Face Images Research Articles

Superposición de miradas en la reconstrucción cráneo-facial forense: El rostro recreado y el rostro recordado.

In the event of emergencies or mass disaster scenarios, when it is not possible to identify human skeletal remains based on scientific evidence (as DNA), and only the testimony of the victims’ relatives is available, a possible alternative is to apply the forensic craniofacial reconstruction method. It consists in recreate, from an unknown person’ skull, a facial image of their face, with the aim of being identified by witnesses. Based on bibliographic review and the author’s experience in the field, this investigation explores the recognition mechanics behind the search for coincidences, between the recreated face and the face that persists in the witnesses’ memory.

PDGrad: Guiding Diffusion Model for Reference-Based Blind Face Restoration with Pivot Direction Gradient Guidance

Reference-based blind face restoration (RefBFR) has gained considerable attention because it utilizes additional reference images to restore facial images in situations where the degradation is caused by unknown factors, making it particularly useful in real-world applications. Recently, guided diffusion models have demonstrated exceptional performance in this task without requiring training. They achieve this by integrating gradients of the losses where each loss reflects the different desired properties of the additional external images. However, these approaches fail to consider potential conflicts between gradients of multiple losses, which can lead to sub-optimal results. To address this issue, we introduce Pivot Direction Gradient guidance (PDGrad), a novel gradient adjustment method for RefBFR within a guided diffusion framework. To this end, we first define the loss function based on both low-level and high-level features. For loss at each feature level, both the coarsely restored image and the reference image are fully integrated. In cases of conflicting gradients, a pivot gradient is established for each level and other gradients are aligned to it, ensuring that the strengths of both images are maximized. Additionally, if the magnitude of the adjusted gradient exceeds that of the pivot gradient, it is adaptively scaled according to the ratio between the two, placing greater emphasis on the pivot. Extensive experimental results on the CelebRef-HQ dataset show that the proposed PDGrad significantly outperforms competitive approaches both quantitatively and qualitatively.

Learning face super-resolution through identity features and distilling facial prior knowledge

Deep learning techniques in electronic surveillance have shown impressive performance for super-resolution (SR) of captured low-quality face images. Most of these techniques adopt facial priors to improve the feature details in the resultant super-resolved images. However, the estimation of facial priors from the captured low-quality images is often inaccurate in real-life situations because of their tiny, noisy, and blurry nature. Thus, the fusion of such priors badly affects the performance of these models. Therefore, this work presents a teacher–student-based face SR framework that efficiently preserves the personal facial structure information in the super-resolved faces. In the proposed framework, the teacher network exploits the facial heatmap-based ground-truth-prior to learn the facial structure that is utilized by the student network. The student network is trained with the identity feature loss for maintaining the identity and facial structure information in reconstructed high-resolution (HR) face images. The performance of the proposed framework is evaluated by conducting the experimental study on standard datasets namely CelebA-HQ and LFW face. The experimental results reveal that the proposed technique conquers the existing methods for the face SR task.

Spatiotemporal hierarchies of face representation in the human ventral temporal cortex

In this study, we examined the relatively unexplored realm of face perception, investigating the activities within human brain face-selective regions during the observation of faces at both subordinate and superordinate levels. We recorded intracranial EEG signals from the ventral temporal cortex in neurosurgical patients implanted with subdural electrodes during viewing of face subcategories (human, mammal, bird, and marine faces) as well as various non-face control stimuli. The results revealed a noteworthy correlation in response patterns across all face-selective areas in the ventral temporal cortex, not only within the same face category but also extending to different face categories. Intriguingly, we observed a systematic decrease in response correlation coupled with an increased response onset time from human face to mammalian face, bird face and marine faces. Our result aligns with the notion that distinctions at the basic level category (e.g., human face versus non-human face) emerges earlier than those at the superordinate level (e.g., animate versus inanimate). This indicates response gradient in the representation of facial images within human face-sensitive regions, transitioning progressively from human faces to non-face stimuli. Our findings provide insights into spatiotemporal dynamic of face representations which varies spatially and at different timescales depending on the face subcategory represented.

Considering How Machine‐Learning Algorithms (Re)produce Social Biases in Generated Faces

ABSTRACTAdvances in computer science–specifically in the development and use of generative machine learning–have provided powerful new tools for psychologists to create synthetic human faces as stimuli, which ultimately provide high‐quality photorealistic face images that have many advantages, including reducing typical ethical and privacy concerns and generating face images from minoritized communities that are typically underrepresented in existing face databases. However, there are a number of ways that using machine learning‐based face generation and manipulation software can introduce bias into the research process, thus threatening the validity of studies. The present article provides a summary of how one class of recently popular algorithms for generating faces–generative adversarial networks (GANs)—works, how we control GANs, and where biases (with a particular focus on racial biases) emerge throughout these processes. We discuss recommendations for mitigating these biases, as well as how these concepts manifest in similar modern text‐to‐image algorithms.

Experimental Manipulation of the Bilateral Posterior Parietal Cortex Strengthens Associative Memory in Healthy Participants: A Continuous Theta-burst Stimulation.

To test whether targeting left and right posterior parietal cortex (PPC) with continuous theta-burst stimulation (cTBS) in healthy adults would strengthen associative memory (AM) performance. This study consisted of two experiments (a behavioral experiment and a formal experiment during each of the two experimental sessions). In Experiment 1, 18 adults (one male, age = 22.83 ± 3.92 years) were included in the behavioral phase and 18 adults (seven males, age = 40.11 ± 12.27 years) in the stimulation phase. There were 120 neutral facial images paired with 120 two-character nouns and then divided into six test versions (10 male faces and 10 female faces paired with 20 different nouns were considered as one version). In the behavioral experiment, participants were tested by six-version tests to assess memory materials, and in the formal experiment, participants' face-word AM performance was measured by certified tests based on a cued recall paradigm. Furthermore, 30 adults (seven males, age = 20.97 ± 1.85 years) and 15 adults (five males, age = 22.27 ± 1.29 years) participated in Experiment 2, respectively. Stimuli and procedure were the same as in Experiment 1, but the AM test was based on a forced-choice paradigm. Experiment 1 did not yield anticipated outcomes; Experiment 2 showed that cTBS of left and right PPC strengthened the AM performance compared with the control condition. In conclusion, cTBS to left and right PPC improved AM in healthy adults, which provided further experimental evidence for strengthening AM by cTBS.

Determinants of shared and idiosyncratic contributions to judgments of faces.

Recent work has shown that the idiosyncrasies of the observer can contribute more to the variance of social judgments of faces than the features of the faces. However, it is unclear what conditions determine the relative contributions of shared and idiosyncratic variance. Here, we examine two conditions: type of judgment and diversity of face stimuli. First, we show that for simpler, directly observable judgments that are consistent across observers (e.g., masculinity) shared exceeds idiosyncratic variance, whereas for more complex and less directly observable judgments (e.g., trustworthiness), idiosyncratic exceeds shared variance. Second, we show that judgments of more diverse face images increase the amount of shared variance. Finally, using machine-learning methods, we examine how stimulus (e.g., incidental emotion resemblance, skin luminosity) and observer variables (e.g., race, age) contribute to shared and idiosyncratic variance of judgments. Overall, our results indicate that an observer's age is the most consistent and best predictor of idiosyncratic variance contributions to face judgments measured in the current research. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

A modified deep learning method for Alzheimer’s disease detection based on the facial submicroscopic features in mice

Alzheimer’s disease (AD) is a chronic disease among people aged 65 and older. As the aging population continues to grow at a rapid pace, AD has emerged as a pressing public health issue globally. Early detection of the disease is important, because increasing evidence has illustrated that early diagnosis holds the key to effective treatment of AD. In this work, we developed and refined a multi-layer cyclic Residual convolutional neural network model, specifically tailored to identify AD-related submicroscopic characteristics in the facial images of mice. Our experiments involved classifying the mice into two distinct groups: a normal control group and an AD group. Compared with the other deep learning models, the proposed model achieved a better detection performance in the dataset of the mouse experiment. The accuracy, sensitivity, specificity and precision for AD identification with our proposed model were as high as 99.78%, 100%, 99.65% and 99.44%, respectively. Moreover, the heat maps of AD correlation in the facial images of the mice were acquired with the class activation mapping algorithm. It was proven that the facial images contained AD-related submicroscopic features. Consequently, through our mouse experiments, we validated the feasibility and accuracy of utilizing a facial image-based deep learning model for AD identification. Therefore, the present study suggests the potential of using facial images for AD detection in humans through deep learning-based methods.

사전학습 모델 기반 발화 동영상 멀티 모달 감정 인식

Recently, as the demand for non-face-to-face counseling has rapidly increased, the need for emotion recognition technology that combines various aspects such as text, voice, and facial expressions is being emphasized. In this paper, we address issues such as the dominance of non-Korean data and the imbalance of emotion labels in existing datasets like FER-2013, CK+, and AFEW by using Korean video data. We propose methods to enhance multimodal emotion recognition performance in videos by integrating the strengths of image modality with text modality. A pre-trained model is used to overcome the limitations caused by small training data. A GPT-4-based LLM model is applied to text, and a pre-trained model based on VGG-19 architecture is fine-tuned to facial expression images. The method of extracting representative emotions by combining the emotional results of each aspect extracted using a pre-trained model is as follows. Emotion information extracted from text was combined with facial expression changes in a video. If there was a sentiment mismatch between the text and the image, we applied a threshold that prioritized the text-based sentiment if it was deemed trustworthy. Additionally, as a result of adjusting representative emotions using emotion distribution information for each frame, performance was improved by 19% based on F1-Score compared to the existing method that used average emotion values for each frame.

BrainSim: AI-Driven Brain MRI Simulation for Alzheimer’s Disease Diagnosis

Alzheimer's Disease, a progressive neurodegenerative disorder with no cure, presents a formidable challenge to global healthcare. The simulation of brain states, encompassing both rejuvenation and aging, aids clinicians in understanding disease progression and early detection. Recent advances in deep adversarial neural networks, effective in generating age-varied facial images, are now applied to brain MRI simulations across different time states. However, existing methods for brain MRI synthesis predominantly focus on aging simulation, lacking rejuvenation capabilities, and relying heavily on longitudinal data. Access to rejuvenated brain scans is essential as it can help researchers track the structural changes and biomarkers in the early stage of AD, facilitating AD research and personalized treatments. Additionally, previous methods are often 2D-based, failing to capture complex 3D spatial information obtained by 3D scans. To overcome these limitations, I propose BrainSim, a novel longitudinal brain MRI synthesis framework. Specifically, BrainSim leverages a bidirectional cycle-consistent generative neural network to generate rejuvenated and aged MRI scans simultaneously using cross-sectional scans only. BrainSim incorporates a 3D conditional U-Net as its fundamental model, facilitating the direct generation of 3D MRI scans conditioned on the subject's health state and sex. BrainSim was evaluated against benchmark models using longitudinal data and a pre-trained age predictor to assess the quality of generated images. Experiments using the ADNI dataset show BrainSim's state-of-the-art performance in brain aging and rejuvenation tasks, marking significant advancements in MRI synthesis for Alzheimer's research and drug development.

Enhancing Biometric Security with Bimodal Deep Learning and Feature-level Fusion of Facial and Voice Data

Recent research in biometric technologies underscores the benefits of multimodal systems that use multiple traits to enhance security by complicating the replication of samples from genuine users. To address this, we present a bimodal deep learning network (BDLN or BNet) that integrates facial and voice modalities. Voice features are extracted using the SincNet architecture, and facial image features are obtained from convolutional layers. Proposed network fuses these feature vectors using either averaging or concatenation methods. A dense connected layer then processes the combined vector to produce a dual-modal vector that encapsulates distinctive user features. This dual-modal vector, processed through a softmax activation function and another dense connected layer, is used for identification. The presented system achieved an identification accuracy of 99% and a low equal error rate (EER) of 0.13% for verification. These results, derived from the VidTimit and BIOMEX-DB datasets, highlight the effectiveness of the proposed bimodal approach in improving biometric security.

P1 evoked by facial expression images is enhanced in Parkinson’s disease patients with depressive symptoms

IntroductionDepressive symptoms are most common non-motor symptoms in Parkinson’s disease (PD), which is often overlooked due to absence of rapid and objective diagnostic biomarkers. Electroencephalography (EEG)-based event-related potentials (ERPs) is commonly used to assess emotional processes. The aim of this study was to investigate changes in ERPs in PD patients exhibiting depressive symptoms and to provide a reliable biomarker for assisting in the diagnosis of PD with depressive symptoms.MethodsWe conducted a case–control study involving 30 PD patients with (dPD group) or without depressive symptoms (nPD group) and 13 age matched healthy controls (HC). We recorded EEG of the patients during the emotional picture stimulation task and analyzed the difference in the early ERPs potentials (P1, N170, early posterior negativity) and their correlation with the severity of symptoms in PD patients.ResultsOur results found that P1 amplitude in the occipital region of the dPD group in response to emotional faces was significantly higher than that of nPD and HC group, and it was positively correlated with severity of depressive symptoms in PD patients.ConclusionOur study shows that facial expression-induced enhancement of P1 amplitude can be utilized as a rapid and objective indicator to screen for depressive symptoms in PD.

ANALYSIS OF CANNY EDGE DETECTION METHOD FOR FACIAL RECOGNITION IN DIGITAL IMAGE PROCESSING

The document explores the application of the Canny Edge Detection method in facial recognition systems, specifically for identifying edge patterns in digital images. In the context of technological advancements, the focus is on enhancing data processing through efficient image analysis techniques. The research addresses how different edge detection methods, including Roberts, Prewitt, Sobel, and Canny, function, with the latter being highlighted for its superior ability to minimize error and deliver accurate edge detection results. The study outlines the development of a system designed to identify optimal edge detection parameters using the Canny method, focusing on facial images captured from the front. The system is limited to edge identification in such images, and performance is measured using a correlation coefficient. The process involves several technical steps, such as pre-processing the image (grayscale conversion and noise reduction) and using Gaussian filters and hysteresis thresholding to refine the detection. The research's ultimate aim is to optimize Canny's performance for identifying edges, contributing to advancements in facial recognition technology.

UK patients face imaging cancellations amid shortage of radioactive isotope.

UK patients face imaging cancellations amid shortage of radioactive isotope.

Generative technology for human emotion recognition: A scoping review

Affective computing stands at the forefront of artificial intelligence (AI), seeking to imbue machines with the ability to comprehend and respond to human emotions. Central to this field is emotion recognition, which endeavors to identify and interpret human emotional states from different modalities, such as speech, facial images, text, and physiological signals. In recent years, important progress has been made in generative models, including Autoencoder, Generative Adversarial Network, Diffusion Model, and Large Language Model. These models, with their powerful data generation capabilities, emerge as pivotal tools in advancing emotion recognition. However, up to now, there remains a paucity of systematic efforts that review generative technology for emotion recognition. This survey aims to bridge the gaps in the existing literature by conducting a comprehensive analysis of over 330 research papers until June 2024. Specifically, this survey will firstly introduce the mathematical principles of different generative models and the commonly used datasets. Subsequently, through a taxonomy, it will provide an in-depth analysis of how generative techniques address emotion recognition based on different modalities in several aspects, including data augmentation, feature extraction, semi-supervised learning, cross-domain, etc. Finally, the review will outline future research directions, emphasizing the potential of generative models to advance the field of emotion recognition and enhance the emotional intelligence of AI systems.

Audio-Driven Facial Animation with Deep Learning: A Survey

Audio-driven facial animation is a rapidly evolving field that aims to generate realistic facial expressions and lip movements synchronized with a given audio input. This survey provides a comprehensive review of deep learning techniques applied to audio-driven facial animation, with a focus on both audio-driven facial image animation and audio-driven facial mesh animation. These approaches employ deep learning to map audio inputs directly onto 3D facial meshes or 2D images, enabling the creation of highly realistic and synchronized animations. This survey also explores evaluation metrics, available datasets, and the challenges that remain, such as disentangling lip synchronization and emotions, generalization across speakers, and dataset limitations. Lastly, we discuss future directions, including multi-modal integration, personalized models, and facial attribute modification in animations, all of which are critical for the continued development and application of this technology.

Automated System for Credibility Diagnosis of Forged Facial Images Using Ensemble Deep Learning and Explainable AI

Automated System for Credibility Diagnosis of Forged Facial Images Using Ensemble Deep Learning and Explainable AI

New Insights on the Turin Shroud’s Body Image: Face Image at Different Wavelengths and its Double Superficiality

Various images of the face of the Turin Shroud Man, acquired at different wavelengths, from the near infrared region to the ultraviolet, have been studied and compared. A correlation as a function of the wavelength, between the penetration depth in the fabric of the incident light and the anatomic details visible on the images, is discussed based on the physical properties of linen threads and light. In addition, the backside of the Turin Shroud, in correspondence of the region of the face, has been examined, evidencing the possible presence of a second superficial image impressed on the backside. Notwithstanding the high level of scientific knowledge today reached, there is no known physical/chemical process which allows to explain all the properties of the Turin Shroud’s body image. According to our scientific knowledge, the corpse of a dead man cannot produce an energy capable to imprint on a linen cloth an image with all the microscopical and macroscopical properties discovered by analyzing the body image of the Turin Shroud, which has not yet been reproduced in any laboratory in the world. According to faith the corpse of a living Man can do it, during the resurrection, assuming a different state of matter. With this respect, the Turin Shroud can be considered as a two-thousand-old relic witnessing to the humanity, just in the age of science, the reasonableness of the faith in the resurrection.

Personalized Super Resolution with Face Prior

Face Super-Resolution (FSR) is a critical technology in computer vision that aims to reconstruct high-resolution facial images from low-resolution inputs. Despite recent advancements, current FSR methods struggle to accurately reconstruct personalized and detailed features. This paper proposes a novel FSR approach that addresses these challenges through a personalized feature extraction and fusion framework. Our method integrates a U-Net based downsampling mechanism to extract individual- specific features from high-resolution reference images, which are then fused with a pre-trained Generative Adversarial Network (GAN) for enhanced reconstruction. We introduce a comprehensive loss function that combines reconstruction, adversarial, facial component, and identity preservation losses to guide the learning process. Extensive experiments on the augmented FFHQ dataset demonstrate that our approach significantly improves the reconstruction of rich facial features, particularly for older individuals, outperforming existing state-of-the-art methods in both quantitative metrics and qualitative visual assessments.

Different Pathways of Skin Aging: Objective Instrumental Evaluation

Background/Objectives: Hypertrophic and atrophic skin aging represent two distinct phenotypes: hypertrophic aging is marked by deep wrinkles and a leathery texture, whereas atrophic aging is characterized by overall skin thinning, increased vascularity, and a higher risk of non-melanoma skin cancers. This study aims to elucidate the characteristics and differences between hypertrophic and atrophic facial aging subtypes using two non-invasive imaging devices: VISIA® and dynamic optical coherence tomography (D-OCT). Methods: We retrospectively evaluated patients who had presented to the outpatient dermatological clinic at Policlinico Umberto I hospital in Rome, Italy for a non-invasive facial imaging check-up. We included 40 patients aged 60–75 who were imaged with VISIA® and dynamic optical coherence tomography (D-OCT). Based on the number of UV spots and amount of red found on VISIA®, subjects were grouped into four subgroups (PIGM, RED, CONTROL, PIGM + RED), and trends among them were analyzed. Results: We found a strong correlation between VISIA® red area scores and D-OCT vascular density at 300 µm depth, confirming VISIA®’s effectiveness for assessing facial vascularity. Wrinkle count was highest in areas with UV spots, particularly in the PIGM and PIGM + RED groups. Conversely, low attenuation coefficients and dermal density were observed in regions with low UV spots but high red areas. Intermediate subgroups (CONTROL and PIGM + RED) displayed varying parameters. Conclusions: Non-invasive imaging devices are effective in evaluating facial aging and distinguishing between aging subtypes. This study identified two intermediate aging types in addition to the hypertrophic and atrophic subtypes.