具有真实感的三维虚拟特定人脸生成方法

三维人脸的计算机生成目前是一个具有挑战性的课题。如何在人脸复杂的、不规则的表面上建模以及如何反映出特定人脸间的个体差异是现真实人脸模拟的两大主要困难所在。本文针对后者,提出了一种新的三维特定人脸生成方法,该方法基于人脸模型变形技术,允许模拟者在交互方式下将一般人脸几何模型和豫先提供的特定人脸多方面图像之间进形特征校准,进而得到特定人脸三维模型,该模型将精确地反映特定人脸的诸特征,同时,这种变形技术     

Video-to-video face authentication system robust to pose variations

High-quality still-to-still (image-to-image) face authentication has shown success under controlled conditions in many safety applications. However, video-to-video face authentication is still challenging due to appearance variations caused by pose changes. In this paper, we propose a video-to-video face authentication system that is robust to pose variations by making use of synthesized frontal face appearance that contains both texture and shape information. To obtain the appearance, we first reconstruct 3D face shape from face feature points detected from the video using active shape model (ASM). Conventional ASM algorithms cannot handle large pose variations and fast head movement exhibited in video sequences. To address these problems, we present a novel prediction-assisted approach that is capable of providing an accurate shape initiation as well as automatically switching on multi-view models for ASM. Then we can generate frontal shape mesh from the reconstructed 3D face shape. Based on the mesh, we synthesize frontal face appearance with the ASM-detected faces in video. For authentication, in order to match the synthesized appearances of enrollment and probe, we propose a 2-directional 2-dimensional client specific fisher’s linear discriminant algorithm. The proposed algorithm is a variant of fisher’s linear discriminant (FLD) and directly computes eigenvectors of image scatter matrices in row and column direction without matrix-to-vector conversion. In experiments, our authentication system is compared with the other state-of-art approaches on public face database and our face database. The results show that our system demonstrates a higher authentication accuracy and pose-robust performance.     

单幅人脸图像的全景纹理图生成方法

目的 针对从单幅人脸图像中恢复面部纹理图时获得的信息不完整、纹理细节不够真实等问题,提出一种基于生成对抗网络的人脸全景纹理图生成方法。方法 将2维人脸图像与3维人脸模型之间的特征关系转换为编码器中的条件参数,从图像数据与人脸条件参数的多元高斯分布中得到隐层数据的概率分布,用于在生成器中学习人物的头面部纹理特征。在新创建的人脸纹理图数据集上训练一个全景纹理图生成模型,利用不同属性的鉴别器对输出结果进行评估反馈,提升生成纹理图的完整性和真实性。结果 实验与当前最新方法进行了比较,在CelebA-HQ和LFW （labled faces in the wild）数据集中随机选取单幅正面人脸测试图像,经生成结果的可视化对比及3维映射显示效果对比,纹理图的完整度和显示效果均优于其他方法。通过全局和面部区域的像素量化指标进行数据比较,相比于UVGAN,全局峰值信噪比（peak signal to noise ratio,PSNR）和全局结构相似性（structural similarity index,SSIM）分别提高了7.9 dB和0.088,局部PSNR和局部SSIM分别提高了2.8 dB和0.053;相比于OSTeC,全局PSNR和全局SSIM分别提高了5.45 dB和0.043,局部PSNR和局部SSIM分别提高了0.4 dB和0.044;相比于MVF-Net （multi-view 3D face network）,局部PSNR和局部SSIM分别提高了0.6和0.119。实验结果证明,提出的人脸全景纹理图生成方法解决了从单幅人脸图像中重建面部纹理不完整的问题,改善了生成纹理图的显示细节。结论 本文提出的人脸全景纹理图生成方法,利用人脸参数和网络模型的特性,使生成的人脸纹理图更完整,尤其是对原图不可见区域,像素恢复自然连贯,纹理细节更真实。     

Face recognition based on fitting a 3D morphable model

This paper presents a method for face recognition across variations in pose, ranging from frontal to profile views, and across a wide range of illuminations, including cast shadows and specular reflections. To account for these variations, the algorithm simulates the process of image formation in 3D space, using computer graphics, and it estimates 3D shape and texture of faces from single images. The estimate is achieved by fitting a statistical, morphable model of 3D faces to images. The model is learned from a set of textured 3D scans of heads. We describe the construction of the morphable model, an algorithm to fit the model to images, and a framework for face identification. In this framework, faces are represented by model parameters for 3D shape and texture. We present results obtained with 4,488 images from the publicly available CMU-PIE database and 1,940 images from the FERET database.     

基于图像的人脸美感初探

在关系数据库中,为了实现以人脸图像为关键字段进行升序或降序排列,对计算机自动评析人脸的漂亮程度进行了初步探讨。采用主动表观模型提取人脸特征,将提取到的特征分为公共特征及私有特征两部分,公共特征用于识别性别,私有特征完成两块功能:计算三庭五眼比例值,获取人脸纹理信息。利用私有特征评析人脸的漂亮程度,用BP神经网络分类器在自建的OID人脸库中进行了实验,取得的效果与人类视觉审美相一致。不仅实现了对于单一测试者能输出确切的结果,而且对于多个测试者,能实现首先按性别分类,相同性别的测试者可依漂亮程度自动排序。     

一种基于左右斜侧面照片的三维人脸重建方法*

创建逼真的三维人脸模型一直以来都是计算机图形学领域一个极富有挑战性的课题。利用左右斜侧面照片生成具有纹理信息的三维人脸。分别对两张左右斜侧面人脸照片通过纹理三角剖分和仿射变换映射至标准纹理模板,再利用计算机视觉和facegen生成的人脸数据库上应用中的算法生成一个三维真实几何模型,最后将纹理映射三维模型生成具有纹理信息的三维人脸。结果表明方法的合成结果与真实人脸在模型以及纹理方面具有较好的相似性。     

利用采样球体提取真实感纹理

提出了一种从真实物体中提取纹理的方法.利用具有复杂纹理的参考球体作为被采样物体,计算其组成材质的BRDF(bidirectional reflectance distribution function)模型参数以及各点由不同材质构成的比例,形成一幅材质权重图.该图作为纹理映射到3D物体上后,配合BRDF模型参数进行渲染,形成一种适用于重光照(relighting)的纹理.被渲染物体可根据自身方位以及光源亮度/方位呈现出自然的光影变化,达到较为逼真的外观效果.     

基于一般人脸模型修改的特定人脸合成技术

目前计算机模拟领域中的人脸合成技术由于其广泛的应用前景得到了越来越多的重视,它可以用于人们语言感知模型研究、虚拟环境、通信技术、辅助教学、医疗研究、电影制作、游戏娱乐等诸多方面。由于在实现中人脸的千差万别,使一般人脸模型的个体化成为人脸合成中的一项关键技术。个体人脸的差异主要表现在不同的面部几何特征和纹理特征两方面。针对这两方面,在已知一般人脸中性模型与一般人脸基本表情模型基础上,根据特定人脸不同     

基于人脸认知模式的相似脸搜索

目的 人类对人脸认知模式的探索由来已久,并且已经成功应用于美容整形等研究领域。然而,目前在计算机视觉和模式识别领域,计算人脸相似度的方法没有考虑人对人脸的认知模式,使得现有方法的计算结果从人的认知习惯角度来讲并非最佳。为克服以上缺陷,提出一种基于人脸认知模式的相似脸搜索算法。方法 依据人脸认知模式,选取特征点,并计算特征量,构造各面部器官（眼睛、鼻子、嘴巴、脸型）分类模型,即面部器官形状相似性度量模型,并采用圆形LBP算子,计算两幅人脸对应器官的纹理相似度,二者综合作为相似脸搜索的依据。结果 分别用本文方法和代表相似脸搜索最高水平的Face++的方法对80幅正面、中性表情、平视角度拍摄的人脸图像进行测试。本文方法的整体准确率高于Face++方法,其中,TOP1、TOP2最相似搜索结果准确率优势明显,均高出Face++方法12%以上。结论 实验结果表明,本文方法的搜索结果更加符合人脸认知模式,可应用于正面、中性表情、平视角度拍摄的人脸图像的相似脸搜索。此外,还可以将此类基于认知模式的图像搜索思路推广应用于商业领域,如基于图像的相似网购商品搜索等。     

Generation of 3D Texture Using Multiple 2D Models Analysis

Solid (30) texturing is commonly used in computer graphics for producing more realistic images. It is often more attractive than the conventional 20 texture mapping but remains more complex on some points. Its major difficulty concerns the generation of 30 texture in a general and efficient way. The well-known traditional procedural methods use generally a simplified mathematical model of a natural texture. No reliable way for the choice of the mathematical model parameters, which characterise directly the produced 30 texture, is given. Therefore, 30 texture generation becomes a more or less experimental process with these methods. Our recently published methodfor an automatic 30 texture generation avoids this problem by the use of the spectral analysis of one 2D model texture. The resulting 30 texture is of good quality but one open problem remains: the aspect of the produced texture cannot be fully controlled over the entire 30 space by only one 20 spectral analysis. This may be considered as a serious limitation for some kinds of textures representing important variations in any direction. In this paper we present a new and more powerful analytical approach for an automatic 30 texture generation. Contrarily to our previous method, this new approach is not exclusively based on the spectral analysis of only one 20 model. It uses two or three 2D models corresponding to different slices of a 30 texture block, so, the aspect of the produced 3D texture can be controlled more efficiently over the entire 30 space. In addition, a more efficient 30 texture antialiasing, well adapted to this new method is presented.     

Real-time moustache detection by combining image decolorization and texture detection with applications to facial gender recognition

There are still many challenging problems in facial gender recognition which is mainly due to the complex variances of face appearance. Although there has been tremendous research effort to develop robust gender recognition over the past decade, none has explicitly exploited the domain knowledge of the difference in appearance between male and female. Moustache contributes substantially to the facial appearance difference between male and female and could be a good feature to be incorporated into facial gender recognition. Little work on moustache segmentation has been reported in the literature. In this paper, a novel real-time moustache detection method is proposed which combines face feature extraction, image decolorization and texture detection. Image decolorization, which converts a color image to grayscale, aims to enhance the color contrast while preserving the grayscale. On the other hand, moustache appearance is normally grayscale surrounded by the skin color face tissue. Hence, it is a fast and efficient way to segment the moustache by using the decolorization technology. In order to make the algorithm robust to the variances of illumination and head pose, an adaptive decolorization segmentation has been proposed in which both the segmentation threshold selection and the moustache region following are guided by some special regions defined by their geometric relationship with the salient facial features. Furthermore, a texture-based moustache classifier is developed to compensate the decolorization-based segmentation which could detect the darker skin or shadow around the mouth caused by the small lines or skin thicker from where he/she smiles as moustache. The face is verified as the face containing a moustache only when it satisfies: (1) a larger moustache region can be found by applying the decolorization segmentation; (2) the segmented moustache region is detected as moustache by the texture moustache detector. The experimental results on color FERET database showed that the proposed approach can achieve 89 % moustache face detection rate with 0.1 % false acceptance rate. By incorporating the moustache detector into a facial gender recognition system, the gender recognition accuracy on a large database has been improved from 91 to 93.5 %.     

基于肤色信息和主分量分析的人脸实时检测系统

提出了一种基于肤色模型、人脸面部结构和模板匹配的人脸检测算法。该方法首先建立肤色模型来对原始图像进行肤色区域分割,再根据人脸的面部结构特征对分割区域进行过滤,最后用基于主元素分析的模板匹配算法对候选区域进行判断。实验结果表明该算法能够适应复杂背景以及多人脸的检测,而且检测速度快,能够达到实时检测的目的。     

Acquisition, Synthesis, and Rendering of Bidirectional Texture Functions

One of the main challenges in computer graphics is still the realistic rendering of complex materials such as fabric or skin. The difficulty arises from the complex meso structure and reflectance behavior defining the unique look‐and‐feel of a material. A wide class of such realistic materials can be described as 2D‐texture under varying light‐ and view direction, namely, the Bidirectional Texture Function (BTF). Since an easy and general method for modeling BTFs is not available, current research concentrates on image‐based methods, which rely on measured BTFs (acquired real‐world data) in combination with appropriate synthesis methods. Recent results have shown that this approach greatly improves the visual quality of rendered surfaces and therefore the quality of applications such as virtual prototyping. This state‐of‐the‐art report (STAR) will present the techniques for the main tasks involved in producing photo‐realistic renderings using measured BTFs in details.     

Texture histograms as a function of irradiation and viewing direction

The textural appearance of materials encountered in our daily environment depends on two directions, the irradiation and viewing direction. We investigate the bidirectional grey level histograms of a large set of materials, obtained from a texture database. We distinguish important categories, relate the various effects to physical mechanisms, and list material attributes that influence the bidirectional histograms. We use a model for rough surfaces with locally diffuse and/or specular reflection properties, a class of materials that commonly occurs, to generate bidirectional histograms and obtain close agreement with experimental data. We discuss several applications of bidirectional texture functions and histograms. In particular, we present a new approach to texture mapping based on bidirectional histograms. For 3D texture, this technique is superior to standard 2D texture mapping at hardly any extra computational cost or memory requirements.     

一种自动鲁棒的三维人脸重建方法

三维人脸模型已经广泛应用到视频电话、视频会议、影视制作、电脑游戏、人脸识别等多个领域。目前三维人脸建模一般使用多幅图像，且要求表情中性。本文提出了基于正、侧面任意表情三维人脸重建方法。首先对二维图像中的人脸进行特征提取，然后基于三维人脸统计模型，通过缩放、平移、旋转等方法，及全局和局部匹配，获得特定的三维人脸。基于二维图像中的人脸纹理信息，通过纹理映射，获得完整的三维人脸。通过对大量实际二维人脸图像的三维人脸重建，证实了该方法的有效性和鲁棒性。     

Face detection using quantized skin color regions merging andwavelet packet analysis

Detecting and recognizing human faces automatically in digital images strongly enhance content-based video indexing systems. In this paper, a novel scheme for human faces detection in color images under nonconstrained scene conditions, such as the presence of a complex background and uncontrolled illumination, is presented. Color clustering and filtering using approximations of the YCbCr and HSV skin color subspaces are applied on the original image, providing quantized skin color regions. A merging stage is then iteratively performed on the set of homogeneous skin color regions in the color quantized image, in order to provide a set of potential face areas. Constraints related to shape and size of faces are applied, and face intensity texture is analyzed by performing a wavelet packet decomposition on each face area candidate in order to detect human faces. The wavelet coefficients of the band filtered images characterize the face texture and a set of simple statistical deviations is extracted in order to form compact and meaningful feature vectors. Then, an efficient and reliable probabilistic metric derived from the Bhattacharrya distance is used in order to classify the extracted feature vectors into face or nonface areas, using some prototype face area vectors, acquired in a previous training stage     

Combining appearance and motion for face and gender recognition from videos

While many works consider moving faces only as collections of frames and apply still image-based methods, recent developments indicate that excellent results can be obtained using texture-based spatiotemporal representations for describing and analyzing faces in videos. Inspired by the psychophysical findings which state that facial movements can provide valuable information to face analysis, and also by our recent success in using LBP (local binary patterns) for combining appearance and motion for dynamic texture analysis, this paper investigates the combination of facial appearance (the shape of the face) and motion (the way a person is talking and moving his/her facial features) for face analysis in videos. We propose and study an approach for spatiotemporal face and gender recognition from videos using an extended set of volume LBP features and a boosting scheme. We experiment with several publicly available video face databases and consider different benchmark methods for comparison. Our extensive experimental analysis clearly assesses the promising performance of the LBP-based spatiotemporal representations for describing and analyzing faces in videos.     

基于肤色学习的多人脸前景抽取方法

针对多人脸场景下快速准确提取人脸内容的问题,提出了基于肤色学习的多人脸前景抽取方法。首先,给出了基于肤色学习的肤色前景分割模型。根据肤色专家的论文结果,采集了著名的SPA数据库的1 200张人脸进行肤色抽样,建立学习模型以得到每个人种在颜色空间的肤色参数,据此进行肤色图像分割,得到肤色前景。其次,利用人脸特征点学习算法,以常见人脸68个特征点为目标,结合肤色前景信息分割出人脸种子区域;并计算人脸中心点,来构建人脸椭圆边界模型以及确定遗传范围。最后,建立了有效抽取算法,在人脸椭圆边界内利用遗传机制进行人脸再生,从而抽取得到有效人脸区域。以三类不同数据库为基础,收集了100张有代表性的多人脸图像,实验结果表明所提方法对这些图像的多人脸抽取的结果准确率达到98.4%以上,且该方法对中密度人群的人脸内容抽取有显著效果,并为人脸识别算法的准确性和可用性提供了基础。