Face recognition based on 3D ridge images obtained from range data

In this paper, we present an approach for 3D face recognition from frontal range data based on the ridge lines on the surface of the face. We use the principal curvature, k_max, to represent the face image as a 3D binary image called ridge image. The ridge image shows the locations of the ridge points around the important facial regions on the face (i.e., the eyes, the nose, and the mouth). We utilized the robust Hausdorff distance and the iterative closest points (ICP) for matching the ridge image of a given probe image to the ridge images of the facial images in the gallery. To evaluate the performance of our approach for 3D face recognition, we performed experiments on GavabDB face database (a small size database) and Face Recognition Grand Challenge V2.0 (a large size database). The results of the experiments show that the ridge lines have great capability for 3D face recognition. In addition, we found that as long as the size of the database is small, the performance of the ICP-based matching and the robust Hausdorff matching are comparable. But, when the size of the database increases, ICP-based matching outperforms the robust Hausdorff matching technique.     

Pose Robust Low-resolution Face Recognition via Coupled Kernel-based Enhanced Discriminant Analysis

Most face recognition techniques have been successful in dealing with high-resolution (HR) frontal face images. However, real-world face recognition systems are often confronted with the low-resolution (LR) face images with pose and illumination variations. This is a very challenging issue, especially under the constraint of using only a single gallery image per person. To address the problem, we propose a novel approach called coupled kernel-based enhanced discriminant analysis (CKEDA). CKEDA aims to simultaneously project the features from LR non-frontal probe images and HR frontal gallery ones into a common space where discrimination property is maximized. There are four advantages of the proposed approach: 1) by using the appropriate kernel function, the data becomes linearly separable, which is beneficial for recognition; 2) inspired by linear discriminant analysis (LDA), we integrate multiple discriminant factors into our objective function to enhance the discrimination property; 3) we use the gallery extended trick to improve the recognition performance for a single gallery image per person problem; 4) our approach can address the problem of matching LR non-frontal probe images with HR frontal gallery images, which is difficult for most existing face recognition techniques. Experimental evaluation on the multi-PIE dataset signifies highly competitive performance of our algorithm.      

On designing practical long range near infrared-based face recognition systems

Although automated face recognition (AFR) is a well-studied problem with a history of more than three decades, it is still far from being considered a solved problem for the case of difficult exposure conditions, such as during night-time, in environments with unconstrained lighting, or at large distances from the camera. However, in practical forensic scenarios, it is often the case that investigators operate in difficult conditions, where cross-session data need to be matched and where, grouping of the data in the context of demographic information (constitute the grouping in terms of gender, ethnicity) may be used in order to assist law enforcement officials, forensic investigators and security personnel in human identification practices. In this paper, we discuss the challenges in designing a practical near infrared (NIR) FR system and, more specifically, study the problems of intra-spectral, cross-spectral, i.e. VIS–NIR, intra-distance and cross-distance NIR FR, in indoors, outdoors, day-time and night-time environments. Furthermore, we propose the usage of a multi-feature scenario dependent fusion scheme that can enhance recognition performance. We also investigate which scenarios used, related to datasets, features useful for face matching or their combination, are most beneficial to the identification accuracy of NIR FR systems, when the gallery set is composed of either visible or NIR band face images. Thus, we illustrate that the selection of specific feature extraction techniques and their fusion are often the key design aspects that can turn practically non-functional systems to effective systems with real-world applicability. As a result, such a strategy can significantly extend the range of conditions under which automated NIR FR systems can operate.     

可变光照条件下的人脸图像识别

对于人脸图像识别中光照变化的影响,传统的解决方法是对待识别图像进行光照补偿,先使它成为标准光照条件下的图像,然后和模板图像匹配来进行识别。为了提高在光照条件大范围变化时,人脸图像的识别率,提出了一种新的可变光照条件下的人脸图像识别方法。该方法首先利用在9个基本光照方向下分别获得的9幅图像来构成人脸光照特征空间,再通过这个光照特征空间,将图像库中的人脸图像变换成与待识别图像具有相同光照条件的图像,并将其作为模板图像;然后利用特征脸方法进行识别。实验结果表明,这种方法不仅能够有效地解决人脸识别中由于光照变化影响所造成的识别率下降的问题,而且对于光照条件大范围变化的情况,也可以得到比较高的正确识别率。     

基于面部曲线弹性匹配的三维人脸识别方法

提出一种基于面部径向曲线弹性匹配的三维人脸识别方法。使用人脸曲 面上的多条曲线表征人脸曲面,提取三维人脸上从鼻尖点发射的多条面部径向曲线,对其进 行分层弹性匹配和点距对应匹配,根据人脸不同部位受表情影响程度不同,对不同曲线识别 相似度赋予不同权重进行加权融合作为总相似度用于识别。测试结果表明该方法具有很好的 识别性能,并且对表情、遮挡和噪声具有较好的鲁棒性。     

Human eyebrow recognition in the matching-recognizing framework

This paper studies the problem of automatically recognizing human eyebrows using a frontal view. In the matching-recognizing framework for image-based object classification, we design an automatic human eyebrow recognition system via fast template matching and Fourier spectrum distance. Fast template matching is used to locate the target subregion of a gallery template or a pure eyebrow image in a probe original eyebrow image, whereas Fourier spectrum distance is used to determine the final identity of the probe original eyebrow image. We conducted a number of experiments to demonstrate the efficacy of the proposed system and corroborate the validity of eyebrow recognition on the BJUT eyebrow database. Moreover, we also tested the system on the color FERET database. Experimental results show that our approach can be directly applied to face recognition by only replacing eyebrow templates with face templates, and may achieve higher accuracy in eyebrow recognition than in small face recognition. This is a strong argument for eyebrow recognition to replace face recognition as an independent biometric in certain scenarios, especially where relatively large eyebrows can be cropped.     

基于脊谷特征提取的三维人脸识别

针对三维人脸数据庞大及识别效率低的问题,提出采用提取脊点及谷点表征人脸。脊点和谷点作为曲面局部区域内主曲率沿主方向变化的极值点,能够很好地表征三维人脸特征。对三维人脸提取脊点模型和谷点模型,通过对它们栅格化后生成对应的空间分布密度直方图实现人脸粗匹配,采用计算LTS-Hausdorff距离实现人脸的精确匹配。在GavabDB三维人脸库的实验结果表明,该方法具有较高的识别率。     

A fast algorithm for ICP-based 3D shape biometrics

In a biometrics scenario, gallery images are enrolled into the database ahead of the matching step, which gives us the opportunity to build related data structures before the probe shape is examined. In this paper, we present a novel approach, called “Pre-computed Voxel Nearest Neighbor”, to reduce the computational time for shape matching in a biometrics context. The approach shifts the heavy computation burden to the enrollment stage, which is done offline. Experiments in 3D ear biometrics with 369 subjects and 3D face biometrics with 219 subjects demonstrate the effectiveness of our approach.     

Virtual illumination grid for correction of uncontrolled illumination in facial images

Face recognition under uncontrolled illumination conditions is still considered an unsolved problem. In order to correct for these illumination conditions, we propose a virtual illumination grid (VIG) approach to model the unknown illumination conditions. Furthermore, we use coupled subspace models of both the facial surface and albedo to estimate the face shape. In order to obtain a representation of the face under frontal illumination, we relight the estimated face shape. We show that the frontal illuminated facial images achieve better performance in face recognition. We have performed the challenging Experiment 4 of the FRGCv2 database, which compares uncontrolled probe images to controlled gallery images. Our illumination correction method results in considerably better recognition rates for a number of well-known face recognition methods. By fusing our global illumination correction method with a local illumination correction method, further improvements are achieved.     

COMPARING FACE IMAGES USING THE MODIFIED HAUSDORFF DISTANCE

We introduce a novel methodology applicable to face matching and fast screening of large facial databases. The proposed shape comparison method operates on edge maps and derives holistic similarity measures, yet, it does not require solving the point correspondence problem. While the use of edge images is important to introduce robustness to changes in illumination, the lack of point-to-point matching delivers speed and tolerance to local non-rigid distortions. In particular, we propose a face similarity measure derived as a variant of the Hausdorff distance by introducing the notion of a neighborhood function (N) and associated penalties (P). Experimental results on a large set of face images demonstrate that our approach produces excellent recognition results even when less than 3% of the original grey-scale face image information is stored in the face database (gallery). These results implicate that the process of face recognition may start at a much earlier stage of visual processing than it was earlier suggested. We argue, that edge-like retinal images of faces are initially screened “at a glance” without the involvement of high-level cognitive functions thus delivering high speed and reducing computational complexity.     

基于双属性图表示的通用人脸图像识别系统

该文提出一个通用的人脸图像识别系统GFRS,对于人脸库中每个待识目标只存储一幅图像的情况下,可以实现各种干扰条件下人脸图像的识别,该系统提出使用双属性图来表示人脸图像,首先利用逐步求精定位法得到人脸图像各局部特征点的位置,图中每个特征点由两上特征属性来描述,即局部主成分特征系数和Gabor变换特征参数,从而构造了双属性图,然后给出双属性图匹配函数、匹配算法以及相应的识别方法。     

基于小波分解和分类的人脸识别

提出了一种基于小波分解和分类的人脸识别算法;算法首先对训练样本进行小波分解,以方差最大之小波系数间相关系数作为分类距离,对样本进行分类,并确定每类图像的类心;人脸识别过程首先寻找与测试样本匹配程度最高的类心图像,然后在该类心图像所在类中寻找最佳匹配图像,从而减少存储空间和计算时间,而且分类和确定类心均是离线操作,从而该算法显著加快了人脸识别速度;实验结果表明,算法有效。     

Multi-resolution feature fusion for face recognition

For face recognition, image features are first extracted and then matched to those features in a gallery set. The amount of information and the effectiveness of the features used will determine the recognition performance. In this paper, we propose a novel face recognition approach using information about face images at higher and lower resolutions so as to enhance the information content of the features that are extracted and combined at different resolutions. As the features from different resolutions should closely correlate with each other, we employ the cascaded generalized canonical correlation analysis (GCCA) to fuse the information to form a single feature vector for face recognition. To improve the performance and efficiency, we also employ “Gabor-feature hallucination”, which predicts the high-resolution (HR) Gabor features from the Gabor features of a face image directly by local linear regression. We also extend the algorithm to low-resolution (LR) face recognition, in which the medium-resolution (MR) and HR Gabor features of a LR input image are estimated directly. The LR Gabor features and the predicted MR and HR Gabor features are then fused using GCCA for LR face recognition. Our algorithm can avoid having to perform the interpolation/super-resolution of face images and having to extract HR Gabor features. Experimental results show that the proposed methods have a superior recognition rate and are more efficient than traditional methods.     

基于模型的三维物体识别

实现了一个完整的基于模型的三维物体识别系统,它可识别灰度图象中包含的物 体,如对遮挡加以限制,还可识别被遮挡的物体.该系统能实现物体的自动建模,也可先定性 识别某一物体的立体图对以获取高层知识,然后在高层知识的指导下准确地匹配立体图对中 相对应的特征.此外,还提出了利用最能表示物体特征的表面(特征面)来识别物体的方法,以 提高系统抗噪声的能力.大量实验证明,该系统具有相当的稳健性.     

基于图像匹配的古陶瓷身份自动认证方法

针对古陶瓷鉴定证书安全性低和公信度有限的问题,利用古陶瓷表面细节信息的独特性,基于图像识别技术,研究安全性高的古陶瓷身份自动认证方法。登记注册时将古陶瓷表面若干点位的细节信息以图像的形式录入系统;认证时,系统在线采集古陶瓷细节信息,与对应点位注册图像作匹配,并依据所有点位细节信息图像间的匹配 结果来对古陶瓷进行认证。为验证方法性能,本文构建了一个古陶瓷细节信息数据库。实验结果表明,本文提出的方法能够实现古陶瓷身份的高精度认证。     

Learning warps based similarity for pose-unconstrained face recognition

Face recognition techniques are widely used in many applications, such as automatic detection of crime scenes from surveillance cameras for public safety. In these real cases, the pose and illumination variances between two matching faces have a big influence on the identification performance. Handling pose changes is an especially challenging task. In this paper, we propose the learning warps based similarity method to deal with face recognition across the pose problem. Warps are learned between two patches from probe faces and gallery faces using the Lucas-Kanade algorithm. Based on these warps, a frontal face registered in the gallery is transformed into a series of non-frontal viewpoints, which enables non-frontal probe face matching with the frontal gallery face. Scale-invariant feature transform (SIFT) keypoints (interest points) are detected from the generated viewpoints and matched with the probe faces. Moreover, based on the learned warps, the probability likelihood is used to calculate the probability of two faces being the same subject. Finally, a hybrid similarity combining the number of matching keypoints and the probability likelihood is proposed to describe the similarity between a gallery face and a probe face. Experimental results show that our proposed method achieves better recognition accuracy than other algorithms it was compared to, especially when the pose difference is within 40 degrees.

     

基于隐马尔科夫模型的人脸识别

对于人脸识别系统来说,人脸图像的特征提取和匹配是决定人脸识别系统性能的关键所在。文中提出基于隐马尔科夫模型的人脸识别方法。首先,根据人脸的特点建立马尔科夫模型,然后对图像进行预处理,再利用采样窗对人脸图像进行采样并进行离散余弦变换,提取变换后的系数作为观察向量。最后对人脸图像进行HMM训练,训练结束后即建立了一个人的HMM。基于DCT系数的二维隐马尔科夫模型由于充分利用了人脸图像的二维统计特性,具有较高的识别率。实验结果证明此方法在准确性方面具有良好的性能。     

一种鲁棒稀疏表示的单样本人脸识别算法

稀疏表示在人脸识别问题上取得了非常优秀的识别结果,但在单样本条件下,算法性能下降严重。为提高单样本条件下稀疏表示的应用能力,提出一种鲁棒稀疏表示单样本人脸识别算法(RSR)。通过使用每张人脸图像创建一组位置图像,扩充每个对象训练样本,并利用L2,1范数约束,保证RSR选择正确对象的位置图像。在AR和Extended Yale B人脸数据库上进行评测,实验结果表明RSR能够有效处理存在遮挡或光照变化的人脸图像,获得了较好的单样本人脸识别准确率,具有很强的鲁棒性。