Face Descriptor Research Articles

Kinship verification in childhood images using curvelet transformed features

Kinship verification poses a formidable challenge due to significant age disparities between parents and children, resulting in diminished facial resemblances and consequently reduced model accuracy. In response, we introduce a novel methodology focusing on childhood imagery, wherein images of both parents and children during their early stages are leveraged, leading to more pronounced feature similarities. Our approach introduces a novel feature descriptor utilizing the curvelet transform (CLT) to extract facial descriptors from sub-bands, effectively capturing unique facial features. Additionally, we employ a convolutional neural network (CNN) to extract texture information, further enhancing the discriminative power of our method. Statistical measures are subsequently applied to evaluate image similarity, with a dedicated training phase utilized to determine an optimal threshold for kinship classification during the testing phase. Extensive evaluations conducted across multiple databases, including KINFACEW-I, II, FIW, TSKINFACE, UBKinface, and childhood image dataset, showcase the superior performance of our proposed model compared to existing state-of-the-art approaches. Our methodology not only enhances kinship verification accuracy but also underscores the significance of childhood images in mitigating age-related challenges within the domain.

The Translation of Body-part Rhetoric in Romeo and Juliet: Take the Example of Facial Terms

In Shakespeare’s Romeo and Juliet, numerous references to the human body are intertwined with a rich array of rhetorical devices including personification, simile, metaphor, metonymy, and synecdoche. Metaphorical rhetoric is a hallmark of Shakespearean language, often used to depict sensory experiences, symbolize objects and emotions, and flesh out characters. However, due to cognitive disparities between Western and Chinese cultures, the same rhetorical themes may be expressed with different objects across cultures. As a result, translators must employ various strategies to bridge these gaps. This study aims to examine the cognitive differences underlying body-related rhetoric, particularly facial descriptions, in five different translations of Romeo and Juliet spanning different periods. The goal is to analyze the translation techniques and methodologies employed by translators to address these cultural disparities.

The relevance and accuracy of an AI algorithm-based descriptor on 23 facial attributes in a diverse female US population.

The response of AI in situations that mimic real life scenarios is poorly explored in populations of high diversity. To assess the accuracy and validate the relevance of an automated, algorithm-based analysis geared toward facial attributes devoted to the adornment routines of women. In a cross-sectional study, two diversified groups presenting similar distributions such as age, ancestry, skin phototype, and geographical location was created from the selfie images of 1041 female in a US population. 521 images were analyzed as part of a new training dataset aimed to improve the original algorithm and 520 were aimed to validate the performance of the AI. From a total 23 facial attributes (16 continuous and 7 categorical), all images were analyzed by 24 make-up experts and by the automated descriptor tool. For all facial attributes, the new and the original automated tool both surpassed the grading of the experts on a diverse population of women. For the 16 continuous attributes, the gradings obtained by the new system strongly correlated with the assessment made by make-up experts (r ≥ 0.80; p<0.0001) and supported by a low error rate. For the seven categorical attributes, the overall accuracy of the AI-facial descriptor was improved via enrichment of the training dataset. However, some weaker performance in spotting specific facial attributes were noted. In conclusion, the AI-automatic facial descriptor tool was deemed accurate for analysis of facial attributes for diverse women although some skin complexion, eye color, and hair features required some further finetuning.

The signaling dimension in generalized probabilistic theories

The signaling dimension of a given physical system quantifies the minimum dimension of a classical system required to reproduce all input/output correlations of the given system. Thus, unlike other dimension measures - such as the dimension of the linear space or the maximum number of (jointly or pairwise) perfectly discriminable states - which examine the correlation space only along a single direction, the signaling dimension does not depend on the arbitrary choice of a specific operational task. In this sense, the signaling dimension summarizes the structure of the entire set of input/output correlations consistent with a given system in a single scalar quantity. For quantum theory, it was recently proved by Frenkel and Weiner in a seminal result that the signaling dimension coincides with the Hilbert space dimension. Here, we derive analytical and algorithmic techniques to compute the signaling dimension for any given system of any given generalized probabilistic theory. We prove that it suffices to consider extremal measurements with ray-extremal effects, and we bound the number of elements of any such measurement in terms of the linear dimension. For systems with a finite number of extremal effects, we recast the problem of characterizing the extremal measurements with ray-extremal effects as the problem of deriving the vertex description of a polytope given its face description, which can be conveniently solved by standard techniques such as the double description algorithm. For each such measurement, we recast the computation of the signaling dimension as a linear program, and we propose a combinatorial branch and bound algorithm to reduce its size. We apply our results to derive the extremal measurements with ray-extremal effects of a composition of two square bits (or squits) and prove that their signaling dimension is five, even though each squit has a signaling dimension equal to two.

A face retrieval technique combining large models and artificial neural networks

SummaryMultimodal sentiment analysis is a popular research direction in the field of affective computing. It extends unimodal‐based sentiment analysis to the environment based on multimodal information exchange. Face retrieval is the most critical technology in the current multimodal sentiment analysis field. Traditional methods for face retrieval rely on large amounts of data to train the matching relationship between text and face images. This approach suffers from several issues, including high data acquisition costs, insufficient or poor quality training data, and high computational costs for training models. To address the aforementioned issues, this paper proposes a face retrieval technique that merges a large language model with a visual base model. This technique explores the use of zero samples for training, eliminating the need to collect data and train the model to achieve face retrieval. As a result, it significantly reduces the cost requirements of data and computational power. First, an accurate natural text of face description is generated using a large language model based on cue engineering based on face‐independent features. Second, the text and images are encoded using a visual base model and mapped into the same multidimensional space for matching. The experimental results indicate that this method performs well on the CelebA dataset. Extracting 31 different sets of face feature descriptions from the CelebA dataset for retrieval achieves 72% on top1 accuracy and 93% on top3 accuracy. Compared to traditional methods, the method proposed in this paper achieves considerable face retrieval accuracy without collecting text image pairs of data and without training the model.

Multi-level textual-visual alignment and fusion network for multimodal aspect-based sentiment analysis

Multimodal Aspect-Based Sentiment Analysis (MABSA) is an essential task in sentiment analysis that has garnered considerable attention in recent years. Typical approaches in MABSA often utilize cross-modal Transformers to capture interactions between textual and visual modalities. However, bridging the semantic gap between modalities spaces and addressing interference from irrelevant visual objects at different scales remains challenging. To tackle these limitations, we present the Multi-level Textual-Visual Alignment and Fusion Network (MTVAF) in this work, which incorporates three auxiliary tasks. Specifically, MTVAF first transforms multi-level image information into image descriptions, facial descriptions, and optical characters. These are then concatenated with the textual input to form a textual+visual input, facilitating comprehensive alignment between visual and textual modalities. Next, both inputs are fed into an integrated text model that incorporates relevant visual representations. Dynamic attention mechanisms are employed to generate visual prompts to control cross-modal fusion. Finally, we align the probability distributions of the textual input space and the textual+visual input space, effectively reducing noise introduced during the alignment process. Experimental results on two MABSA benchmark datasets demonstrate the effectiveness of the proposed MTVAF, showcasing its superior performance compared to state-of-the-art approaches. Our codes are available at https://github.com/MKMaS-GUET/MTVAF.

Sensitivity and Specificity of Qualitative Visual Field Tests for Screening Visual Hemifield Deficits in Right-Brain-Damaged Stroke Patients.

A timely detection of visual hemifield deficits (VHFDs; hemianopias or quadrantanopias) is critical for both the diagnosis and treatment of stroke patients. The present study determined the sensitivity and specificity of four qualitative visual field tests, including face description, confrontation tests (finger wiggle), and kinetic boundary perimetry, to screen large and dense VHFDs in right-brain-damaged (RBD) stroke patients. Previously, the accuracy of qualitative visual field tests was examined in unselected samples of patients with heterogeneous aetiology, in which stroke patients represented a very small fraction. Building upon existing tests, we introduced some procedural ameliorations (incl. a novel procedure for kinetic boundary perimetry) and provided a scoresheet to facilitate the grading. The qualitative visual field tests' outcome of 67 consecutive RBD stroke patients was compared with the standard automated perimetry (SAP; i.e., reference standard) outcome to calculate sensitivity and specificity, as well as positive and negative predictive values (PPV and NPV), both for each individual test and their combinations. The face description test scored the lowest sensitivity and NPV, while the kinetic boundary perimetry scored the highest. No test returned false positives. Combining the monocular static finger wiggle test (by quadrants) and the kinetic boundary perimetry returned the highest sensitivity and specificity, in line with previous studies, but with higher accuracy (100% sensitivity and specificity). These findings indicate that the combination of these two tests is a valid approach with RBD stroke patients, prompting referral for a formal visual field examination, and representing a quick, easy-to-perform, and inexpensive tool for improving their care and prognosis.

An Exploration of Face Recognition Methods Based on LBP Algorithm and PCA Analysis

Local Binary Pattern is an operator that can be effectively used for facial description, and its application field is relatively wide, which has made great contribution to the research and technical support related to face recognition. The traditional local texture feature extraction method of LBP operator is relatively single and cannot fully synthesize the problem of neighborhood correlation. Therefore, this paper proposes a face recognition method based on the combination of LBP algorithm and PCA principal component analysis method for the above problems. Through the application of this method, it can effectively weaken the influence of noise on the results and show the basic characteristic situation of the sub-block region, and the experiments of this method have confirmed that, compared with the use of PCA, LBP and other methods alone, the method in this study has a significant improvement in the recognition rate.

An investigation into the effectiveness of using acoustic touch to assist people who are blind.

Wearable smart glasses are an emerging technology gaining popularity in the assistive technologies industry. Smart glasses aids typically leverage computer vision and other sensory information to translate the wearer's surrounding into computer-synthesized speech. In this work, we explored the potential of a new technique known as "acoustic touch" to provide a wearable spatial audio solution for assisting people who are blind in finding objects. In contrast to traditional systems, this technique uses smart glasses to sonify objects into distinct sound auditory icons when the object enters the device's field of view. We developed a wearable Foveated Audio Device to study the efficacy and usability of using acoustic touch to search, memorize, and reach items. Our evaluation study involved 14 participants, 7 blind or low-visioned and 7 blindfolded sighted (as a control group) participants. We compared the wearable device to two idealized conditions, a verbal clock face description and a sequential audio presentation through external speakers. We found that the wearable device can effectively aid the recognition and reaching of an object. We also observed that the device does not significantly increase the user's cognitive workload. These promising results suggest that acoustic touch can provide a wearable and effective method of sensory augmentation.

End-to-end convolutional neural network for automatic encoding facial descriptor (N-CNN) in the diagnosis of intrauterine distress

Background. Existing methods for studying intrauterine distress, despite their prevalence, still have their limitations, so studying and assessment of fetal movements during ultrasound diagnostics can become a convenient and affordable additional tool for diagnosing this pathological condition. The aim of the study. To assess the prevalence and diagnostic significance of a known set of fetal facial movements for the timely determination of intrauterine distress. Methods. This prospective single-center study included 225 fetuses of a gestational age from 32 to 40 weeks. The FIGO chart was used as fitting criteria of intrauterine distress. The assessment of facial movements in all fetuses was carried out using the BabyFACS technique, where the action unit (AU) used for the assessment; its coding is carried out in strict accordance with the chart of motor descriptors (MD). Statistical data processing was carried out using SPSS Statistics 20 (IBM Corp., USA). The Mann – Whitney test was used as the main statistical parameter, where a threshold level of 0.05 was chosen to interpret the p-tests value. Results. Despite the occurrence of AU1, AU2, AU3, AU4 in both groups, these MDs were recorded in the group with confirmed distress (p = 0.00001). Facial units such as AU9 and AU20 were found only in children with intrauterine distress, which, in the total amount of the MD assessment, can be considered one of the main search signs that specialists should first of all pay attention to. All motor descriptors showed high positive predictive value and diagnostic sensitivity, with the highest results registered for AU9 and AU20. Conclusion. Assessment of facial units during ultrasound diagnostics can be a convenient tool as an additional diagnosis of the development of intrauterine distress and requires further study.

A Comparative Analysis on the Aging Recognition and Facial Description in Poetry of Han-yu and Bai-ju-yi

A Comparative Analysis on the Aging Recognition and Facial Description in Poetry of Han-yu and Bai-ju-yi

Evaluating the utility of facial identification information: Accuracy versus precision

Facial identification evidence obtained from eyewitnesses, such as person descriptions and facial composites, plays a fundamental role in criminal investigations and is regularly regarded as valuable evidence for apprehending and prosecuting perpetrators. However, the reliability of such facial identification information is often queried. Person descriptions are frequently reported in the research literature as being vague and generalisable, whilst facial composites often exhibit a poor likeness to an intended target face. This raises questions regarding the accuracy of eyewitness facial identification information and its ability to facilitate efficient searches for unknown perpetrators of crimes. More specifically, it questions whether individuals, blind to the appearance of a perpetrator of a crime (i.e. the public), can correctly identify the intended target face conveyed by facial identification information recalled from eyewitness memory, and which of the two traditional facial identification formats would be better relied upon by law enforcement to enable such searches. To investigate this, in the current study (N=167) we employed two metrics – identification accuracy and identification precision – to assess the utility of different formats of eyewitness facial identification information in enabling participants to correctly identify an unknown target face across three different formats: facial descriptions, facial composites and computer-generated description-based synthetic faces. A statistically significant main effect for the format of facial identification information on identification accuracy (p&lt;0.001) was found, with a higher target identification accuracy yielded by facial descriptions in comparison to composites and description-based synthetic faces. However, the reverse relationship was established for identification precision, where composites and description-based synthetic faces enabled significantly greater precision in the narrowing down of a suspect pool than did facial descriptions, but did not necessarily result in the retainment of the intended target face (p&lt;0.001). Significance: This study highlights the relative importance of person descriptions in being as effective as, if not better than, facial composites in allowing for accurate identifications when solely relying upon eyewitness facial identification information to facilitate the search for unknown perpetrators. We introduce the metric of identification precision to evaluate the utility of facial identification information obtained by eyewitnesses. The study provides a novel approach to directly model facial composites based on a person description using traditional fourth-generation composite systems, thus producing a computer-generated description-based synthetic face that resembles a target face observed by an eyewitness.

DOPING AMONG MINNOWS IN GHANA: IS ELIGIBILITY THE MAIN ISSUE?

Despite the use of drugs among amateur athletes linked to inadvertent doping, there is a gap in the literature about other factors that prompted doping behaviour. The present study examined if eligibility to participate in sports competitions is the main cause of doping among young athletes in Ghana. To achieve this, an interpretative qualitative research design approach was adopted. Purposive and snowballing sampling techniques were employed to recruit 10 former basic school student-athletes who admitted to using drugs to participate in school competitions. Semi-structured interviews were the instruments used to collect the data to answer the research questions. Thematic analysis was employed after the data have been transcribed verbatim. The findings of the study revealed that students take performance-enhancing drugs to “become eligible to participate in the competitions”, “to improve stamina”, and “gives them extra energy to perform without getting tired”. Again, it was found that the former student-athletes were unaware of the effects of taking the drugs. The study further exposed some effects of performance-enhancing drugs which included addictiveness and physiological health challenges on the individual. The study recommends that stakeholders should educate minnows on the adverse effects of taking drugs without a doctor’s prescription. Again, age should be used when organising competitions for student-athletes at the basic school level rather than weight, height and facial description.&lt;p&gt; &lt;/p&gt;&lt;p&gt;&lt;strong&gt; Article visualizations:&lt;/strong&gt;&lt;/p&gt;&lt;p&gt;&lt;img src="/-counters-/soc/0025/a.php" alt="Hit counter" /&gt;&lt;/p&gt;

BESRGAN: Boundary equilibrium face super‐resolution generative adversarial networks

AbstractExisting Generative Adversarial Networks (GAN)‐based face hallucination algorithms are hard to control the face fidelity of the generated samples, and easily generate flawed faces with unfavourable artefacts and distortions. To address this problem, the authors propose a fidelity‐controllable face super‐resolution (FSR) network boundary equilibrium face super‐resolution generative adversarial networks (BESRGAN), a fidelity ratio is introduced in their network to control how much the adversarial effect the discriminator is put on the generator; therefore, the authors’ network better trades off the objective and perceptual quality. Additionally, the authors design an equilibrium perceptual discriminator to match the perception loss distributions. Under the equilibrium constraint, the discriminator pays more attention to learning fine‐grained feature statistics of ground truths, and further guides the generator to produce photo‐realistic faces, especially in terms of facial textures. Moreover, the authors propose a novel channel‐spatial attention module (CSAM) to eliminate local distortions, by further fusing richer information from the facial prior knowledge and global high‐level facial descriptions. Extensive experiments illustrate that the authors’ approach preserves high pixel‐wise accuracy while achieving superior visual performance against state‐of‐the‐art methods. Specifically, the peak signal to noise ratio (PSNR) and structural similarity index (SSIM) of the authors’ proposed BESRGAN rise 0.64 dB and 0.02 for CelebA compared with one of the state‐of‐the‐art face super‐resolution (FSR) methods.

Learning Streamed Attention Network from Descriptor Images for Cross-Resolution 3D Face Recognition

In this article, we propose a hybrid framework for cross-resolution 3D face recognition which utilizes a Streamed Attention Network (SAN) that combines handcrafted features with Convolutional Neural Networks (CNNs). It consists of two main stages: first, we process the depth images to extract low-level surface descriptors and derive the corresponding Descriptor Images (DIs), represented as four-channel images. To build the DIs, we propose a variation of the 3D Local Binary Pattern (3DLBP) operator that encodes depth differences using a sigmoid function. Then, we design a CNN that learns from these DIs. The peculiarity of our solution consists in processing each channel of the input image separately, and fusing the contribution of each channel by means of both self- and cross-attention mechanisms. This strategy showed two main advantages over the direct application of Deep-CNN to depth images of the face; on the one hand, the DIs can reduce the diversity between high- and low-resolution data by encoding surface properties that are robust to resolution differences. On the other, it allows a better exploitation of the richer information provided by low-level features, resulting in improved recognition. We evaluated the proposed architecture in a challenging cross-dataset, cross-resolution scenario. To this aim, we first train the network on scanner-resolution 3D data. Next, we utilize the pre-trained network as feature extractor on low-resolution data, where the output of the last fully connected layer is used as face descriptor. Other than standard benchmarks, we also perform experiments on a newly collected dataset of paired high- and low-resolution 3D faces. We use the high-resolution data as gallery, while low-resolution faces are used as probe, allowing us to assess the real gap existing between these two types of data. Extensive experiments on low-resolution 3D face benchmarks show promising results with respect to state-of-the-art methods.

MISSING CHILD IDENTIFICATION AND ADOPTION OF THE CHILD FROM THE REMAINING CHILDREN DATABASE AFTER A TIME PERIOD

In India, countless children are reported missing every year. Among the missing child cases, a large percentage of children remain untraced. The enhancement of missing child identification is the adoption of the child from the remaining children database after a period Child welfare Centre is responsible for checking the parent's authenticity. In Adoption customers, after logging in to the parents, registered parents have to fill in the same child details that were filled in the registration form of the parents. The Convolutional Neural Network (CNN), a highly effective deep learning technique for image based applications is adopted here for face recognition. Face descriptors are extracted from the images using a pre-trained CNN model VGG-Face deep architecture. The images using a pre-trained CNN model VGG-Face deep architecture.

CAN THE COMBINATION OF FACIAL FEATURES ENHANCE THE PERFORMANCE OF FACE RECOGNITION?

The field of computer vision and pattern recognition has shown great interest in facial recognition due to its wide range of applications. These applications span across historical and genealogical research, forensic science, searching for missing family members, analyzing social media, automatically managing and annotating image databases, and identifying kinship relationships. This research paper aims to address the challenges associated with facial recognition by introducing two innovative approaches: Fusion-based Classifier Combination (FCC) and Sequential CNN Deep learning-based face recognition (S-CNN). In the first part of the study, we assess the effectiveness of three techniques: Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), and a hand-crafted learned technique called Compact Binary Facial Descriptors (CBFD). To overcome these challenges, we employ a classification step that utilizes a novel multi-classifier combination model. In the second part, we propose a novel method where we extract high-level features from multiple image regions treated as sequential data using ensemble of Convolutional Neural Networks (CNNs). These features are then fed into a Deep Neural Network (DNN) for facial recognition. The experimental results obtained from well-known face databases, including Labeled Faces in the Wild (LFW) and ORL, highlight the competitive performance of both the proposed multi-classifier combination model and the S-CNN deep learning model when compared to state-of-the-art methods .

Let's talk about faces: Identifying faces from verbal descriptions.

Face descriptions inform real-world identification decisions, for example when eyewitnesses describe criminal perpetrators. However, it is unclear how effective face descriptions are for identification. Here, we examined the accuracy of face identification from verbal descriptions, and how individual differences in face perception relate to producing and using descriptions for identification. In Study 1, participants completed a face communication task in pairs. Each participant saw a single face, and via verbal communication only, the pair decided if they were viewing the same person or different people. Dyads achieved 72% accuracy, compared to 81% when participants completed the task individually by matching face pairs side-by-side. Performance on the face communication and perceptual matching tasks were uncorrelated, perhaps due to low measurement reliability of the face communication task. In subsequent studies, we examined the abilities of face 'describers' (Study 2) and 'identifiers' separately (Study 3). We found that 'super-recognizers' - people with extremely high perceptual face identification abilities - outperformed controls in both studies. Overall, these results show that people can successfully describe faces for identification. Preliminary evidence suggests that this ability - and the ability use facial descriptions for identification - has some association with perceptual face identification skill.

Open-set face identification with automatic detection of out-of-distribution images

One of main issues in face identification is the lack of training data of specific type (bad quality image, varying scale or illumination, children/old people faces, etc.). As a result, the recogni-tion accuracy may be low for input images which are not similar to the majority of images in the dataset used to train the feature extractor. In this paper, we propose that this issue is dealt with by the automatic detection of such out-of-distribution data based on the addition of a preliminary stage of their automatic rejection using a special convolutional network trained using a set of rare data collected using various transformations. To increase the computational efficiency, the decision about the presence of a rare image is made on the basis of the same face descriptor that is used in the classifier. Experimental research confirmed the accuracy improvement of the proposed approach for several datasets of faces and modern neural network descriptors.

Morphologic analysis of the sublime tubercle: considerations in the approach to ulnar collateral ligament reconstruction.

Given the increased incidence of ulnar collateral ligament (UCL) injuries and the projected increase in reconstruction procedures, a robust understanding of the morphologic location of the sublime tubercle is paramount to anatomic reconstruction. There is limited research evaluating the morphology of the sublime tubercle of the proximal ulna in an anterior-to-posterior plane. Twenty-five computed tomography (CT) scans of intact proximal elbow joints for patients were selected using a de-identified database. Cases with history of fracture or surgical intervention to the elbow joint were excluded. These CT scans were then imported into the Mimics Innovation Suite 24.0 software to analyze the sublime tubercle angle from the midpoint of the trochlear notch. All left elbow angle and clock-face values were converted to right elbow values for analysis. The average sublime tubercle angle from the midpoint of the trochlear notch was 282.53 degrees. The angle was converted to a clock face descriptor which located the sublime tubercle at 9.42. Our findings demonstrate that, in the non-throwing population, the morphology of the sublime tubercle can be expected to have a consistent medial location between 9 and 10 o'clock or 2 and 3 o'clock on the contralateral elbow. In relation to the proximal ulnar landmarks, the sublime tubercle, in the non-throwing population, has a consistent relative location.