Random permutation principal component analysis for cancelable biometric recognition

Although biometrics is being increasingly used across the world, it also raises concerns over privacy and security of the enrolled identities. This is due to the fact that biometrics are not cancelable and if compromised may give access to the intruder. To address these problems, in this paper, we suggest two simple and powerful techniques called (i) Random Permutation Principal Component Analysis (RP-PCA) and (ii) Random Permutation Two Dimensional Principal Component Analysis (RP-2DPCA). The proposed techniques are based on the idea of cancelable biometric which can be reissued if compromised. The proposed techniques work in a cryptic manner by accepting the cancelable biometric template and a key (called PIN) issued to a user. The identity of a person is recognized only if the combination of template and PIN is valid, otherwise the identity is rejected. The superiority of the proposed techniques is demonstrated on three freely available face (ORL), iris (UBIRIS) and ear (IITD) datasets against state-of-the-art methods. The key advantages of the proposed techniques are (i) classification accuracy remains unaffected due to cancelable biometric templates generated using random permutation (ii) robustness across different biometrics. In addition, no image registration is required for performing recognition.     

基于改进的局部保持投影算法的人脸识别

局部保持投影算法是基于流形的学习方法,在人脸识别过程中容易遇到奇异值问题,为此提出一种利用奇异值分解的方法。在模型中,样本数据被投影到一个非奇异正交矩阵中,解决了奇异值问题;然后再根据局部保持投影算法求出新样本空间的低维投影子空间。将训练样本和测试样本分别投影到低维子空间中,再利用最近邻分类器进行分类识别。在ORL人脸数据库中,采用了一系列的实验来对比该算法与传统局部保持投影算法和主成分分析算法的识别效果。实验结果验证了改进的局部保持投影算法在人脸识别的有效性。     

Optimal locality preserving projection for face recognition

In face recognition, when the number of images in the training set is much smaller than the number of pixels in each image, Locality Preserving Projections (LPP) often suffers from the singularity problem. To overcome singularity problem, principal component analysis is applied as a preprocessing step. But this procession may discard some important discriminative information. In this paper, a novel algorithm called Optimal Locality Preserving Projections (O-LPP) is proposed. The algorithm transforms the singular eigensystem computation to eigenvalue decomposition problems without losing any discriminative information, which can reduce the computation complexity. And the theoretical analysis related to the algorithm is also obtained. Extensive experiments on face databases demonstrate the proposed algorithm is superior to the traditional LPP algorithm.     

子模式局部保持映射人脸识别

研究表明基于整体思想的人脸识别方法由于忽略图像的局部信息,在识别性能方面不如局部信息特征保持较好的基于子模块思想的识别算法。基于应用流形技术对图像降维后能够较好保持非线性子流形中的局部数据流形结构,提出了一种改进的子模式局部保持映射人脸识别算法。其主要思想是将同类的不同图像一并划分子集,由同位置子图组成子模块,并对子模块运用LPP算法学习其流形结构,与将不同类图像一并划分子集学习流形的方法不同。实验表明,该算法能更好地保持人脸图像的局部流形结构和信息特征,提高了识别率。     

Discriminant sparse locality preserving projection for face recognition

Multimedia Tools and Applications - In this paper, aiming at the drawback of the popular dimensionality reduction method Discriminant Sparse Neighborhood Preserving Embedding(DSNPE), i.e. the...     

面向酉子空间的二维判别保局投影的人脸识别*

保局投影算法（LPP）在人脸识别中具有较好的识别性能,但它是一种非监督学习,并且在具体实现时需要把图像转换为向量,破坏了图像的像素结构,这显然不利于模式识别。针对这些问题,提出基于酉子空间的二维判别保局算法,不仅在判别保局算法的基础上增加了类别信息,而且直接在灰度矩阵上进行水平和垂直方向上的二维保局投影。该方法构造酉空间上的复向量后再运用线性判别分析提取特征。在ORL、Yale和XJTU人脸库中验证了算法的正确性和有效性,其识别率比传统的2DLDA和2DLPP等方法提高4～5个百分点。     

基于监督判别局部保持投影的表情识别算法

LPP算法是无监督算法,并没有考虑到不同类别的样本对分类效果的影响,结果会造成不同类数据点的重叠,故所获得的子空间对于分类问题来说未必是最优的。提出一种新的基于监督判别局部保持投影（SDLPP）的表情识别算法。利用样本的类别信息重新构造LPP算法中的相似矩阵,然后在目标函数中增加类间散度约束,这样就会在保持样本点局部结构的同时,使不同类的样本点相互远离,从而得到更具有判别性的表情特征。该算法在识别率上比其他方法都有较大提高,通过在JAFFE表情库上的实验验证了其有效性。     

CBRC: a novel approach for cancelable biometric template generation using random permutation and Chinese Remainder Theorem

Multimedia Tools and Applications - Cancelable Biometrics is a challenging research field in which a cancelable template corresponding to a biometric is generated without affecting the performance....     

基于集成图的保局投影算法

为了克服保局投影方法(locality preserving projection,LPP)对噪音敏感,有效性依赖于近邻图构造等缺点,提出一种基于集成图的保局投影方法(graphs ensemble based LPP,GELPP).该方法先根据鲁棒统计原理定义出对噪声鲁棒的样本间相似性度量,再以该度量为基础构造多个近似的最大生成树;然后利用集成学习泛化能力强的优点来组合多个树为一个集成图;最后通过替换LPP的近邻图和相似性度量来进行保局投影.在高维人脸图像上的降维实验结果表明,该方法对噪声鲁棒,以及在集成图上降维的有效性.     

An adaptively weighted sub-pattern locality preserving projection for face recognition

In this paper, an adaptively weighted sub-pattern locality preserving projection (Aw-SpLPP) algorithm is proposed for face recognition. Unlike the traditional LPP algorithm which operates directly on the whole face image patterns and obtains a global face features that best detects the essential face manifold structure, the proposed Aw-SpLPP method operates on sub-patterns partitioned from an original whole face image and separately extracts corresponding local sub-features from them. Furthermore, the contribution of each sub-pattern can be adaptively computed by Aw-SpLPP in order to enhance the robustness to facial pose, expression and illumination variations. The efficiency of the proposed algorithm is demonstrated by extensive experiments on three standard face databases (Yale, YaleB and PIE). Experimental results show that Aw-SpLPP outperforms other holistic and sub-pattern based methods.     

基于局部保持投影与隐马尔可夫模型的维文字符识别

针对传统隐马尔可夫模型(HMM)在对手写维吾尔文字符建模时,字符宽度变化大,模型训练收敛缓慢,且易陷入局部极值的问题,提出一种基于保局投影(LPP)与HMM相结合的维吾尔字符识别方法。首先,通过高度归一化保持原图像的宽高比,用滑动窗获取子图像序列,形成观测向量序列;其次,采用局部保持投影将观测序列映射到低维空间,并用随机抽样方法降低邻接图矩阵的规模;最后,采用新观测序列训练HMM。该算法在降维的同时提高了HMM的收敛速度,降低了陷入局部极值的风险。实验结果显示,算法的平均收敛步数减少,错误率降低,表明算法是有效的。     

Local sparsity preserving projection and its application to biometric recognition

Multimedia Tools and Applications - Dimensionality reduction techniques based on sparse representation have drawn great attentions recently and they are successfully applied to biometric...     

基于类别信息的监督局部保持投影方法

局部保持投影算法(LPP)是拉普拉斯映射(LE)的线性近似,但LPP作为一种无监督方法,并没有有效利用已有的类别信息提高分类效率。为此提出一种基于类别信息的监督局部保持投影方法(SLPP-LI)。在学习投影矩阵时,SLPP-LI综合利用了流形的几何结构和已有训练点的类别信息,通过调整控制参数的取值,有效地利用已知的低维信息,并且直接求解线性方程获得高维数据的低维模型。通过在多个人脸数据库和手写数字库上的对比实验,表明了SLPP-LI对于高维数据的初始维数以及训练数据的数目并不敏感,〖BP(〗同类问题中与相应的对比算法相比〖BP)〗与主分量分析法(PCA)、LPP、正交LPP(OLPP)、有监督的LPP(SLPP)相比,均具有较高的识别率,充分说明SLPP-LI算法能够有效处理分类问题。     

基于SLPP和张量分解相结合的人脸识别*

针对多线性分析算法对多姿态多身份因素并存时,人脸的识别率大大下降等问题,提出了带监督的局 部保留投影映射算法与多线性张量分析算法相结合的人脸识别方法。该方法将人脸转动的近邻点信息作为监 督信息引入,更精确地描述了姿态空间的非线性结构,再结合张量分解和核函数将姿态流形系数映射到高维图 像空间,使得从低维空间到高维空间映射的精确性得以提高。在东方人脸数据库上进行实验,结果验证了该算 法的有效性。     

一种增强的局部保持投影方法

维数灾难是机器学习算法在高维数据上学习经常遇到的难题,基于局部保持的投影方法（Locality Preserving Projection,LPP）,可以很好地解决维数灾难难题。然而传统LPP的相似性度量方法对噪音敏感,为此利用鲁棒路径相似的度量方法,提出一种增强的局部保持投影方法。在高维流形数据上的降维实验证实了该方法对噪声和离群点的有效性。     

Kernel class-wise locality preserving projection

In the recent years, the pattern recognition community paid more attention to a new kind of feature extraction method, the manifold learning methods, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among them, locality preserving projection (LPP) is one of the most promising feature extraction techniques. However, when LPP is applied to the classification tasks, it shows some limitations, such as the ignorance of the label information. In this paper, we propose a novel local structure based feature extraction method, called class-wise locality preserving projection (CLPP). CLPP utilizes class information to guide the procedure of feature extraction. In CLPP, the local structure of the original data is constructed according to a certain kind of similarity between data points, which takes special consideration of both the local information and the class information. The kernelized (nonlinear) counterpart of this linear feature extractor is also established in the paper. Moreover, a kernel version of CLPP namely Kernel CLPP (KCLPP) is developed through applying the kernel trick to CLPP to increase its performance on nonlinear feature extraction. Experiments on ORL face database and YALE face database are performed to test and evaluate the proposed algorithm.     

Supervised optimal locality preserving projection

In the past few years, the computer vision and pattern recognition community has witnessed a rapid growth of a new kind of feature extraction method, the manifold learning methods, which attempt to project the original data into a lower dimensional feature space by preserving the local neighborhood structure. Among these methods, locality preserving projection (LPP) is one of the most promising feature extraction techniques. Unlike the unsupervised learning scheme of LPP, this paper follows the supervised learning scheme, i.e. it uses both local information and class information to model the similarity of the data. Based on novel similarity, we propose two feature extraction algorithms, supervised optimal locality preserving projection (SOLPP) and normalized Laplacian-based supervised optimal locality preserving projection (NL-SOLPP). Optimal here means that the extracted features via SOLPP (or NL-SOLPP) are statistically uncorrelated and orthogonal. We compare the proposed SOLPP and NL-SOLPP with LPP, orthogonal locality preserving projection (OLPP) and uncorrelated locality preserving projection (ULPP) on publicly available data sets. Experimental results show that the proposed SOLPP and NL-SOLPP achieve much higher recognition accuracy.     

基于局部保持投影的复合位置投影

为解决在人脸识别领域的特征提取问题,提出一种基于局部保持投影（LPP）的复合位置投影（MLPP）方法,通过选取不同的类内、类间度量矩阵和约束矩阵,将求解最优变换矩阵的问题转换成普通的特征值问题。在构造邻接图时,该算法将相同类各点作为邻接点,将类内结构保持到特征空间中,在保留局部结构稳定的同时,使整体结构趋于最大化,从而形成高效的聚簇。在AT&T和JAFFE标准人脸图像库上的实验结果表明,MLPP算法具有较高的识别率。     

有监督正交局部保留投影及其在人脸识别中的应用

针对局部保留投影算法（LPP）的无监督和非正交问题,提出了一种有监督的正交局部保留投影算法SOLPP。该算法同时考虑了样本的类别信息以及投影向量间的相互正交性,首先利用样本的类标签信息重新定义了类内和类间相似度矩阵,同时最大化类间离散度与类内离散度之比,有效地保持了样本的局部结构;其次对投影基向量进行正交化,在保持数据空间结构的同时进一步提高了人脸识别效果。在ORL和FERET人脸库上的实验表明,该方法的识别率要优于SLPP等算法。     

全局加权稀疏局部保留投影

针对稀疏保留投影(SPP)算法运行时间较长并且忽略了样本的类间差异信息的问题,在稀疏保留投影算法的基础上,提出了全局加权稀疏局部保留投影(GWSLPP)算法。该算法在保持样本的稀疏重构关系的同时,使样本具有很好的鉴别能力,算法通过对样本进行稀疏重构处理;然后对样本进行投影并且最大化样本的类间散度;最后利用得到的投影将样本分类。该算法分别在FERET人脸库和YALE人脸库上进行实验。实验结果表明,全局加权稀疏保留算法在执行时间和识别率综合性能上,优于局部保留投影(LPP)、SPP和FisherFace算法,执行时间只有25s,识别率能达到95%以上,实验数据验证了算法的有效性。