Fig 2 - available via license: Creative Commons Attribution 4.0 International
Content may be subject to copyright.
![3D face data representations. Reproduced with permission from Ref. [20], c IEEE 2011.](publication/372944357/figure/fig2/AS:11431281179683716@1691325113166/D-face-data-representations-Reproduced-with-permission-from-Ref-20-c-IEEE-2011.jpg)
Source publication
In the past ten years, research on face recognition has shifted to using 3D facial surfaces, as 3D geometric information provides more discriminative features. This comprehensive survey reviews 3D face recognition techniques developed in the past decade, both conventional methods and deep learning methods. These methods are evaluated with detailed...
Contexts in source publication
Context 1
... demand, many research institutions and researchers have created various 3D face databases. Table 1 lists current prominent 3D face databases and compares their data formats, number of persons contained (IDs), image variations (e.g., expression, pose, and occlusion), and scanning devices. Four different 3D data formats are in use: point clouds ( Fig. 2(a)), 3D meshes ( Fig. 2(b)), range images ( Fig. 2(c)), and depth maps plus 3D video. Before 2004, there were few public 3D face databases. Some representatives include 3DRMA [21], FSU [22], and GavabDB [23]. The GavabDB database contains 61 individuals, aged between 18 and 40. Each has 3 frontal images with different expressions and 4 ...
Context 2
... institutions and researchers have created various 3D face databases. Table 1 lists current prominent 3D face databases and compares their data formats, number of persons contained (IDs), image variations (e.g., expression, pose, and occlusion), and scanning devices. Four different 3D data formats are in use: point clouds ( Fig. 2(a)), 3D meshes ( Fig. 2(b)), range images ( Fig. 2(c)), and depth maps plus 3D video. Before 2004, there were few public 3D face databases. Some representatives include 3DRMA [21], FSU [22], and GavabDB [23]. The GavabDB database contains 61 individuals, aged between 18 and 40. Each has 3 frontal images with different expressions and 4 rotated images with a ...
Context 3
... have created various 3D face databases. Table 1 lists current prominent 3D face databases and compares their data formats, number of persons contained (IDs), image variations (e.g., expression, pose, and occlusion), and scanning devices. Four different 3D data formats are in use: point clouds ( Fig. 2(a)), 3D meshes ( Fig. 2(b)), range images ( Fig. 2(c)), and depth maps plus 3D video. Before 2004, there were few public 3D face databases. Some representatives include 3DRMA [21], FSU [22], and GavabDB [23]. The GavabDB database contains 61 individuals, aged between 18 and 40. Each has 3 frontal images with different expressions and 4 rotated images with a neutral expression [23]. In ...
Similar publications
Occlusion in facial photos poses a significant challenge for machine detection and recognition. Consequently, occluded face recognition for camera-captured images has emerged as a prominent and widely discussed topic in computer vision. The present standard face recognition methods have achieved remarkable performance in unoccluded face recognition...
Citations
... Extracting facial features is crucial for robust recognition, ensuring adaptability to environmental changes. This step is essential for enhancing recognition results [1]. ...
... B Xuequan Lu b.lu@latrobe.edu.au 1 OPT MV, Dongguan, China 2 La Trobe University, Melbourne, VIC, Australia potentially be forged. In recent years, biometric identification has come to the horizon and swiftly become a dominant alternative in the field primarily due to its distinctiveness and convenience. ...
... Among the human physiological features, the face [1,2] and hand stand out as the two most widely used components in contemporary applications. However, the face-based recognition approach can be potentially attacked [3,4]. ...
Hand vein identification stands out to be an increasingly popular approach for biometric identification due to its distinctiveness and convenience. While state-of-the-art techniques are able to achieve good performance, they share two common drawbacks: (1) complex preprocessing procedures, e.g., vein enhancement and Region of Interest (ROI) extraction, and (2) vein information loss due to hand ROI partition. To address these issues, we propose VeinTr, an end-to-end full-hand vein identification approach. In particular, our VeinTr consists of three components: a local feature extractor, a lightweight transformer, and a global feature decoder. We first obtain local features via convolution-based ResNet-like blocks. Then the attention mechanism is employed to aggregate global features from local features, which can be then decoded as global hand vein features. Finally, a global feature decoder is applied to generate robust hand features. By doing so, VeinTr is capable of directly extracting robust hand vein features from raw hand vein images. We evaluate our method on CASIA, TPV, and PLUSVein hand vein datasets. Experimental results show that our approach outperforms the state-of-the-art methods and has strong inter-dataset generalization abilities.
... However, the models suggested are limited in scope and do not encompass the entire CF field. Therefore, other researchers [42,43] point out the need for a unified model to include all CF terms with an organized data collection process [44]. These works collectively offer a foundation for the CFMM development and integration. ...
Cloud computing has revolutionized the way businesses operate by offering accuracy in Normalized Mutual Information (NMI). However, with the growing adoption of cloud services, ensuring the accuracy and validation of common processes through machine learning and clustering of these common concepts as well as of the processes generated by cloud forensics experts’ data in cloud environments has become a paramount concern. The current paper proposes an innovative approach to enhance the data collection procedure in cloud environments by applying a Cloud Forensic Meta-Model (CFMM) and integrating it with machine learning techniques to improve the cloud forensic data. Through this approach, consistency and compatibility across different cloud environments in terms of accuracy are ensured. This research contributes to the ongoing efforts to validate the clustering process for data collection in cloud computing environments and advance the field of cloud forensics for standardizing the representation of cloud forensic data, certifying NMI and accuracy across different cloud environments.
... 3D face recognition is more accurate than 2D face recognition: Jing, Y et al. [1] comprehensively explain 3D face recognition, attributing face geometry and deep learning as the main drive for new developments. The use of A.I. methods help minimize the number of features and speed up the recognition process, making it suitable for near real-time applications, such as our proposal. ...
... It is also the most common output generated by 3D scanners. It encompasses an unorganized collection of 3D coordinates corresponding to points on the facial surface [160]. In the past, it was viewed as a sparse approximation of the actual surface, but with the advent of point-based rendering and increases in storage and processing capabilities this perception is diminishing. ...
Due to their ease-of-use, biometric verification methods to control access to digital devices have become ubiquitous. Many rely on supervised machine learning, a process that is notoriously data-hungry. At the same time, biometric data is sensitive from a privacy perspective, and a comprehensive review from a data set perspective is lacking. In this survey, we present a comprehensive review of multimodal face data sets (e.g., data sets containing RGB color plus other channels such as infrared or depth). This follows a trend in both industry and academia to use such additional modalities to improve the robustness and reliability of the resulting biometric verification systems. Furthermore, such data sets open the path to a plethora of additional applications, such as 3D face reconstruction (e.g., to create avatars for VR and AR environments), face detection, registration, alignment, and recognition systems, emotion detection, anti-spoofing, etc. We also provide information regarding the data acquisition setup and data attributes (ethnicities, poses, facial expressions, age, population size, etc.) as well as a thorough discussion of related applications and state-of-the-art benchmarking. Readers may thus use this survey as a tool to navigate the existing data sets both from the application and data set perspective. To existing surveys we contribute, to the best of our knowledge, the first exhaustive review of multimodalities in these data sets.
... According to Jing et al. (2023) and our synthesis of recent literature, conventional facial recognition algorithms can be grouped into: local, global and hybrid algorithms. This classification was done according to the approach to feature extraction. ...
Face recognition is a crucial and rapidly evolving field within computer vision and artificial intelligence. The human face is one important element for recognizing a person in a group. The mechanism used by the human brain for face recognition is not yet fully understood, making it a complex problem. Over the past decade, there have been significant advancements in both the accuracy and applicability of face recognition systems. Deep learning techniques, particularly convolutional neural networks (CNNs), have played a pivotal role in achieving state-of-the-art performance in face recognition tasks. This paper proposes a review of research on face recognition techniques, algorithms and existing applications, with their advantages and disadvantages. It also includes a comparison of the results obtained with various algorithms and the related limitations. In the last part, it presents future directions of development in the field of face recognition.
3D face recognition has been extensively investigated in the last two decades due to its wide range of applications in many areas such as security and forensics. Numerous methods have been proposed to deal with the challenges faced by 3D face recognition such as facial expressions, pose variations and occlusions. These methods have achieved superior performances on several small-scale datasets including FRGC v2.0, Bosphorus, BU-3DFE, and Gavab. However, deep learning based 3D face recognition methods are still in their infancy due to the lack of large-scale 3D face datasets. To stimulate future research in this area, we present a comprehensive review of the progress achieved by both traditional and deep learning based 3D face recognition methods in the last two decades. Moreover, comparative results on several publicly available datasets under different challenges of facial expressions, pose variations and occlusions are also presented.
