obtaining preference information, which can better increase the user's experience and meet their own needs more easily. Based on the main workflow of the recommender system, this paper designs the overall architecture of the human resources recommendation system and implements a human resources recommendation prototype system based on deep learning. The system can better overcome the cold start problem and provide real-time recommendation results, improving the quality of HR personalized recommendation results.

Healthy aging impairs face discrimination ability.

Face images enable individual identities to be discriminated from one another. We aimed to quantify age-related changes in different aspects of face identity discrimination. Face discrimination sensitivity was measured with a memory-free “odd-one-out” task. Five age groups (N = 15) of healthy adults with normal vision were tested: 20, 50-59, 60-69, 70-79, and 80-89. Sensitivity was measured for full-face images (all features visible), external features (head-shape, hairline), internal features (nose, mouth, eyes, and eyebrows) and closed-contour shapes (control object). Sensitivity to full-faces continuously declined by approximately 13% per decade, after 50 years of age. When age-related differences in visual acuity were controlled, the effect of age on face discrimination sensitivity remained. Sensitivity to face features also deteriorated with age. Although the effect for external features was similar to full-faces, the rate of decline was considerably steeper (approximately 3.7 times) for internal, relative to external, features. In contrast, there was no effect of age on sensitivity to shapes. All age groups demonstrated the same overall pattern of sensitivity to different types of face information. Healthy aging was associated with a continuous decline in sensitivity to both full-faces and face features, although encoding of internal features was disproportionately impaired. This age-related deficit was independent of differences in low-level vision. That sensitivity to shapes was unaffected by age suggests these results cannot be explained by general cognitive decline or lower-level visual deficits. Instead, healthy aging is associated with a specific decline in the mechanisms that underlie face discrimination.

Gone but not Forgotten: How Inventor Exit Helps in Technology Acquisitions

Firms interact with the strategic factor market to acquire new or external knowledge. However, firms face information asymmetries while trading resources in the strategic factor market because it is not perfect. We argue that inventor-exit helps a firm to identify a target for knowledge acquisition. Inventor–exit from a focal firm to a hiring firm suppresses information asymmetry between the firms and therefore increases the probability of acquisition. Moreover, the positive effect of inventor–exit on the likelihood of acquisition is negatively moderated by the research experience of the hiring firm. The analysis based on the global biopharmaceutical industry in the period 1993–2010 supports the arguments.

Multimodal Biometrics Recognition Using a Deep Convolutional Neural Network with Transfer Learning in Surveillance Videos

Biometric recognition is a critical task in security control systems. Although the face has long been widely accepted as a practical biometric for human recognition, it can be easily stolen and imitated. Moreover, in video surveillance, it is a challenge to obtain reliable facial information from an image taken at a long distance with a low-resolution camera. Gait, on the other hand, has been recently used for human recognition because gait is not easy to replicate, and reliable information can be obtained from a low-resolution camera at a long distance. However, the gait biometric alone still has constraints due to its intrinsic factors. In this paper, we propose a multimodal biometrics system by combining information from both the face and gait. Our proposed system uses a deep convolutional neural network with transfer learning. Our proposed network model learns discriminative spatiotemporal features from gait and facial features from face images. The two extracted features are fused into a common feature space at the feature level. This study conducted experiments on the publicly available CASIA-B gait and Extended Yale-B databases and a dataset of walking videos of 25 users. The proposed model achieves a 97.3 percent classification accuracy with an F1 score of 0.97and an equal error rate (EER) of 0.004.

A High-Security Privacy Image Encryption Algorithm Based on Chaos and Double Encryption Strategy

Faces are widely used in information recognition and other fields. Due to the openness of the Internet, ensuring that face information is not stolen by criminals is a hot issue. The traditional encryption method only encrypts the whole area of the image and ignores some features of the face. This paper proposes a double-encrypted face image encryption algorithm. The contour features of the face are extracted, followed by two rounds of encryption. The first round of encryption algorithm encrypts the identified face image, and the second round of encryption algorithm encrypts the entire image. The encryption algorithm used is scrambling and diffusion at the same time, and the keystream of the cryptosystem is generated by 2D SF-SIMM. The design structure of this cryptosystem increases security, and the attacker needs to crack two rounds of the algorithm to get the original face image.

A neural signature of exposure to masked faces after 18 months of COVID-19

In the last two years, face-to-face interactions have drastically changed worldwide, because of the COVID-19 pandemic: the persistent use of masks has had the advantage of reducing viral transmission, but it has also had the cost of impacting on the perception and recognition of social information from faces, especially emotions. To assess the cerebral counterpart to this condition, we carried out an EEG experiment, extracting Event-Related Potentials (ERPs) evoked by emotional faces with and without surgical masks. Besides the expected impairment in emotion recognition in both accuracy and response times, also the classical face-related ERPs (N170 and P2) are altered by the presence of surgical masks. Importantly, the effect is stronger in individuals with a lower daily exposure to masks, suggesting that the brain must adapt to an extra constraint in decoding social input, due to masks hiding crucial facial information.

Research on the effect of generative adversarial network based on wavelet transform hidden Markov model on face creation and classification

Abstract Identity authentication and identification as the main activities in the modern human daily life, in the development of social economy and technological innovation of science and technology, information security and public security and other fields of identity recognition technology put forward higher request, not only to accurately record the relevant data information, and use of advanced technology concept advanced authentication technology is put forward. Knowing the living habits of current social residents, they need to choose appropriate ways to prove their identity, whether they enter the computer system or participate in financial services. For example, passwords, keys, ID cards and other contents are traditional means of identity authentication. As the reliability of traditional identity authentication means is getting lower and lower in today’s social network environment, in order to meet the needs of increasingly innovative network platforms and enhance the security and reliability of identity authentication technology, researchers propose to use biometric identification, among which face recognition is the most common. This recognition method is more direct and effective than palmprint, retina, fingerprint and so on, and occupies an important position in the current biometric research topic. After understanding the application of hidden Markov model (HMM) based on wavelet transform and its improved model in the field of face authentication, this paper analyzes the influence of various observation vector optimization methods on the authentication probability, and proposes a dynamic threshold method combined with the authentication model, in order to obtain a better authentication probability. The final design and implementation of the face information as the core of the identity authentication system. The improved hidden Markov model can effectively represent the correlation between face organs, so it has a positive role in the application of face modeling and authentication technology.

Face Spoofing, Age, Gender and Facial Expression Recognition Using Advance Neural Network Architecture-Based Biometric System.

Nowadays, the demand for soft-biometric-based devices is increasing rapidly because of the huge use of electronics items such as mobiles, laptops and electronic gadgets in daily life. Recently, the healthcare department also emerged with soft-biometric technology, i.e., face biometrics, because the entire data, i.e., (gender, age, face expression and spoofing) of patients, doctors and other staff in hospitals is managed and forwarded through digital systems to reduce paperwork. This concept makes the relation friendlier between the patient and doctors and makes access to medical reports and treatments easier, anywhere and at any moment of life. In this paper, we proposed a new soft-biometric-based methodology for a secure biometric system because medical information plays an essential role in our life. In the proposed model, 5-layer U-Net-based architecture is used for face detection and Alex-Net-based architecture is used for classification of facial information i.e., age, gender, facial expression and face spoofing, etc. The proposed model outperforms the other state of art methodologies. The proposed methodology is evaluated and verified on six benchmark datasets i.e., NUAA Photograph Imposter Database, CASIA, Adience, The Images of Groups Dataset (IOG), The Extended Cohn-Kanade Dataset CK+ and The Japanese Female Facial Expression (JAFFE) Dataset. The proposed model achieved an accuracy of 94.17% for spoofing, 83.26% for age, 95.31% for gender and 96.9% for facial expression. Overall, the modification made in the proposed model has given better results and it will go a long way in the future to support soft-biometric based applications.

Vulnerability in Financial Regulation: The Case of SMEs

SMEs are the driving force of economies. For many years, this supported, somewhat ironically, the neglect in designing a coherent regulatory framework to ensure their fair treatment. But the reality is that many SMEs face information asymmetries, lack resources and negotiation power and in the absence of regulatory protection are exposed to harm. In recent years, mounting ad-hoc, eclectic responses have mushroomed to address various aspects of appropriate conduct standards, dispute resolution and accountability. While these mechanisms allow for adaptability and dynamism, they may prove to be inadequate to achieve the FCA’s consumer protection objectives. This article proposes to broaden the application of vulnerability, which was initially designed with natural persons in mind, to guide the fair treatment of SMEs. It argues that expanding the application of vulnerability to SMEs would reflect the hybrid nature of this business model which is often akin to that of individual consumers. Conduct of business, Vulnerability, SMEs, FCA perimeter, Regulated activities, Commercial lending, Industry codes of conduct, Senior Managers and Certification Regime, Dispute resolution and redress, The Financial Markets Test Case Scheme, Business Lending Standards