3D Face Recognition Research Articles

Learning Descriptors Invariance through Equivalence Relations within Manifold: A New Approach to Expression Invariant 3D Face Recognition

This paper presents a unique approach for the dichotomy between useful and adverse variations of key-point descriptors, namely the identity and the expression variations in the descriptor (feature) space. The descriptors variations are learned from training examples. Based on labels of the training data, the equivalence relations among the descriptors are established. Both types of descriptor variations are represented by a graph embedded in the descriptor manifold. Invariant recognition is then conducted as a graph search problem. A heuristic graph search algorithm suitable for the recognition under this setup was devised. The proposed approach was tested on the FRGC v2.0, the Bosphorus and the 3D TEC datasets. It has shown to enhance the recognition performance, under expression variations, by considerable margins.

Mesh-based scale-invariant feature transform-like method for three-dimensional face recognition under expressions and missing data

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.

A new method for protein characterization and classification using geometrical features for 3D face analysis: An example of tubulin structures.

This article reports on the results of research aimed to translate biometric 3D face recognition concepts and algorithms into the field of protein biophysics in order to precisely and rapidly classify morphological features of protein surfaces. Both human faces and protein surfaces are free-forms and some descriptors used in differential geometry can be used to describe them applying the principles of feature extraction developed for computer vision and pattern recognition. The first part of this study focused on building the protein dataset using a simulation tool and performing feature extraction using novel geometrical descriptors. The second part tested the method on two examples, first involved a classification of tubulin isotypes and the second compared tubulin with the FtsZ protein, which is its bacterial analog. An additional test involved several unrelated proteins. Different classification methodologies have been used: a classic approach with a support vector machine (SVM) classifier and an unsupervised learning with a k-means approach. The best result was obtained with SVM and the radial basis function kernel. The results are significant and competitive with the state-of-the-art protein classification methods. This leads to a new methodological direction in protein structure analysis.

SpPCANet: a simple deep learning-based feature extraction approach for 3D face recognition

Abstract A Sparse Principal Component Analysis Network (SpPCANet) based feature extraction is proposed here for 3D face recognition. The network consists of three basic components: (1) Multistage sparse principal component analysis filters, (2) Binary hashing, and (3) Block-wise histogram computation. Here, the sparse principal component analysis is used to learn multistage filter banks at the convolution stage, which is followed by binary hashing for indexing and block-wise histogram for pooling. Finally, a linear support vector machine (SVM) is used for classifying the features extracted by SpPCANet. The proposed network SpPCANet is a lightweight deep learning network. Three well-known 3D face databases, namely, Frav3D, Bosphorus3D, and Casia3D, are used for validating the proposed system. This proposed network has been extensively studied by varying different parameters, such as the number of filters at the convolution layer and the size of filters at the convolution layer and size of non-overlapping blocks at the pooling layer. Handling all types of variation of faces available in Frav3D, Bosphorus3D, and Casia3D databases, the system has acquired 96.93%, 98.54%, and 88.80% recognition rates, respectively.

Low-threshold, single-transverse-mode, 940-nm vertical-cavity surface-emitting laser with a mode filter and half-wavelength cavity

We demonstrate a structure for a vertical-cavity surface-emitting laser (VCSEL) with a mode filter and half-wavelength (λ/2) cavity. The effects of λ/2- and λ-cavities on the threshold current are studied. The thickness and etched diameter of the mode filter are optimised to achieve single-transverse-mode output. The results show that when changing from λ-cavity to λ/2-cavity, the threshold current of the VCSEL decreases by 30.7% (from 0.85 mA to 0.65 mA). In addition, for the mode-filter thickness of 80 nm, and the etched diameter of 2.5 μm, the side mode suppression ratio reaches 90 dB, which meets the requirement of single-transverse-mode output. The VCSELs with the optimised design can overcome many difficulties and have great potential in 3D face recognition.

Past, Present, and Future of Face Recognition: A Review

Face recognition is one of the most active research fields of computer vision and pattern recognition, with many practical and commercial applications including identification, access control, forensics, and human-computer interactions. However, identifying a face in a crowd raises serious questions about individual freedoms and poses ethical issues. Significant methods, algorithms, approaches, and databases have been proposed over recent years to study constrained and unconstrained face recognition. 2D approaches reached some degree of maturity and reported very high rates of recognition. This performance is achieved in controlled environments where the acquisition parameters are controlled, such as lighting, angle of view, and distance between the camera–subject. However, if the ambient conditions (e.g., lighting) or the facial appearance (e.g., pose or facial expression) change, this performance will degrade dramatically. 3D approaches were proposed as an alternative solution to the problems mentioned above. The advantage of 3D data lies in its invariance to pose and lighting conditions, which has enhanced recognition systems efficiency. 3D data, however, is somewhat sensitive to changes in facial expressions. This review presents the history of face recognition technology, the current state-of-the-art methodologies, and future directions. We specifically concentrate on the most recent databases, 2D and 3D face recognition methods. Besides, we pay particular attention to deep learning approach as it presents the actuality in this field. Open issues are examined and potential directions for research in facial recognition are proposed in order to provide the reader with a point of reference for topics that deserve consideration.

Voxel-based 3D occlusion-invariant face recognition using game theory and simulated annealing

A novel voxel-based occlusion-invariant 3D face recognition framework (V3DOFR) based on game theory and simulated annealing is proposed. In V3DOFR approach, 3D meshes are converted to voxel form of sizes 43, 83, and 163. After that, locality preserving projection-based embeddings are computed for removing the sparseness of voxels and generating consistent linear embedding per mesh with size 64????????3, 128????????3, and 256????????3, respectively. The generator of triplets provides the triplets of sizes 64x3x3, 128x3x3, and 256x3x3. The simulated annealing is used to check the threshold value of adversarial triplet loss generated after ensembling losses of different grid sizes. The proposed framework is compared with four well-known methods using three face datasets, namely, Bosphorus, UMBDB, and KinectFaceDB. The performance evaluation has been done using four different cases of experimentations, viz. voxel based face recognition, occlusion invariant face recognition, landmarks based 3D face recognition, and 3D mesh based face recognition. Seven evaluation metrics are used to compare the proposed technique with other methods. The proposed method provides better accuracy and computation time over the other existing techniques in the majority of cases.

Research on 3D face recognition method based on LBP and SVM

In order to improve the accuracy and speed of three-dimensional face recognition, this paper proposes a three-dimensional face recognition method combining LBP and SVM. First, the LBP algorithm is used to extract the feature information of the three-dimensional face depth image, then the SVM algorithm is used to classify the feature information. By selecting samples in the Texas 3DFRD three-dimensional face depth database and the self-made depth database, the experiment proves that the algorithm has a better recognition rate and shorter time consumption.

Point cloud based deep convolutional neural network for 3D face recognition

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 by Reconstructing A 2.5 D Face using Photometric Stereo

Face recognition is an important application of image analysis and it has received a lot of interest in the last decade. There is a critical need for a reliable identification system. As of now, face recognition is not reliable enough in the majority of security applications, therefore a low cost, accurate, and viable identification method are required for face recognition. Two dimensional (2D) face recognition systems that are already existing are often not reliable. Three dimensional (3D) face recognition systems produce more accurate and robust than 2D systems but they are very costly due to large scanning and coded light and also consume a lot of time in the recognition process. This paper aims to produce a low-cost 3D face recognition system (2.5D) using photometric stereo which is less explored in face recognition systems. The capabilities of photometric stereo for use in face recognition are evaluated using a number of experiments conducted using the photometric stereo system and it is implemented and shown to be better than our traditional 2D systems. This system is aimed to solve a number of issues we see in face recognition systems like illumination, distance from the camera and pose and thus, it could be a useful application for biometric authentications in homes, governmental organizations and financial institutions

A multi-scale three-dimensional face recognition approach with sparse representation-based classifier and fusion of local covariance descriptors

In this paper, an efficient multi-scale hybrid approach is proposed to tackle two main problems in three-dimensional (3D) face recognition, namely the singularity of scale features representation and underexplored locality in dictionary learning. The multi-scale features space representation is developed based on the new 3D faces generated by the Gaussian filter. The locality-sensitive Riemannian sparse representation-based classifier is also constructed to accurately recognize faces with various expressions, poses and occlusions. Two sets of face recognition experiment, one that includes expression variations, and the another that includes pose and occlusion variations, are conducted to compare the performance of the proposed approach against other benchmark 3D face recognition algorithms. The recognition accuracies of the proposed algorithm to both Neutral vs. Neutral achieved on Face Recognition Grand Challenge (FRGC) v2.0 database and Bosphorus database are 100%.

Deep 3D Facial Landmark Localization on position maps

3D facial landmark detection is a crucial step for many computer vision applications, such as 3D facial expression analysis, 3D face recognition, and 3D cephalometry. Pose variations, expression changes and self-occlusion yet make 3D facial landmark detection a very challenging task. In this paper, we propose a novel 3D Facial Landmark Localization Network (3DLLN), which is robust to the above challenges. Different from existing methods, the proposed 3DLLN utilizes the position maps as an intermediate representation, from which 3DLLN detects 3D landmark coordinates. Further, we demonstrate the usage of a deep regression architecture to improve the accuracy and robustness of a large number of landmarks. The proposed scheme is evaluated on two public datasets FRGCv2 subset and BU-3DFE, and is shown to achieve state-of-the-art results.

Differential 3D Facial Recognition: Adding 3D to Your State-of-the-Art 2D Method.

Active illumination is a prominent complement to enhance 2D face recognition and make it more robust, e.g., to spoofing attacks and low-light conditions. In the present work we show that it is possible to adopt active illumination to enhance state-of-the-art 2D face recognition approaches with 3D features, while bypassing the complicated task of 3D reconstruction. The key idea is to project over the test face a high spatial frequency pattern, which allows us to simultaneously recover real 3D information plus a standard 2D facial image. Therefore, state-of-the-art 2D face recognition solution can be transparently applied, while from the high frequency component of the input image, complementary 3D facial features are extracted. Experimental results on ND-2006 dataset show that the proposed ideas can significantly boost face recognition performance and dramatically improve the robustness to spoofing attacks.

A Literature Review of 2D Face Recognition Systems: Attacks and Defenses

Abstract:
 In a world where biometric identification and authentication is increasingly growing, it is critical for IT Security personnel to have an understanding of how these systems they use work, and weaknesses that lay with them. Face recognition is a very common form of biometric identification and authentication, where the face of the user is used to both identify and authenticate the user. This paper serves as a literature review for a preliminary understanding of face recognition systems. First the basics of how a facial recognition system works is reviewed. After this, selected articles demonstrating a variety of facial recognition spoofing attacks are summarized to demonstrate the attack surface. This is then followed by a review of studies conducted for defenses against these attacks, focusing primarily on the key concepts used to help identify spoofing attempts. This paper then concludes by summarizing the findings, and explaining the importance of understanding these different aspects of facial recognition from a business perspective.

ALCN: Adaptive Local Contrast Normalization

To make Robotics and Augmented Reality applications robust to illumination changes, the current trend is to train a Deep Network with training images captured under many different lighting conditions. Unfortunately, creating such a training set is a very unwieldy and complex task. We therefore propose a novel illumination normalization method that can easily be used for different problems with challenging illumination conditions. Our preliminary experiments show that among current normalization methods, the Difference-of-Gaussians method remains a very good baseline, and we introduce a novel illumination normalization model that generalizes it. Our key insight is then that the normalization parameters should depend on the input image, and we aim to train a Convolutional Neural Network to predict these parameters from the input image. This, however, cannot be done in a supervised manner, as the optimal parameters are not known a priori. We thus designed a method to train this network jointly with another network that aims to recognize objects under different illuminations: The latter network performs well when the former network predicts good values for the normalization parameters. We show that our method significantly outperforms standard normalization methods and would also be appear to be universal since it does not have to be re-trained for each new application. Our method improves the robustness to light changes of state-of-the-art 3D object detection and face recognition methods.

Voxel-based 3D face reconstruction and its application to face recognition using sequential deep learning

In this paper, a novel 3D face reconstruction technique is proposed along with a sequential deep learning-based framework for face recognition. It uses the voxels generated from the voxelization process. It uses the reflection principle for generating the reconstructed point in 3D using the mid-face plane. From the reconstructed face, a sequential deep learning framework is developed to recognize gender, emotion, occlusion, and person. The developed framework utilizes the concepts of variational autoencoders, bidirectional long short-term memory, and triplet loss training. The sequential deep learning model extracts and refines the reconstructed voxels by generating deep features. The support vector machine is applied to deep features for the final prediction. The proposed 3D face recognition system is compared with the three well-known deep learning approaches over three occluded datasets. Experimental results show that the proposed 3D face recognition technique is invariant to occlusion and facial expression. The proposed technique recognizes the gender with accuracy of 97.28%, 92.12%, and 94.44%, emotion with accuracy of 94.57%, 87.78%, and 89.95%, occlusion with accuracy of 94.02%, 81.26%, and 89.85% and person face with accuracy of 90.01%, 78.21%, and 85.68% for Bosphorus, UMBDB and KinectFaceDB datasets respectively. The proposed framework performs better than state-of-the-art approaches in terms of computational time as well as face recognition accuracy.

A New Face Recognition Method for Intelligent Security

With the advent of the era of artificial intelligence and big data, intelligent security robots not only improve the efficiency of the traditional intelligent security industry but also propose higher requirements for intelligent security. Aiming to solve the problem of long recognition time and high equipment cost of intelligent security robots, we propose a new face recognition method for intelligent security in this paper. We use the Goldstein branching method for phase unwrapping, which can improve the three-dimensional (3D) face reconstruction effect. Subsequently, by using the three-dimensional face recognition method based on face radial curve elastic matching, different weights are assigned to different curve recognition similarity for weighted fusion as the total similarity for recognition. Experiments show that the method has a higher face recognition rate and is robust to attitude, illumination, and noise.

Landmark-based homologous multi-point warping approach to 3D facial recognition using multiple datasets.

Over the years, neuroscientists and psychophysicists have been asking whether data acquisition for facial analysis should be performed holistically or with local feature analysis. This has led to various advanced methods of face recognition being proposed, and especially techniques using facial landmarks. The current facial landmark methods in 3D involve a mathematically complex and time-consuming workflow involving semi-landmark sliding tasks. This paper proposes a homologous multi-point warping for 3D facial landmarking, which is verified experimentally on each of the target objects in a given dataset using 500 landmarks (16 anatomical fixed points and 484 sliding semi-landmarks). This is achieved by building a template mesh as a reference object and applying this template to each of the targets in three datasets using an artificial deformation approach. The semi-landmarks are subjected to sliding along tangents to the curves or surfaces until the bending energy between a template and a target form is minimal. The results indicate that our method can be used to investigate shape variation for multiple datasets when implemented on three databases (Stirling, FRGC and Bosphorus).

GAN-Based Blur Restoration for Finger Wrinkle Biometrics System

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.

结合局部关键点集与测地线的三维人脸识别

结合局部关键点集与测地线的三维人脸识别