Virtual Face Images Research Articles

Analyzing abnormalities on age attribute in GAN-control

The controllable GAN algorithm has the capability of producing high-quality virtual face images. However, the generated results may not always be of optimal quality. The small changes in the sub-vectors of particular parameters may result in big change in the quality and effect of the face images, such as higher occurrence of face distortions and artefect. This paper mainly aims to investigate the reasons behind the suboptimal performance when we alter the age of the image. To achieve this, we analyze the latent space of the outliers and visualize the distance between the outliers using the PCA algorithm. Additionally, this work introduces noise to each sub-vector to gain insights into the potential reasons for the occurrence of outliers. This paper gave a detailed analysis on the inharmonious performance of different features in the latent space, and provided an aspect on the future improvement work in the face synthesis by controllable GAN algorithm.

A Novel Face Super-Resolution Method Based on Parallel Imaging and OpenVINO

Face image super-resolution refers to recovering a high-resolution face image from a low-resolution one. In recent years, due to the breakthrough progress of deep representation learning for super-resolution, the study of face super-resolution has become one of the hot topics in the field of super-resolution. However, the performance of these deep learning-based approaches highly relies on the scale of training samples and is limited in efficiency in real-time applications. To address these issues, in this work, we introduce a novel method based on the parallel imaging theory and OpenVINO. In particular, inspired by the methodology of learning-by-synthesis in parallel imaging, we propose to learn from the combination of virtual and real face images. In addition, we introduce a center loss function borrowed from the deep model to enhance the robustness of our model and propose to apply OpenVINO to speed up the inference. To the best of our knowledge, it is the first time to tackle the problem of face super-resolution based on parallel imaging methodology and OpenVINO. Extensive experimental results and comparisons on the publicly available LFW, WebCaricature, and FERET datasets demonstrate the effectiveness and efficiency of the proposed method.

Auxiliary Dictionary of Diversity Learning for Face Recognition with a Single Sample Per Person

Face recognition for a single sample per person is challenging due to the lack of sufficient sample information. However, using generic training set to learn an auxiliary dictionary is an effective way to alleviate this problem. Considering generic training sample of diversity, we proposed an algorithm of auxiliary dictionary of diversity learning (ADDL). We first produced virtual face images by mirror images, square block occlusion and grey transform, and then learned an auxiliary dictionary of diversity using a designed objective function. Considering patch-based method can reduce the influence of variations, we seek extended sparse representation with l2-minimization for each probe patch. Experimental results in the CMUPIE, Extended Yale B and LFW datasets demonstrate that ADDL performs better than other related algorithms.

Compound dictionary learning based classification method with a novel virtual sample generation Technology for Face Recognition

Face recognition has earned its high reputation for many years since its considerable advances. However, it is still faced with the challenge of the small sample size problem. With the inspiration of the axis-symmetrical property of human faces, we propose a novel virtual sample synthesis strategy to address the issue of limited training samples. It is noteworthy that the novel algorithm can produce symmetry-based virtual face images, in which the pixels in symmetric parts of the face image were exchanged. And it is mathematically very tractable and quite easy to implement. In addition, considering the fact that dictionary learning (DL) based classification methods have excellent learning ability, we incorporate the virtual samples to learn virtual dictionary so as to enhance the accuracy of face recognition. Differing from conventional learning algorithms, the proposed method provides new insights into two crucial parts. Firstly, it proposes an originally creative idea and algorithm to automatically generate symmetry-based virtual samples and obtain virtual dictionary. Secondly, the original dictionary and virtual dictionary are integrated to construct the compound dictionary learning based classification in the way of adaptive weighted fusion. In this paper, we take the axis-symmetrical nature of faces into consideration and design a framework to generate compound dictionary, where more satisfactory classification accuracy can be achieved than the original dictionary learning methods, referred as, the locality-constrained and label embedding dictionary learning (LCLE-DL). Moreover, the experimental results demonstrate the superior performance of the proposed method in comparison with state-of-the-art dictionary learning methods.

A Face Image Virtualization Mechanism for Privacy Intrusion Prevention in Healthcare Video Surveillance Systems

Closed-circuit television (CCTV) and video surveillance systems (VSSs) are becoming increasingly more common each year to help prevent incidents/accidents and ensure the security of public places and facilities. The increased presence of VSS is also increasing the number of per capita exposures to CCTV cameras. To help protect the privacy of the exposed objects, attention is being drawn to technologies that utilize intelligent video surveillance systems (IVSSs). IVSSs execute a wide range of surveillance duties—from simple identification of objects in the recorded video data, to understanding and identifying the behavioral patterns of objects and the situations at the incident/accident scenes, as well as the processing of video information to protect the privacy of the recorded objects against leakage. Besides, the recorded privacy information is encrypted and recorded using blockchain technology to prevent forgery of the image. The technology herein proposed (the “proposed mechanism”) is implemented to a VSS, where the mechanism converts the original visual information recorded on a VSS into a similarly constructed image information, so that the original information can be protected against leakage. The face area extracted from the image information is recorded in a separate database, allowing the creation of a restored image that is in perfect symmetry with the original image for images with virtualized face areas. Specifically, the main section of this study proposes an image modification mechanism that inserts a virtual face image that closely matches a predetermined similarity and uses a blockchain as the storage area.

A New Virtual Samples-Based CRC Method for Face Recognition

The research of automatic face recognition has attracted much attention from many researchers because of human faces’ uniqueness and usability. However, in the real-world applications, the acquisition equipment of face images is affected by illumination changes, facial expression variations, different postures and other environment factors, resulting in limited number of face images collected. This situation has become an obstacle to the development of face recognition technology. Therefore, in this paper, we utilize the information of the left-half face and right-half face to generate respectively two virtual ‘axis-symmetrical’ face images from an original face image and adopt collaborative representation based classification method (CRC) to perform classification. The first and second virtual face images convey more information of the right-half face and left-half face, respectively. Experiments have been performed on the Extended Yale_B, ORL, AR and FERET face databases and the experimental results show that our method can improve the recognition accuracy effectively.

Undersampled face recognition based on virtual samples and representation classification

Classifiers such as sparse representation or collaborative representation can get good performance in face recognition. But these methods require a number of train samples in each class to construct the dictionary. On the condition of undersampled train samples, their performance decreases dramatically. A novel method is proposed in this paper to address undersampled face recognition problem. Firstly, virtual face images are generated by principal component analysis and mirror transform. Secondly, the test sample is collaboratively represented by the augmented train samples and is recognized by classifier based on representation. A number of face recognition experiments on three benchmark face database show that the recognition accuracy of our method is greater than that of a similar method, while time efficiency of our method is competitive to similar method.

A survey of virtual sample generation technology for face recognition

Despite considerable advances made in face recognition in recent years, the recognition performance still suffers from insufficient training samples. Hence, various algorithms have been proposed for addressing the problems of small sample size with dramatic variations in illuminations, poses and facial expressions in face recognition. Among these algorithms, the virtual sample generation technology achieves promising performance with reasonable and effective mathematical function and easy implementation. In this paper, we systematically summarize the research progress in the virtual sample generation technology for face recognition and categorize the existing methods into three groups, namely, (1) construction of virtual face images based on the face structure; (2) construction of virtual face images based on the idea of perturbation and distribution function of samples; (3) construction of virtual face images based on the sample viewpoint. We carry out thorough and comprehensive comparative study in which different methods are compared by conducting an in-depth analysis on them. It demonstrates the significant advantage of combining the virtual sample generation technology with representation based methods.

Sample diversity, representation effectiveness and robust dictionary learning for face recognition

Conventional dictionary learning algorithms suffer from the following problems when applied to face recognition. First, since in most face recognition applications there are only a limited number of original training samples, it is difficult to obtain a reliable dictionary with a large number of atoms from these samples. Second, because the face images of the same person vary with facial poses and expressions as well as illumination conditions, it is difficult to obtain a robust dictionary for face recognition. Thus, obtaining a robust and reliable dictionary is a crucial key to improve the performance of dictionary learning algorithms for face recognition. In this paper, we propose a novel dictionary learning framework to achieve this. The proposed algorithm framework takes training sample diversities of the same face image into account and tries to obtain more effective representations of face images and a more robust dictionary. It first produces virtual face images and then designs an elaborate objective function. Based on this objective function, we obtain a mathematically tractable and computationally efficient algorithm to generate a robust dictionary. Experimental results demonstrate that the proposed algorithm framework outperforms some previous state-of-the-art dictionary learning and sparse coding algorithms in face recognition. Moreover, the proposed algorithm framework can also be applied to other pattern classification tasks.

Approximately symmetrical face images for image preprocessing in face recognition and sparse representation based classification

Though most of the faces are axis-symmetrical objects, few real-world face images are axis-symmetrical images. In the past years, there are many studies on face recognition, but only little attention is paid to this issue and few studies to explore and exploit the axis-symmetrical property of faces for face recognition are conducted. In this paper, we take the axis-symmetrical nature of faces into consideration and design a framework to produce approximately axis-symmetrical virtual dictionary for enhancing the accuracy of face recognition. It is noteworthy that the novel algorithm to produce axis-symmetrically virtual face images is mathematically very tractable and quite easy to implement. Extensive experimental results demonstrate the superiority in face recognition of the virtual face images obtained using our method to the original face images. Moreover, experimental results on different databases also show that the proposed method can achieve satisfactory classification accuracy in comparison with state-of-the-art image preprocessing algorithms. The MATLAB code of the proposed method can be available at http://www.yongxu.org/lunwen.html.

Generating virtual training samples for sparse representation of face images and face recognition

There are many challenges in face recognition. In real-world scenes, images of the same face vary with changing illuminations, different expressions and poses, multiform ornaments, or even altered mental status. Limited available training samples cannot convey these possible changes in the training phase sufficiently, and this has become one of the restrictions to improve the face recognition accuracy. In this article, we view the multiplication of two images of the face as a virtual face image to expand the training set and devise a representation-based method to perform face recognition. The generated virtual samples really reflect some possible appearance and pose variations of the face. By multiplying a training sample with another sample from the same subject, we can strengthen the facial contour feature and greatly suppress the noise. Thus, more human essential information is retained. Also, uncertainty of the training data is simultaneously reduced with the increase of the training samples, which is beneficial for the training phase. The devised representation-based classifier uses both the original and new generated samples to perform the classification. In the classification phase, we first determine K nearest training samples for the current test sample by calculating the Euclidean distances between the test sample and training samples. Then, a linear combination of these selected training samples is used to represent the test sample, and the representation result is used to classify the test sample. The experimental results show that the proposed method outperforms some state-of-the-art face recognition methods.

User Authorization Method based on Face Recognition for Auto Network Access in Home Network System

Security is very important under home network environment that provides trustworthy services afterpersonal information authentication. Especially, reliable user authentication technology is needed toprovide various tailored smart services for individual users at a home network system. This papersuggests a user authentication technique using long-distance face recognition to provide a safe homenetwork service. For the long distance face recognition test, face images by actual distance from 1m-5m away were obtained directly. Both actual and virtual face images taken by distance were appliedto resolve the issue rising from distance change while histogram equalization and MCT were used asa preprocessing to address the illumination change. The test result showed that an LDA-based facerecognition algorithm that used histogram equalization as a preprocessing and face images by actualdistance for training was found to show the best performance, so it is expected to be applicable foruser authorization of home network system.

Producing virtual face images for single sample face recognition

For single sample face recognition, there are limited training samples, so the traditional face recognition methods are not applicable to this problem. In this paper we propose to combine two methods to produce virtual face images for single sample face recognition. We firstly use a symmetry transform to produce symmetrical face images. We secondly use the linear combination of two samples to generate virtual samples. As a result, we convert the special single sample problem into a non-single sample problem. We then use the 2DPCA method to extract features from the samples and use the nearest neighbor classifier to perform classification. Experimental results show that the proposed method can effectively improve the recognition rate of single sample face recognition.

Subspace Based Face Recognition on Hypercomplex Field

Color information is very important cues for recognition task. In this paper, a novel color face recognition approach based on subspace is proposed. The approach employs hypercomplex to encode color information of different channels simultaneously. Hypercomplex matrix decomposition is then used to construct feature extraction approach. To improve learning efficiency of the algorithm, 3D active deformable model is exploited to generate virtual color face images. Experimental results on CMU PIE database verify the effectiveness of the proposed approach.

Class Dependent Face Recognition with 3D Deformable Model

Both class information of face subjects and color information of face images are very important cues for recognition. In this paper, a novel class dependent color face recognition approach based on block diagonal discriminant NMF is proposed. The approach employs block diagonal matrix to encode color information of face images simultaneously. Block diagonal constraint is imposed on discriminant NMF algorithm to construct feature extraction approach, which fuses class and color information at the same time into the extracted facial features. To improve learning efficiency of the algorithm, 3D active deformable model is exploited to generate virtual face images. Experimental results on CVL and CMU PIE face databases verify the effectiveness of the proposed approach.

2D face fitting-assisted 3D face reconstruction for pose-robust face recognition

Recent face recognition algorithm can achieve high accuracy when the tested face samples are frontal. However, when the face pose changes largely, the performance of existing methods drop drastically. Efforts on pose-robust face recognition are highly desirable, especially when each face class has only one frontal training sample. In this study, we propose a 2D face fitting-assisted 3D face reconstruction algorithm that aims at recognizing faces of different poses when each face class has only one frontal training sample. For each frontal training sample, a 3D face is reconstructed by optimizing the parameters of 3D morphable model (3DMM). By rotating the reconstructed 3D face to different views, pose virtual face images are generated to enlarge the training set of face recognition. Different from the conventional 3D face reconstruction methods, the proposed algorithm utilizes automatic 2D face fitting to assist 3D face reconstruction. We automatically locate 88 sparse points of the frontal face by 2D face-fitting algorithm. Such 2D face-fitting algorithm is so-called Random Forest Embedded Active Shape Model, which embeds random forest learning into the framework of Active Shape Model. Results of 2D face fitting are added to the 3D face reconstruction objective function as shape constraints. The optimization objective energy function takes not only image intensity, but also 2D fitting results into account. Shape and texture parameters of 3DMM are thus estimated by fitting the 3DMM to the 2D frontal face sample, which is a non-linear optimization problem. We experiment the proposed method on the publicly available CMUPIE database, which includes faces viewed from 11 different poses, and the results show that the proposed method is effective and the face recognition results toward pose variants are promising.

A Low-dimensional Illumination Space Representation of Human Faces for Arbitrary Lighting Conditions

The proposed method for low-dimensional illumination space representation (LDISR) of human faces can not only synthesize a virtual face image when given lighting conditions but also estimate lighting conditions when given a face image. The LDISR is based on the observation that 9 basis point light sources can represent almost arbitrary lighting conditions for face recognition application and different human faces have a similar LDISR. The principal component analysis (PGA) and the nearest neighbor clustering method are adopted to obtain the 9 basis point light sources. The 9 basis images under the 9 basis point light sources are then used to construct an LDISR which can represent almost all face images under arbitrary lighting conditions. Illumination ratio image (IRI) is employed to generate virtual face images under different illuminations. The LDISR obtained from face images of one person can be used for other people. Experimental results on image reconstruction and face recognition indicate the efficiency of LDISR.

Dynamic Analysis of Facial Color and Synthesis for the Virtual Face Image under Fearful Emotion

Dynamic Analysis of Facial Color and Synthesis for the Virtual Face Image under Fearful Emotion

VIEW SYNTHESIS UNDER PERSPECTIVE PROJECTION

This paper addresses the issue of generating a 2D view of a 3D object from its other 2D views. Linear Combination method is the typical approach to this problem. However, a 2D view cannot be represented by a linear combination of other 2D views under perspective projection. Instead, we have presented a solution under perspective projection. The proposed method also applies to the construction of virtual frontal view face image and the results are encouraging.

Facial Color Image Analysis and Synthesis for the Virtual Face Image in Emotional Change.

Human facil color can be applied to the display of virtual face image, emotional evaluation, individual identification, and remote health care. We already developed a method for emphasizing the individual characteristics in facial color based on a virtual face image using the HSV (hue, saturation, value) color space. To make virtual face images more natural and richer, the clarification of the relation between facial color and emotion would be expected. In this paper, we propose a synthetic method for the virtual face image based on the analysis of facial color in emotional change. First, the facial colors under the emotion of joy or anger are determined quantitatively by using the HSV color space. Secondly, we examined the relation between the facial color and the physiological index of facial skin temperature, which indicates the change of blood flux, in drinking for the emotion of joy. Also, we examined the relation between the change of facial color and that of skin temperature under the joy in laughing. Finally, on the basis of these results, we synthesized seven enhanced facial color images based on an average facial color image from 68 females, and evaluated the effectiveness of these images through sensory evaluation by paired comparison.