Pose-invariant 3D face recognition using half face

In this paper, a noble nonintrusive three-dimensional (3D) face modeling system for random-profile-based 3D face recognition is presented. Although recent two-dimensional (2D) face recognition systems can achieve a reliable recognition rate under certain conditions, their performance is limited by internal and external changes, such as illumination and pose variation. To address these issues, 3D face recognition, which uses 3D face data, has recently received much attention. However, the performance of 3D face recognition highly depends on the precision of acquired 3D face data, while also requiring more computational power and storage capacity than 2D face recognition systems. In this paper, we present a developed nonintrusive 3D face modeling system composed of a stereo vision system and an invisible near-infrared line laser, which can be directly applied to profile-based 3D face recognition. We further propose a novel random-profile-based 3D face recognition method that is memory-efficient and pose-invariant. The experimental results demonstrate that the reconstructed 3D face data consists of more than 50 k 3D point clouds and a reliable recognition rate against pose variation.

This paper proposes a 3D face recognition approach using sphere depth image, which is robust to pose variations in unconstrained environments. The input 3D face point clouds is first transformed into sphere depth images, and then represented as a 3DLBP image to enhance the distinctiveness of smooth and similar facial depth images. An improved SIFT algorithm is applied in the following matching process. The improved SIFT algorithm employs the learning to rank approach to select the keypoints with higher stability and repeatability instead of manually rule-based method used by the original SIFT algorithm. The proposed face recognition method is evaluated on CASIA 3D face database. And the experimental results show our approach has superior performance than many existing methods for 3D face recognition and handles pose variations quite well.

Recent researches in three-dimensional (3D) face recognition area have proved that, 3D face recognition methods, achieve better accuracy than its 2D counterpart. One of the main advantages of 3D face recognition methods is that it measures the geometry of rigid features on the human face, due to which it becomes an invariant to illumination, expressions and rotations of head (pose variation). But the main drawback of 3D face recognition methods is the acquisition of 3D face images which generally needs a range camera. It is where the research community is facing difficulty. Research in 3D face recognition also depends on available databases. In this paper, we present a qualitative review of all the available 3D face databases. A comparative table of all the databases is also given at the end with all the necessary parameters.

This paper presents an efficient 3D face recognition method to handle facial expression. The proposed method uses the Surfaces Empirical Mode Decomposition (SEMD), facial curves and local shape descriptor in a matching process to overcome the distortions caused by expressions in faces. The basic idea is that, the face is presented at different scales by SEMD. Then the isometric-invariant features on each scale are extracted. After that, the geometric information is obtained on the 3D surface in terms of radial and level facial curves. Finally, the feature vectors on each scale are associated with their corresponding geometric information. The presented method is validated on GavabDB database resulting a rank 1 recognition rate (RR) of 98.9% for all faces with neutral and non-neutral expressions. This result outperforms other 3D expression-invariant face recognition methods on the same database.

Face recognition has attracted enormous interest from researchers due to its widescale adaptation. However, most of the work in the literature is based on face recognition in controlled environments i.e., high-resolution face images with slight variation in pose, illumination and expression. CNN is used as backbone architecture in the face recognition models. Low-resolution face images having large variations in pose, illumination and expressions make a face recognition problem more challenging. It is difficult to extract discriminative features from low-resolution images. That's why the performance of face recognition models trained on high-resolution images deteriorate on low-resolution images. In this work, quality of low-resolution images is enhanced through multiple super-resolution GANs in order to improve the identification accuracy. Experiments are performed on SCface dataset and the improvement in the identification accuracy shows the effectiveness of using enhanced images generated through super-resolution GANs.

This work presents a method to automatically locate facial feature points under large variations in pose, illumination and facial expressions. First we propose a method to calculate probabilistic-like output for each pixel of image. This probabilistic-like output describes the possibility of the pixel to be the center of specified object. A Gaussian mixture model is used to approximate the distribution of probabilistic-like output. The centers of these Gaussians are assigned with a probabilistic-like measure and they are considered as candidate feature points. There might be one or more candidate feature points in each facial region. A 3D model of facial feature points is built to enforce constraints on the localization results of feature points. Compared with active shape model (ASM) and its variant methods, our method could accommodate larger variations in pose, lighting and face expressions. Moreover, it is less sensitive to initialization errors, accurate, and fast. It takes a computer with P4 CPU about 10 ms to locate the five feature points (two eye centers, two mouth corners and nose tip). The feature localization accuracy is comparable with the accuracy of manually labeled features and it is robust to noise (glasses, beards). Experiments on FERET gallery and PIE are reported in this paper as well.

Face recognition is a challenging task as it has to deal with several issues such as illumination orientation and variability among the different faces. Previous works have shown that 3D face is a robust biometric trait and is less sensitive to light and pose variations. Also due to availability of inexpensive sensors and new 3D data acquisition techniques it has become easy to capture 3D data. A 3D depth image of a face is found to be rich in information and biometric recognition performance can be enhanced by using 3D face data along with convolutional neural network. However the shortcoming of this approach is the conversion of 3D data to lower dimensions (depth image) which suffer from loss of geometric information and the network becomes computationally expensive. In this work we endeavor to apply deep learning method for 3D face recognition and propose a deep convolutional neural network based on PointNet architecture which consumes point cloud directly as input and siamese network for similarity learning. Further we propose a solution to the issue of a limited database by applying data augmentation at the point cloud level. Our proposed technique shows encouraging performance on Bosphorus and IIT Indore 3D face databases.

Face recognition methods, which usually represent face images using holistic or local facial features, rely heavily on alignment. Their performances also suffer a severe degradation under variations in expressions or poses, especially when there is one gallery per subject only. With the easy access to high-resolution (HR) face images nowadays, some HR face databases have recently been developed. However, few studies have tackled the use of HR information for face recognition or verification. In this paper, we propose a pose-invariant face-verification method, which is robust to alignment errors, using the HR information based on pore-scale facial features. A new keypoint descriptor, namely, pore-Principal Component Analysis (PCA)-Scale Invariant Feature Transform (PPCASIFT)-adapted from PCA-SIFT-is devised for the extraction of a compact set of distinctive pore-scale facial features. Having matched the pore-scale features of two-face regions, an effective robust-fitting scheme is proposed for the face-verification task. Experiments show that, with one frontal-view gallery only per subject, our proposed method outperforms a number of standard verification methods, and can achieve excellent accuracy even the faces are under large variations in expression and pose.

In this paper, we propose a discriminative keypoint selection-based 3D face recognition method that is superior to prevalent techniques in terms of both computational complexity and performance. We use the average face model (AFM) for face registration to efficiently locate the axis of symmetry in the rotated face mesh and recover a full frontal face from a 3D face model commonly corrupted due to pose variances. Instead of using the keypoint detection method, we use the feature selection algorithm to find the most discriminant keypoints for face identification and reduce computational time for not only feature extraction but also keypoint matching. The results of the experiments conducted on the Bosphorus database and the UMB-DB show that our algorithm can improve rank-1 identification accuracy, thus confirming its robustness against pose variances, expressions, and occlusions.

Face recognition has been widely used in people’s daily lives due to its contactless process and high accuracy. Existing works can be divided into two categories: global and local approaches. The mainstream global approaches usually extract features on whole faces. However, global faces tend to suffer from dramatic appearance changes under the scenarios of large pose variations, heavy occlusions, and so on. On the other hand, since some local patches may remain similar, they can play an important role in such scenarios. Existing local approaches mainly rely on cropping local patches around facial landmarks and then extracting corresponding local representations. However, facial landmark detection may be inaccurate or even fail, which would limit their applications. To address this issue, attention mechanisms are applied to automatically locate discriminative facial parts, while suppressing noisy parts. Following this motivation, several models are proposed, including: the Local multi-Scale Convolutional Neural Networks (LS-CNN), Hierarchical Pyramid Diverse Attention (HPDA) networks, Contrastive Quality-aware Attentions (CQA-Face), Diverse and Sparse Attentions (DSA-Face), and Attention Augmented Networks (AAN-Face). Firstly, a novel spatial attention (local aggregation networks, LANet) is proposed to adaptively locate useful facial parts. Meanwhile, different facial parts may appear at different scales due to pose variations and expression changes. In order to solve this issue, LS-CNN are proposed to extract discriminative local information at different scales. Secondly, it is observed that some important facial parts may be neglected, if without a proper guidance. Besides, hierarchical features from different layers are not fully exploited which can contain rich low-level and high-level information. To overcome these two issues, HPDA are proposed. Specifically, a diverse learning is proposed to enlarge the Euclidean distances between each two spatial attention maps, locating diverse facial parts. Besides, hierarchical bilinear pooling is adopted to effectively combine features from different layers. Thirdly, despite the decent performance of the HPDA, the Euclidean distance may not be flexible enough to control the distances between each two attention maps. Further, it is also important to assign different quality scores for various local patches because various facial parts contain information with various importance, especially for faces with heavy occlusions, large pose variations, or quality changes. The CQA-Face is proposed which mainly consists of the contrastive attention learning and quality-aware networks where the former proposes a better distance function to enlarge the distances between each two attention maps and the latter applies a graph convolutional network to effectively learn the relations

Existing methods for iris, fingerprint, and 3D face recognition in mobile devices have constraints in terms of price and size owing to their use of additional cameras, lighting, and sensors. Additionally, visible light, camera-based 2D face recognition, palm print recognition, touchless fingerprint recognition, and finger knuckle print recognition are difficult to be used in mobile devices due to limitations in recognition performance and user inconvenience. In response to these problems, studies have been conducted on finger wrinkle recognition in mobile devices; however, image quality is often reduced by motion blurring caused by the movement of the camera or the user's finger, thereby reducing recognition performance. This study proposes a method for restoring and recognizing motion-blurred finger wrinkle images based on a generative adversarial network and deep convolutional neural network. Experiments were performed using two types of finger wrinkle databases, which were custom-made from images of 33 people captured by smart phone cameras (Dongguk mobile finger wrinkle database versions 1 and 2, denoted as DMFW-DB1 and DMFW-DB2, respectively). The results demonstrated high restoration and recognition performance in comparison with the state-of-the-art methods.

One of the challenging problems encountered by face recognition is the difficulty in tackling pose variations, where fast and reliable head pose estimation is an essential step. In this paper, based on the correlation filter technique, a novel feature extraction framework, i.e., directional correlation filter set (DCFS), is developed for robust head pose estimation. In this framework, a principal optimal tradeoff filter (called POTF) is designed in the feature subspace obtained according to principal component analysis (PCA). Compared with the traditional methods that rely on the exact localization of facial feature points, our proposed method exploits the 1D frequency domain of the training data by using the correlation filter technique, which can capture the high-order statistics of a face for effective head pose estimation. Experimental results on several public face databases with large pose variations, including PIE, HPI, and UMIST, show the promising performance obtained by the proposed method on head pose estimation.KeywordsHead pose estimationfeature extractioncorrelation filter

Biometric identification from three-dimensional (3-D) face surface characteristics has become popular. Traditional face recognition methods have achieved very high recognition accuracy under controlled environments. However, 3-D face recognition technology still faces a great challenge for facial expressions and missing data caused by pose variations or occlusions. The mesh-based scale-invariant feature transform (SIFT)-like method is one of the most effective methods to deal with these issues. However, eliminating edge response has not been considered in this kind of method, which affects recognition performance and computation cost. To address this problem, a mesh edge point filter is proposed to remove edge keypoints. For feature description, a local descriptor that is composed of the histogram of geometric shapes and the histogram of shape index is designed to describe local shapes of keypoints. A complete mesh-based SIFT-like framework for 3-D face recognition is also presented. Results from experiments based on the Bosphorus and face recognition grand challenge v2.0 databases show that the proposed method is effective for expression variations, occlusions, and pose variations. Compared with several state-of-the-art methods, the proposed method has obtained a great compromise between computational complexity and recognition performance.

2D Face recognition has been extensively studied for decades and has reached remarkable results in recent years. However, 2D Face recognition is sensitive to variations in poses, facial expressions and illuminations. Depth images provide valuable information to help model facial boundaries and understand the global facial layout and provide low frequency patterns. Intuitively, RGB-D images are more robust to external environments than RGB images. Unfortunately, RGB-D datasets are orders of magnitude smaller than 2D datasets and insufficient to train a deep CNN model as effective as RGB-based models. To tackle these challenges, we present an RGB-D ResNet50 model which can be transferred from a pretrained RGB model and takes RGB-D images as input. We achieved an accuracy of 94.64% and won the \(1^{\text {st}}\) place on 3D Face Recognition Algorithm Challenge, 2019 BenchCouncil International Artificial Intelligence System Challenges.

This paper addresses two LDA problems in face recognition. The first one is small sample size (S3) problem while the second is illumination and pose variations. To overcome the S3 problem, this paper proposes a new method in subspace approach in determining the optimal projection for LDA. Also, an in-depth investigation is conducted on the influence of different illuminations and poses variations. Comparisons with existing LDA-based methods are performed using FERET and Yale Group B face databases. The experimental results show that the proposed method gives the best performance comparing with the existing LDA-based methods for both databases. Moreover, the computational cost of the proposed method is near the same as the existing fastest LDA-based method.