Facial Texture Research Articles

An Investigation into the Utilisation of CNN with LSTM for Video Deepfake Detection

Video deepfake detection has emerged as a critical field within the broader domain of digital technologies driven by the rapid proliferation of AI-generated media and the increasing threat of its misuse for deception and misinformation. The integration of Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) has proven to be a promising approach for improving video deepfake detection, achieving near-perfect accuracy. CNNs enable the effective extraction of spatial features from video frames, such as facial textures and lighting, while LSTM analyses temporal patterns, detecting inconsistencies over time. This hybrid model enhances the ability to detect deepfakes by combining spatial and temporal analysis. However, the existing research lacks systematic evaluations that comprehensively assess their effectiveness and optimal configurations. Therefore, this paper provides a comprehensive review of video deepfake detection techniques utilising hybrid CNN-LSTM models. It systematically investigates state-of-the-art techniques, highlighting common feature extraction approaches and widely used datasets for training and testing. This paper also evaluates model performance across different datasets, identifies key factors influencing detection accuracy, and explores how CNN-LSTM models can be optimised. It also compares CNN-LSTM models with non-LSTM approaches, addresses implementation challenges, and proposes solutions for them. Lastly, open issues and future research directions of video deepfake detection using CNN-LSTM will be discussed. This paper provides valuable insights for researchers and cyber security professionals by reviewing CNN-LSTM models for video deepfake detection contributing to the advancement of robust and effective deepfake detection systems.

An Attempt for Numerical Optimisation of a Micro-Groove Geometry at The Rake Face When Turning Ti6Al4V Alloy with Indexable Inserts

Machining of Ti6Al4V is considered difficult because the material removal rates are relatively small if the tool wear shall be low. In recent years the reduction of process forces as well as tool wear have been investigated by introducing textures (pockets) into the tool surface. To advance the understanding how those textured tools function and to reduce the experimental effort, a smoothed particle hydrodynamics (SPH) model of the orthogonal cutting process with a parametrised tool containing a single pocket on the rake face with variable position and depth is presented. This simulation model is used to enhance the understanding of rake face textures in order to design optimum cutting tools for given process parameters. Using an optimisation algorithm, an optimum texture geometry is determined numerically and is then experimentally validated, followed by a discussion, why process force reductions are lower than predicted.

Performance Assessment of Basic Oxygen Furnace Slag (BOFS) as an Ice-Melting Abrasive Material

Abrasives play a crucial role in surface blasting, especially in cold climates, where snow and ice significantly challenge transportation infrastructure and road safety. The main purpose of this research is to address the critical need for effective and sustainable winter maintenance techniques. This study examined the possibilities of Basic Oxygen Furnace Slag (BOFS) as a substitute (an abrasive substance) for conventional aggregates in ice-melting applications. Thus, this research assessed the physical properties of BOFS, such as absorption capacity, tested at -5°C, and aggregate angularity test, and designed for evaluation of the surface texture, friction, and percentage of fractured faces in uncompacted voids (SSD%) of the aggregates. Moreover, the potential use of a blend of BOFS with de-icing salts, specifically sodium chloride (NaCl) and calcium chloride (CaCl2), was investigated as an effective ice-melting agent. For this purpose, three tests were carried out: the petri dish test according to SHRP H-205.1, the polishing ice melting test using a modified ASTM C 944 (rotational cutter), and the surface temperature measurement test. By assessing the performance of BOFS, our goal was to justify its efficacy, offering a practical alternative for regions experiencing severe winter conditions. Eventually, the findings from this study assert that BOFS can be used for surface blasting, indicating its potential as a substitute for traditional abrasives.

Self-supervised reconstruction of re-renderable facial textures from single image

Reconstructing high-fidelity 3D facial texture from a single image is a quite challenging task due to the lack of complete face information and the domain gap between the 3D face and 2D image. Further, obtaining re-renderable 3D faces has become a strongly desired property in many applications, where the term ’re-renderable’ demands the facial texture to be spatially complete and disentangled with environmental illumination. In this paper, we propose a new self-supervised deep learning framework for reconstructing high-quality and re-renderable facial albedos from single-view images in the wild. Our main idea is to first utilize a prior generation module based on the 3DMM proxy model to produce an unwrapped texture and a globally parameterized prior albedo. Then we apply a detail refinement module to synthesize the final texture with both high-frequency details and completeness. To further make facial textures disentangled with illumination, we propose a novel detailed illumination representation that is reconstructed with the detailed albedo together. We also design several novel regularization losses on both the albedo and illumination maps to facilitate the disentanglement of these two factors. Finally, by leveraging a differentiable renderer, each face attribute can be jointly trained in a self-supervised manner without requiring ground-truth facial reflectance. Extensive comparisons and ablation studies on challenging datasets demonstrate that our framework outperforms state-of-the-art approaches.

A Novel Hybrid Attention-Based Dilated Network for Depression Classification Model from Multimodal Data Using Improved Heuristic Approach

Automatic depression classification from multimodal input data is a challenging task. Modern methods use paralinguistic information such as audio and video signals. Using linguistic information such as speech signals and text data for depression classification is a complicated task in deep learning models. Best audio and video features are built to produce a dependable depression classification system. Textual signals related to depression classification are analyzed using text-based content data. Moreover, to increase the achievements of the depression classification system, audio, visual, and text descriptors are used. So, a deep learning-based depression classification model is developed to detect the person with depression from multimodal data. The EEG signal, Speech signal, video, and text are gathered from standard databases. Four stages of feature extraction take place. In the first stage, the features from the decomposed EEG signals are attained by the empirical mode decomposition (EMD) method, and features are extracted by means of linear and nonlinear feature extraction. In the second stage, the spectral features of the speech signals from the Mel-frequency cepstral coefficients (MFCC) are extracted. In the third stage, the facial texture features from the input video are extracted. In the fourth stage of feature extraction, the input text data are pre-processed, and from the pre-processed data, the textual features are extracted by using the Transformer Net. All four sets of features are optimally selected and combined with the optimal weights to get the weighted fused features using the enhanced mountaineering team-based optimization algorithm (EMTOA). The optimal weighted fused features are finally given to the hybrid attention-based dilated network (HADN). The HDAN is developed by combining temporal convolutional network (TCN) with bidirectional long short-term memory (Bi-LSTM). The parameters in the HDAN are optimized with the assistance of the developed EMTOA algorithm. At last, the classified output of depression is obtained from the HDAN. The efficiency of the developed deep learning HDAN is validated by comparing it with various traditional classification models.

Preserving manipulated and synthetic Deepfake detection through face texture naturalness

With the rapid development of deep learning and face recognition technology, AI(Artificial Intelligence) experts have rated Deepfake cheating as the top AI threat. It is difficult for the human eye to distinguish the fake face images generated by Deepfake. Therefore, it has become a popular tool for criminals to seek benefits. Deepfake can be mainly divided into two types, a manipulated Deepfake that falsifies images of others by targeting real faces, and a synthetic Deepfake using GAN to generate a new fake image. So far, seldom cybersecurity system is able to detect these two types simultaneously. In this article, we aim to propose a hybrid Deepfake detection mechanism (HDDM) based on face texture and naturalness degree. HDDM constructs a unique texture from a facial image based on CNN(Convolutional Neural Network) and builds a naturalness degree recognition model via DNN(Deep Neural Network) to help cheating detection. Experimental results have proved that HDDM possesses a sound effect and stability for synthetic and manipulated Deepfake attacks. In particular, the WildDeepfake simulation has demonstrated the possibility of applying HDDM to the real world.

Progressive reconstruction-decoupled face super-resolution framework with controllable knowledge guidance

Large-factor face super-resolution is a severely ill-posed problem that requires additional information to assist in image reconstruction. Existing methods improve the super-resolution performance by introducing estimated face or pre-trained generative adversarial network (GAN) priors. However, they ignore the interference between contour and detail reconstruction as well as the errors in pretrained GAN and estimated face priors. To address these problems, we propose a progressive reconstruction-decoupled face super-resolution (PDFSR) framework with controllable knowledge guidance. First, a three-level index (pose, semantics, geometry) is proposed to utilize the high-resolution face texture to construct a lightweight knowledge base robust to bias. Then, the face contours are reconstructed by a basic super-resolution network. Finally, a constraint module is proposed to constrain the output of the knowledge base to provide accurate and controllable explicit knowledge for the reconstruction of facial details. The progressive framework decouples contour and detail reconstruction during training for the reconstructed images to consider both fidelity and perceptual quality. The knowledge base provides accurate and controllable low-dimensional explicit knowledge without estimation or pre-training, which reduces prior errors. Experiments demonstrate that our PDFSR outperforms state-of-the-art face super-resolution methods. Moreover, during the testing phase, faces can be edited by adjusting the explicit knowledge output by the knowledge base to obtain diverse reconstruction results.

Age-Invariant Cross-Age Face Verification using Transfer Learning

The integration of face verification technology has become indispensable in numerous safety and security software systems. Despite its promising results, the field of face verification encounters significant challenges due to age-related disparities. Human facial characteristics undergo substantial transformations over time, leading to diverse variations including changes in facial texture, morphology, facial hair, and eyeglass adoption. This study presents a pioneering methodology for cross-age face verification, utilizing advanced deep learning techniques to extract resilient and distinctive facial features that are less susceptible to age-related fluctuations. The feature extraction process combines handcrafted features like Local Binary Pattern/Histogram of Oriented Gradients with deep features from MobileNetV2 and VGG-16 networks. As the texture of the facial skin defines the age related characteristic the well-known texture feature extractors like LBP and HoG is preferred. These features are concatenated to achieve fusion, and subsequent layers fine-tune them. Experimental validation utilizing the Cross-Age Celebrity Dataset demonstrates remarkable efficacy, achieving an accuracy of 98.32%.

Person Image Generation Guided by Posture, Expression and Illumination

Person pose transfer has shown great application prospects and potential in recent years. However, this research mainly focuses on posture transfer and does not pay much attention to other human body attributes. In addition, there are problems such as blurred facial expressions and inconsistent facial texture. In order to solve these problems and improve user experience, this paper proposes a multi-feature transfer person image generation model, which combines facial expression transfer and pose transfer and completes the lighting reconstruction of person images. Our model can simultaneously migrate and supplement facial expressions while migrating a person’s posture, ensuring the consistency of characters’ overall migration. Our model can freely switch personal body lighting to adapt to different scenes, greatly improving the user experience. The experimental results show that our method’s preservation rate for face identity is improved by nearly 35% compared with the benchmark, and the similarity index for the overall person body is improved by nearly 14%. The evaluation results indicate that our method performs well in person posture transfer. The experimental results show that the proposed method is superior to the existing algorithms in person posture transformation.

GANtlitz: Ultra High Resolution Generative Model for Multi‐Modal Face Textures

AbstractHigh‐resolution texture maps are essential to render photoreal digital humans for visual effects or to generate data for machine learning. The acquisition of high resolution assets at scale is cumbersome, it involves enrolling a large number of human subjects, using expensive multi‐view camera setups, and significant manual artistic effort to align the textures. To alleviate these problems, we introduce GANtlitz (A play on the german noun Antlitz, meaning face), a generative model that can synthesize multi‐modal ultra‐high‐resolution face appearance maps for novel identities. Our method solves three distinct challenges: 1) unavailability of a very large data corpus generally required for training generative models, 2) memory and computational limitations of training a GAN at ultra‐high resolutions, and 3) consistency of appearance features such as skin color, pores and wrinkles in high‐resolution textures across different modalities. We introduce dual‐style blocks, an extension to the style blocks of the StyleGAN2 architecture, which improve multi‐modal synthesis. Our patch‐based architecture is trained only on image patches obtained from a small set of face textures (<100) and yet allows us to generate seamless appearance maps of novel identities at 6k × 4k resolution. Extensive qualitative and quantitative evaluations and baseline comparisons show the efficacy of our proposed system. (see https://www.acm.org/publications/class-2012)

Double Reference Guided Interactive 2D and 3D Caricature Generation

In this paper, we propose the first geometry and texture (double) referenced interactive 2D and 3D caricature generating and editing method. The main challenge of caricature generation lies in the fact that it not only exaggerates the facial geometry but also refreshes the facial texture. We address this challenge by utilizing the semantic segmentation maps as an intermediary domain, removing the influence of photo texture while preserving the person-specific geometry features. Specifically, our proposed method consists of two main components: 3D-CariNet and CariMaskGAN. 3D-CariNet uses sketches or caricatures to exaggerate the input photo into several types of 3D caricatures. To generate a CariMask, we geometrically exaggerate the photos using the projection of exaggerated 3D landmarks, after which CariMask is converted into a caricature by CariMaskGAN. In this step, users can edit and adjust the geometry of caricatures freely. Moreover, we propose a semantic detail preprocessing approach that considerably increases the details of generated caricatures and allows modification of hair strands, wrinkles, and beards. By rendering high-quality 2D caricatures as textures, we produce 3D caricatures with a variety of texture styles. Extensive experimental results have demonstrated that our method can produce higher-quality caricatures as well as support interactive modification with ease.

ControlFace: Feature Disentangling for Controllable Face Swapping.

Face swapping is an intriguing and intricate task in the field of computer vision. Currently, most mainstream face swapping methods employ face recognition models to extract identity features and inject them into the generation process. Nonetheless, such methods often struggle to effectively transfer identity information, which leads to generated results failing to achieve a high identity similarity to the source face. Furthermore, if we can accurately disentangle identity information, we can achieve controllable face swapping, thereby providing more choices to users. In pursuit of this goal, we propose a new face swapping framework (ControlFace) based on the disentanglement of identity information. We disentangle the structure and texture of the source face, encoding and characterizing them in the form of feature embeddings separately. According to the semantic level of each feature representation, we inject them into the corresponding feature mapper and fuse them adequately in the latent space of StyleGAN. Owing to such disentanglement of structure and texture, we are able to controllably transfer parts of the identity features. Extensive experiments and comparisons with state-of-the-art face swapping methods demonstrate the superiority of our face swapping framework in terms of transferring identity information, producing high-quality face images, and controllable face swapping.

An Efficient Latent Style Guided Transformer-CNN Framework for Face Super-Resolution

In the Face Super-Resolution (FSR) task, it is important to precisely recover facial textures while maintaining facial contours for realistic high resolution faces. Although several CNN-based FSR methods have achieved great performance, they fail in restoring the facial contours due to the limitation of local convolutions. In contrast, Transformer-based methods which use self-attention as the basic component, are expert in modeling long-range dependencies between image patches. However, learning long-range dependencies often deteriorates facial textures due to the lack of locality. Therefore, a question is naturally raised: <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">how to effectively combine the superiority of CNN and Transformer for better reconstructing faces?</i> To address this issue, we propose an Efficient Latent Style guided Transformer-CNN framework for FSR called <bold xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">ELSFace</b> , which can sufficiently integrate the advantages of CNN and Transformer. The framework consists of a Feature Preparation Stage and a Feature Carving Stage. Basic facial contours and textures are generated in the Feature Preparation Stage, and separately guided by latent styles, so that facial details are better represented in reconstruction. CNN and Transformer streams in the Feature Carving Stage are used to individually restore facial textures and facial contours, respectively in a parallel recursive way. Considering the negligence of high-frequency features when learning the long-range dependencies, we design the High-Frequency Enhancement Block (HFEB) in the Transformer stream. The Sharp Loss is also proposed for better perceptual quality in optimization. Extensive experimental results demonstrate that our ELSFace can achieve the best results among all metrics compared to the state-of-the-art CNN and Transformer-based methods on commonly used datasets and real-world tasks. Meanwhile, our ELSFace method has the least model parameters and running time. The codes are released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/FVL2020/ELSFace</uri> .

FaceRefiner: High-Fidelity Facial Texture Refinement With Differentiable Rendering-Based Style Transfer

FaceRefiner: High-Fidelity Facial Texture Refinement With Differentiable Rendering-Based Style Transfer

3D facial animation generation technology based on 2D image

In order to improve the modeling efficiency and ensure the authenticity of the model, this paper proposes a 3D facial animation generation method based on front and side images. First, the feature point information reflecting the shape characteristics of the face is extracted from the front and side photos of a given face, and then these feature point information is used to modify the general face model to obtain a specific face model. Then, the face texture information in the front and side photos is used to texture map the specific face model, and finally a realistic virtual 3D face animation is obtained. In the aspect of feature extraction, this paper uses an improved color Snake model to accurately locate contour lines. The experimental results show that the system still has good processing performance, and the average processing time is less than 0.1s. On the set V, the light source angle is greater than 78 °, the illumination is seriously uneven, and the recognition rate is very low, which indicates that the texture features are not well extracted. But even in this case, the recognition rate after light compensation has doubled, which proves that the two-dimensional image can realize the three-dimensional facial animation generation technology.

Attention-Rectified and Texture-Enhanced Cross-Attention Transformer Feature Fusion Network for Facial Expression Recognition

Facial Expression Recognition (FER) in the wild is a challenging task for affective computing in human-machine interaction fields. However, most of existing methods fail to learn the most prominent regions of facial images by simple cross-entropy loss due to the imbalance problem commonly existing in FER datasets, which limits the robustness and interpretability of the model. In addition, these methods only capture local features of original images with multi-size shallow convolution and ignore facial texture characteristics, leading to a suboptimal recognition performance. To address these issues, we propose a novel facial expression recognition network, named the attention-rectified and texture-enhanced cross-attention transformer feature fusion network (AR-TE-CATFFNet). Specifically, an attention-rectified convolution block is first designed to assist multiple convolution heads to focus on critical areas of human faces and improve the model generalization. Second, we investigate a texture enhancement block to capture texture features through local binary pattern and gray-level co-occurrence matrix, which solves the limitation of insufficient texture information. Finally, a cross-attention transformer feature fusion block is employed to deeply integrate RGB features and texture features globally, which is beneficial to boost the accuracy of recognition. Competitive experimental results on three public datasets validate the efficacy of the proposed method, indicating that our proposed method achieves superior classification performance of 89.50% on RAF-DB dataset, 65.66% on AffectNet dataset, and 74.84% on FER2013 dataset against the existing methods. The code of our proposed method will be available at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/smy17/AR-TE-CATFFNet</uri> .

Cyclic style generative adversarial network for near infrared and visible light face recognition

Near Infrared and Visible Light (NIR-VIS) face recognition attracts attention from researchers because of its potential for safety, illumination invariance, and stability. Nevertheless, the difference between NIR and VIS domains, the domain gap, remains a huge problem for matching NIR and VIS images. Specifically, for the same identity, the appearance in the NIR domain is different from the VIS domain. Thus, traditional face recognition methods cannot be effective. To address this problem, this paper proposes a novel model, called Cyclic-Style GAN (CS-GAN). First, the pre-trained Style-GAN 3 network is embedded into the Cycle-GAN structure for NIR-VIS cross-domain learning. Second, there is a cyclic subspace learning method consisting of latent loss and style loss, through which both style (domain feature) and facial characteristic features are learned to improve the quality of synthesized images. The model synthesizes realistic VIS images from NIR images and does the face recognition task in the VIS domain. The proposed method achieves 99.6% Rank-1 accuracy on the CASIA NIR-VIS 2.0 database which is a state-of-the-art result. The visualization results show that the proposed model synthesizes VIS images with a clear texture of faces and in close-to-reality color.

Enhancing Attendance Management through Real-Time Face Recognition using combination of LBP Histogram and Linear Discriminant Analysis

Face recognition technology's excellent accuracy and non-intrusiveness have made it a major player in the attendance management space. This research study presents an advanced method of tracking attendance through the integration of a Face Recognition System (FRS) with Linear Discriminant Analysis (LDA) and Local Binary Pattern (LBP) histogram analysis. The architecture of the suggested attendance system is described in the study, with an emphasis on how LDA and LBP techniques are used to increase the accuracy of face feature extraction and recognition. Through the use of LDA, the system improves face data's discriminative strength, producing attendance records that are more trustworthy. Robust facial texture and pattern identification are simultaneously made possible by LBP histogram analysis, particularly in a variety of environmental settings. To sum up, this study advances biometric attendance systems by demonstrating how LDA and LBP histogram analysis may improve the precision and dependability of face recognition systems used for attendance tracking

Face deblurring based on regularized structure and enhanced texture information

Image deblurring is an essential problem in computer vision. Due to highly structured and special facial components (e.g. eyes), most general image deblurring methods and face deblurring methods failed to yield more explicit structure and facial details, resulting in too smooth, uncoordinated and distorted face structure. Considering the unique face texture and sufficient facial details, we present an effective face deblurring network by exploiting more regularized structure and enhanced texture information (RSETNet). We first incorporate the face parsing network with fine-tuning to obtain more accurate face structure, and we present the feature adaptive denormalization (FAD) to regularize the facial structure as a condition of auxiliary to generate more harmonious and undistorted face structure. Meanwhile, to improve the generated facial texture information, we propose a new Laplace depth-wise separable convolution (LDConv) and multi-patch discriminator. Compared with existing methods, our face deblurring method could restore face structure more accurately and with more facial details. Experiments on two public face datasets have demonstrated the effectiveness of our proposed methods in terms of qualitative and quantitative indicators.

A novel sintering method of Al2O3/SiCw ceramic composites with improved wear resistance: Oscillatory pressure‐assisted sinter forging

As a typical ceramic tool, the wear resistance of Al2O3/SiCw composites is a prominent parameter in engineering applications. Therefore, how to improve its wear resistance has becomes a research emphasis of ceramic tools. In this work, the Al2O3/SiCw composites with improved wear resistance were prepared by a novel oscillatory pressure-assisted sinter forging (OPSF) process. The composites prepared by OPSF process not only exhibit higher density and significantly improved mechanical properties, but also own lower coefficient of friction than conventional sinter forging and hot oscillatory pressing processes. EBSD results indicated that the OPSF process could improve the texture of (0001) crystal face, low-angle grain boundaries, high-angle grain boundaries with special angles in the Al2O3 matrix and enhance shear deformation at micro-scales, which are multiple contributed to enhanced wear resistance. Therefore, OPSF process is a promising technique to prepare ceramic-based cutting tools with excellent mechanical properties and wear resistance.