Face Images Research Articles

Pain assessment from facial expression images utilizing Statistical Frei-Chen Mask (SFCM)-based features and DenseNet

Estimating pain levels is crucial for patients with serious illnesses, those recovering from brain surgery, and those receiving intensive care etc. An automatic pain intensity estimator is proposed in this study that gathers information about pain and intensity from the user’s expressions. The faces in the database are first cropped using a ‘Chehra’ face detector, which performs well even in wildly uncontrolled environments with a wide range of lighting and position fluctuations. The suggested technique extracts the beneficial and distinct patterns from facial expressions using novel Statistical Frei-Chen Mask (SFCM)-based features and DenseNet-based features. As it offers quick as well as accurate pain identification and pain intensity estimation, the Radial Basis Function Based Extreme Learning Machine (RBF-ELM) is employed for pain recognition and pain intensity level estimation using the characteristics. All the data is kept, updated and protected in the cloud because availability and high-performance decision-making are so important for informing physicians and auxiliary IoT nodes (such as wearable sensors). In addition, cloud computing reduces the time complexity of the training phase of Machine Learning algorithms in situations where it is possible to build a complete cloud/edge architecture by allocating additional computational resources and memory in use. The facial expression images from the UNBC-McMaster Shoulder Pain Expression Archive and 2D face dataset are used to test the proposed method. The measurement of pain intensity uses four stages. When compared to the results from the literature, the proposed work attains enhanced performance.

Automatic human age estimation from face images using MLP and RBF neural network algorithms in secure communication networks

Age estimation finds application in several contexts including biometric authentication, surveillance, forensic investigations, and the entertainment industries, among others, making it a realistic, complex, and relevant problem in the subfield of machine vision and pattern recognition. This article proposes a system that can determine the age of people by applying the multilayer perceptron neural network technique, feature fusion, and integration. It is imperative to define three fundamental stages of the proposed procedure. One of the methods necessary at the first stage involves face parts detection and resizing. The second activity is feature extraction of the facial regions of the video frames. To do this, we select and use features through the use of Gabor Filters, SIFT, and LBP with optimal values being picked through combinations. The third step in the process entails making an age range prediction of the face image using neural network algorithms such as MLP and RBF for securing communication networks. For further reduction of dimensions and for getting rid of any possibly overlapping features, independent component analysis (ICA) is used. The datasets adopted for this research work are FG-NET and PAL which are widely acclaimed research data sets. Simply based on the features adopted, the proposed age estimate procedure was seemingly superior to the MLP algorithm and possessed high accuracy for a given range of ages.

Can You Tell Real from Fake Face Images? Perception of Computer-Generated Faces by Humans

With recent advances in machine learning and big data, it is now possible to create synthetic images that look real. Face generation is often of particular interest, as faces can be used for various purposes. However, improper use of such content can lead to the dissemination of false information, such as fake news, and thus pose a threat to society. This work studies whether people believe the truthfulness of faces using eye tracking and self-reports, including free-form textual explanations when participants encounter real and computer-generated faces. We used three different datasets for our evaluations, and our experimental results show that while people are relatively better at identifying the truthfulness of real faces and faces generated by earlier machine learning algorithms with different gazing behaviors in viewing and rating phases, they perform less accurately when deciding the truthfulness of synthetic face images that are generated by newer algorithms. Our findings provide important insights for society and policymakers.

Multimodal Fusion for Talking Face Generation Utilizing Speech-Related Facial Action Units

Talking face generation is to synthesize a lip-synchronized talking face video by inputting an arbitrary face image and corresponding audio clips. The current talking face model can be divided into four parts: visual feature extraction, audio feature processing, multimodal feature fusion, and rendering module. For the visual feature extraction part, existing methods face the challenge of complex learning task with noisy features, this article introduces an attention-based disentanglement module to disentangle the face into Audio-face and Identity-face using speech-related facial action unit (AU) information. For the multimodal feature fusion part, existing methods ignore not only the interaction and relationship of cross-modal information but also the local driving information of the mouth muscles. This study proposes a novel generative framework that incorporates a dilated non-causal temporal convolutional self-attention network as a multimodal fusion module to enhance the learning of cross-modal features. The proposed method employs both audio- and speech-related facial AUs as driving information. Speech-related AU information can facilitate more accurate mouth movements. Given the high correlation between speech and speech-related AUs, we propose an audio-to-AU module to predict speech-related AU information. Finally, we present a diffusion model for the synthesis of talking face images. We verify the effectiveness of the proposed model on the GRID and TCD-TIMIT datasets. An ablation study is also conducted to verify the contribution of each component. The results of quantitative and qualitative experiments demonstrate that our method outperforms existing methods in terms of both image quality and lip-sync accuracy. Code is available at https://mftfg-au.github.io/Multimodal_Fusion/.

S2HConv-Caps-BiGRU: Deep Learning-Based Heterogeneous Face Recognition Model with Divergent Stages

Real-time images of faces captured in different spectrum bands are considered heterogeneous images. Heterogeneous Face Recognition (HFR) matches faces across domains and is crucial to public safety. This paper proposes an HFR approach based on Deep Neural Networks (DNN). Feature maps are extracted from two images, such as gallery and sketch images, using Squirrel Search Heterogeneous Convolutional-Capsule- Bidirectional Gated Recurrent Unit (S2HConv-Caps-BiGRU). As a method of efficiently recognizing faces, coupled representation similarity metric (CRSM) will use the measure for the similarity of two feature maps. The experimental results will be evaluated to state-of-the-art (SOTA) statistical measures in terms of accuracy, recall, Jaccard score, dice score, mean square error (MSE), image similarity, performance and root mean square error (RMSE). Compared to other SOTA, the model produces the best results. The accuracy value of a CUFS dataset is 98.7%.

Jeet Wheel Scale: A Novel Tool for Evaluation of Dental Anxiety in Children.

One of the major concerns of the current era is dental anxiety in Pediatric Dentistry. Kids are very well adapted to emojis or emoticons nowadays, and they represent emotions or moods better than a cartoon picture. Therefore, this study was conducted to evaluate a newly designed anxiety rating scale. The Jeet Wheel Scale (JWS) uses emoticons and colors to assess the anxiety or mood of the child during the first visit of the child. The aim was to establish the novel anxiety rating scale and compare it with the Venham Picture Test (VPT) and Facial Image Scale (FIS). The study included 100 healthy children aged 4-8 years, and their dental anxiety was assessed using the JWS, VPT, and FIS at their first dental appointment, along with their scale preference. The mean and standard deviation of anxiety scores measured using the FIS, VPT, and JWS were 1.67 ± 0.88, 1.99 ± 1.17, and 2.79 ± 1.35, respectively. Among the scales used, a significant difference was observed. A strong correlation was observed with the Pearson correlation test. The results indicated a strong correlation (0.863) between the JWS and VPT, and a strong correlation (0.802) between the JWS and the FIS. Based on the above observations, it could be confirmed that the JWS has high validity. Children preferred the JWS over the other two established scales. The JWS was found to be more efficient for assessing dental anxiety in children. Chakraborty S, Jana S, Dey B, et al. Jeet Wheel Scale: A Novel Tool for Evaluation of Dental Anxiety in Children. Int J Clin Pediatr Dent 2024;17(8):898-902.

Impaired facial emotion recognition in individuals with bipolar disorder

BackgroundIndividuals with bipolar disorder (BD) often struggle with emotional regulation and social interactions, partly due to difficulties in accurately recognizing facial emotions. MethodsFrom September 2021 to February 2023, 69 BD individuals-comprising 23 with bipolar manic/hypomanic episode (BME), 23 with bipolar depressive episode (BDE), 23 with bipolar euthymic (EUT)-and 23 healthy controls (HCs) were enrolled. Diagnosis adhered to DSM-IV criteria using M.I.N.I 5.0, alongside assessments via Hamilton Depression Scale 17 and Young Manic Rating Scale. Recognition tasks involving 84 facial expression images across six categories. The Wilcoxon rank-sum test compares two groups, while the Kruskal-Wallis test compares multiple groups with subsequent adjusted pairwise comparisons. ResultsThe overall correct recognition rate of facial expressions in the BD group (79 %) was significantly lower than that of the HC group (83 %) (P=0.004). Primary differences were noted in neutral (93 % vs. 100 %, P=0.012) and fear (79 % vs. 86 %, P=0.023) expressions. Within the BD group, correct recognition rates were 71 % for BME, 80 % for BDE, and 80 % for EUT, all lower than in the HC group. Significant differences in correct recognition rates of neutral, fear, and joy expressions were observed among the four groups (P<0.05), with the BME group exhibiting the lowest rate. Misidentification of facial expressions was more frequent in the BD group compared to the HC group, particularly among negative expressions. ConclusionPatients with BD demonstrate lower correct recognition and higher misidentification rates of facial expressions, with those experiencing manic episodes showing impaired recognition of neutral, joy, and fear expressions.

Three-dimensional Assessment of Longitudinal Surgical Outcome in Patients with Unilateral Cleft Lip and Palate: A Modified Rotation Advancement Technique.

Optimization of a modified rotation advancement technique is hampered by lack of objective measures to quantify the longitudinal surgical outcome. We collected and assessed facial 3D images of 115 consecutive patients who underwent primary repair between 2017 and 2019. Photogrammetry was performed preoperatively, immediately postoperatively and at a first and second follow-up interval, occurring at an average year of 0.6 and 5.3 years, respectively. 10 additional age-matched noncleft control subjects were also included. Growth lag in cleft side lateral lip and gradual elongation of medial lip height on the cleft side caused continuous deviation of philtrum towards the cleft side. The columellar length on the cleft side continued to grow slower, accompanied by a persistent widening of alar base width on the cleft side, leading to in the gradual deviation of columella towards the cleft side. The pre-operative and post-operative nasolabial asymmetry would increase with greater degree of postoperative deficiencies. Right clefts presented with greater degrees of deficiencies in lateral lip height in preoperative measurement, but this discrepancy of the laterality of clefts was not observed in the two follow-up periods. The surgical outcome of this modified rotational advancement technique in unilateral cleft lip primary repair is promising. Growth lag in lateral lip and lateral displacement of alar base cause continuous deviation of philtrum towards the cleft side. Pre-operative severity does predict post-operative outcomes. Laterality of oral clefts does not significantly affect the long-term outcomes of surgery. This surgical technique meets the current trend of cleft lip and palate primary repair and is worth promoting.

Weakly Supervised 3D Face Reconstruction with Joint Spatial and Frequency Domain Information

3D face reconstruction is an important research direction in computer vision, and its goal is to recover a 3D face model from a single face picture. In the absence of real 3D face data, how to reconstruct a 3D face with a high degree of realism has become a hot research topic in recent years. Existing reconstruction algorithms usually rely on 3D labels generated from a large number of 2D face images as training data, however, inaccurate data will seriously affect the reconstruction quality. For this reason, the paper proposes a joint spatial-frequency domain decoupled weak supervision to achieve 3D face reconstruction, the main idea of which is to construct a multi-level loss function by using the weakly supervised information extracted from the spatial domain, and separating the frequency-domain information between the input and the rendered image in the frequency domain, and minimizing the difference between the two by difference computation. The method combines deep learning with 3D deformable models to reconstruct 3D models with high quality texture and shape from only a single face image. Quantitative experiments on the AFLW2000-3D and MICC Florence datasets show that the normalized average error in the small pose interval is as low as 2.42%, and the face reconstruction accuracy in the outdoor scene is 0.98 0.22 mm. Qualitative experiments on the MoFa-test, MICA datasets show that when faced with reconstruction with different poses, lighting, and expressions , our method outperforms other state-of-the-art reconstruction methods.

A comparative study of linear and nonlinear regression models for blood glucose estimation based on near-infrared facial images from 760 to 1650 nm wavelength

A comparative study of linear and nonlinear regression models for blood glucose estimation based on near-infrared facial images from 760 to 1650 nm wavelength

Synthesis of Comic-Style Portraits Using Combination of CycleGAN and Pix2Pix

This paper proposes a system for converting face photos into portraits with specific charcoal sketch-like style. NPR (non-photorealistic rendering) for converting real photo images into anime-style images have been studied. Its promising application is the creation of users’ portraits on social networks for preventing leaks of personal information. An image-to-image transformation using GAN (Generative Adversarial Network), such as CycleGAN or Pix2Pix, is expected to be used for this goal. However, it is difficult to generate portraits with specific comic styles that satisfy two conditions at the same time: preserving photorealistic features and reproducing the comic styles. For example, replacing too many photorealistic features on the face with comic style will destroy users’ identity, such as eyes shape. To solve this problem, the proposed system combines CycleGAN and Pix2Pix. CycleGAN is used to generate paired examples for Pix2Pix and Pix2Pix learns photo-to-comic transformation. To further emphasize a comic style, this paper also proposes two extensions, which divides face images into several parts such as hair and eye parts. The quality of generated images are evaluated with questionnaire by 50 answerers. The results show that the images generated by the proposed system are highly evaluated than the images generated by CycleGAN in terms of preserving the features in a photo and reproducing a comic style. Although the segmentation tend to collapse the generated images, it can reproduce a comic style effectively, especially on facial parts.

Beyond the visible: A survey on cross-spectral face recognition

Cross-spectral face recognition (CFR) refers to recognizing individuals using face images stemming from different spectral bands, such as infrared versus visible. While CFR is inherently more challenging than classical face recognition due to significant variation in facial appearance caused by the modality gap, it is useful in many scenarios including night-vision biometrics and detecting presentation attacks. Recent advances in deep neural networks (DNNs) have resulted in significant improvement in the performance of CFR systems. Given these developments, the contributions of this survey are three-fold. First, we provide an overview of CFR, by formalizing the CFR problem and presenting related applications. Secondly, we discuss the appropriate spectral bands for face recognition and discuss recent CFR methods, placing emphasis on deep neural networks. In particular we describe techniques that have been proposed to extract and compare heterogeneous features emerging from different spectral bands. We also discuss the datasets that have been used for evaluating CFR methods. Finally, we discuss the challenges and future lines of research on this topic.

When guided diffusion model meets zero-shot image super-resolution

Existing deep learning-based single-image super-resolution (SR) methods typically rely on vast quantities of paired data. As an essential solution, zero-shot SR methods require only a single image to handle image-specific degradation. However, these methods still struggle to recover fine-grained details due to the lack of supervised information. In this work, we propose a novel guided Diffusion model for Zero-shot image SR (ZeroDiff) to explicitly direct image quality enhancement. Specifically, we elaborate two key guidance strategies: (1) high-frequency guidance and (2) content-consistent guidance. The former concentrates on boosting fine-grained textures by embedding high-frequency information into the cross-attention mechanism of the noise estimator. The latter avoids the sampling deviating from the original image in terms of structure and low-frequency content. Specifically, the noisy images at each diffusion step are injected into the corresponding sampling step, encouraging the sampled image to be consistent with that of the corresponding diffusion step. Moreover, we design a progressive zoom-in paradigm by gradually enlarging the image size and enriching the image details to boost the sampling efficiency of diffusion models, while enabling high-quality image reconstruction. Extensive experiments reveal that our method achieves comparable results with other state-of-the-art methods in quantitative and qualitative evaluations on both face and natural images from synthetic and real-world datasets.

Deep convolutional neural networks for age and gender estimation using an imbalanced dataset of human face images

Deep convolutional neural networks for age and gender estimation using an imbalanced dataset of human face images

Biometric access system with automatic registration and loyalty check in the system of recognition and database entry

ABSTRACT Against the backdrop of ongoing terrorist threats and uncontrolled migration flows, there is increased interest in biometric human recognition technology and barcoding technology combined with it. As a possible solution, a biometric access system is proposed, designed to implement three main urgent tasks – automatic registration of people crossing the border; recording registration information in a special biometric database; checking registration information and facial image on the database of wanted people. Effective biometric systems combine verification and identification tasks to increase the reliability of person identification and comparison with reference data sets. In the course of the study, various methods of information processing with its subsequent encoding were considered and analyzed, and the experience of previous systems of this type was investigated. As a result of the study, the effectiveness of using the latest biometric technologies in the migration sphere and in law enforcement agencies for the effective search of offenders has been substantiated. This paper will be useful as a material for further study of facial recognition technology and the integration of QR into the field of biometrics.

Diverse Face Images (DFI): Validated for racial representation and eye gaze.

Face processing is a central component of human communication and social engagement. The present investigation introduces a set of racially and ethnically inclusive faces created for researchers interested in perceptual and socio-cognitive processes linked to human faces. The Diverse Face Images (DFI) stimulus set includes high-quality still images of female faces that are racially and ethnically representative, include multiple images of direct and indirect gaze for each model and control for low-level perceptual variance between images. The DFI stimuli will support researchers interested in studying face processing throughout the lifespan as well as other questions that require a diversity of faces or gazes. This report includes a detailed description of stimuli development and norming data for each model. Adults completed a questionnaire rating each image in the DFI stimuli set on three major qualities relevant to face processing: (1) strength of race/ethnicity group associations, (2) strength of eye gaze orientation, and (3) strength of emotion expression. These validation data highlight the presence of rater variability within and between individual model images as well as within and between race and ethnicity groups.

Ensembling U-Nets for microaneurysm segmentation in optical coherence tomography angiography in patients with diabetic retinopathy

Diabetic retinopathy is one of the leading causes of blindness around the world. This makes early diagnosis and treatment important in preventing vision loss in a large number of patients. Microaneurysms are the key hallmark of the early stage of the disease, non-proliferative diabetic retinopathy, and can be detected using OCT angiography quickly and non-invasively. Screening tools for non-proliferative diabetic retinopathy using OCT angiography thus have the potential to lead to improved outcomes in patients. We compared different configurations of ensembled U-nets to automatically segment microaneurysms from OCT angiography fundus projections. For this purpose, we created a new database to train and evaluate the U-nets, created by two expert graders in two stages of grading. We present the first U-net neural networks using ensembling for the detection of microaneurysms from OCT angiography en face images from the superficial and deep capillary plexuses in patients with non-proliferative diabetic retinopathy trained on a database labeled by two experts with repeats.

An efficient identity-preserving and fast-converging hybrid generative adversarial network inversion framework

In this paper, we present a novel Hybrid Generative Adversarial Network (HGAN) inversion framework that enables facial images to be rapidly inverted while preserving identity and personality characteristics. Accurate inversion of facial images requires high precision in computer vision and is critical to the success of future facial manipulations (age progression, regression, accessory, and hair stylization). However, existing methods often fail to preserve the personality characteristics of the real image, negatively affecting the accuracy of manipulations. In this context, our key contribution lies in using a transformer-based strategy to initiate the generator, which effectively models spatial relationships for detailed image processing. This approach is innovative because it leverages transformer structures to enhance image inversion tasks. Additionally, we introduce a novel loss function to enhance convergence speed and reliability, ensuring high accuracy in identity and personality trait preservation. Experimental results show that our method achieves a reconstruction accuracy of 93% and improves inversion time by 86%. This advancement could significantly impact facial manipulation technologies, laying the foundation for a technological breakthrough with potential applications in secure digital authentication systems and personal data protection. Our method may have a significant impact on privacy and security in future studies, contributing to the development of secure digital authentication systems and enhancing the protection of personal data. Therefore, our work is crucial for advancing the field of facial image manipulation and ensuring the privacy and security of personal data.

CAFIN: cross-attention based face image repair network

CAFIN: cross-attention based face image repair network

Enhancing eyeglasses removal in facial images: a novel approach using translation models for eyeglasses mask completion

Enhancing eyeglasses removal in facial images: a novel approach using translation models for eyeglasses mask completion