Local structure based supervised feature extraction

In the past few years, the computer vision and pattern recognition community has witnessed the 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 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 feature extraction method, called locally discriminating projection (LDP). LDP utilizes class information to guide the procedure of feature extraction. In LDP, 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 similarity has several good properties which help to discover the true intrinsic structure of the data, and make LDP a robust technique for the classification tasks. We compare the proposed LDP approach with LPP, as well as other feature extraction methods, such as PCA and LDA, on the public available data sets, FERET and AR. Experimental results suggest that LDP provides a better representation of the class information and achieves much higher recognition accuracies.     

一种基于核的监督流形学习算法

针对流形学习算法——局部保持映射存在的参数选择及不能进行非线性特征提取的问题,提出一种基于核的监督流形学习算法.该算法作为局部保持映射算法的改进算法用样本类标识信息指导建立局部最近邻图,并在建立局部最近邻图使用无参数的相似度量.利用核方法来解决局部保持映射算法在处理线性不可分问题上的局限性问题.在两个常用数据库上验证本文算法的可行性和有效性.     

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.     

基于大间距准则的不相关保局投影分析

局部保持投影(Locality preserving projections,LPP)算法只保持了目标在投影后的邻域局部信息,为了更好地刻画数据的流形结构, 引入了类内和类间局部散度矩阵,给出了一种基于有效且稳定的大间距准则(Maximum margin criterion,MMC)的不相关保局投影分析方法.该方法在最大化散度矩阵迹差时,引入尺度因子α,对类内和类间局部散度矩阵进行加权,以便找到更适合分类的子空间并且可避免小样本问题; 更重要的是,大间距准则下提取的判别特征集一般情况下是统计相关的,造成了特征信息的冗余, 因此,通过增加一个不相关约束条件,利用推导出的公式提取不相关判别特征集, 这样做, 对正确识别更为有利.在Yale人脸库、PIE人脸库和MNIST手写数字库上的测试结果表明,本文方法有效且稳定, 与LPP、LDA (Linear discriminant analysis)和LPMIP(Locality-preserved maximum information projection)方法等相比,具有更高的正确识别率.     

基于全局不相关的多流形学习

为提升人脸识别算法的鲁棒性,减少判别信息的冗余度,提出基于全局不相关的多流形判别学习算法(UFDML)。使用特征空间到特征空间的距离,学习样本局部判别信息,提出全局不相关约束,使提取的判别特征是统计不相关的。在Yale,AR,ORL人脸库上的实验结果表明,与LPP(局部保持投影)、LDA(线性判别分析)、UDP(非监督判别投影)等人脸识别算法相比,所提算法的平均识别率高于其它算法,验证了其有效性。     

基于有监督直接局部保持投影的人脸识别

提出一种用于图像识别的有监督直接局部保持投影算法,该算法结合样本类别信息,通过同时对角化的方法求解局部保持投影问题,避免矩阵的奇异性。在ORL人脸库上的测试结果表明,该算法的识别率高于PCA, PCA+LPP等方法。     

融合局部结构和差异信息的监督特征提取算法

针对监督局部保持投影(Supervised locality preserving projection, SLPP)存在过学习和不能较好地保持图像空间的差异信息等问题,造成算法性能不够好, 提出了一种新的基于流形学习的监督特征提取方法(Supervised local structure and diversity projection, S-LSDP). S-LSDP从信息统计量角度引入差异信息,并给出度量差异信息大小的准则(差异离散度) 及明确的物理含义;然后通过最小化局部离散度和最大化差异离散度准则提取投影方向. 投影后的特征既能有效地保持图像之间的局部结构属性,又能较好地保持图像之间的差异信息, 而且避免了过学习问题.在UMIST, Yale, PIE和AR数据库上的实验结果表明了该算法的有效性.     

无关性判别保局算法及其在人脸识别中的应用

特征提取是人脸识别过程中的一个重要步骤,是人脸识别算法有效性的关键。提出了一种基于无关性判别保局的特征提取算法,并应用于人脸识别。基于保局投影算法的人 脸识别是一种有效的人脸识别算法,但它只考虑了数据的局部性,没有考虑类别信息,也没有考虑所提特征之间的相关性,现有的改进算法虽然考虑了类别信息,但是没有考虑到 类间信息。本文算法使得所提特征之间相互无关,这样降低了数据冗余,同时考虑到类别信息,使得投影后的类间区分度加强了。实验结果验证了算法的正确性和有效性,比传统 算法有较好的识别性能。     

Feature extraction using constrained maximum variance mapping

In this paper, an efficient feature extraction method named as constrained maximum variance mapping (CMVM) is developed. The proposed algorithm can be viewed as a linear approximation of multi-manifolds learning based approach, which takes the local geometry and manifold labels into account. The CMVM and the original manifold learning based approaches have a point in common that the locality is preserved. Moreover, the CMVM is globally maximizing the distances between different manifolds. After the local scatters have been characterized, the proposed method focuses on developing a linear transformation that can maximize the dissimilarities between all the manifolds under the constraint of locality preserving. Compared to most of the up-to-date manifold learning based methods, this trick makes contribution to pattern classification from two aspects. On the one hand, the local structure in each manifold is still kept; on the other hand, the discriminant information between manifolds can be explored. Finally, FERET face database, CMU PIE face database and USPS handwriting data are all taken to examine the effectiveness and efficiency of the proposed method. Experimental results validate that the proposed approach is superior to other feature extraction methods, such as linear discriminant analysis (LDA), locality preserving projection (LPP), unsupervised discriminant projection (UDP) and maximum variance projection (MVP).     

Local sparse representation projections for face recognition

How to define the sparse affinity weight matrices is still an open problem in existing manifold learning algorithm. In this paper, we propose a novel supervised learning method called local sparse representation projections (LSRP) for linear dimensionality reduction. Differing from sparsity preserving projections (SPP) and the recent manifold learning methods such as locality preserving projections (LPP), LSRP introduces the local sparse representation information into the objective function. Although there are no labels used in the local sparse representation, it still can provide better measure coefficients and significant discriminant abilities. By combining the local interclass neighborhood relationships and sparse representation information, LSRP aims to preserve the local sparse reconstructive relationships of the data and simultaneously maximize the interclass separability. Comprehensive comparison and extensive experiments show that LSRP achieves higher recognition rates than principle component analysis, linear discriminant analysis and the state-of-the-art techniques such as LPP, SPP and maximum variance projections.     

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。     

Towards a face recognition method based on uncorrelated discriminant sparse preserving projection

Feature extraction has always been an important step in face recognition, the quality of which directly determines recognition result. Based on making full use of advantages of Sparse Preserving Projection (SPP) on feature extraction, the discriminant information was introduced into SPP to arrive at a novel supervised feather extraction method that named Uncorrelated Discriminant SPP (UDSPP) algorithm. The obtained projection with the method by sparse preserving intra-class and maximizing distance inter-class can effectively express discriminant information, while preserving local neighbor relationship. Moreover, statistics uncorrelated constraint was also added to decrease redundancy among feature vectors so as to obtain more information as possible with little vectors as possible. The experimental results show that the recognition rate improved compared with SPP. The method is also superior to recognition methods based on Euclidean distance in processing face database in light.     

中心近邻嵌入学习算法的人脸识别研究

针对人脸识别问题,提出了一种中心近邻嵌入的学习算法,其与经典的局部线性嵌入和保局映射不同,它是一种有监督的线性降维方法。该方法首先通过计算各类样本中心,并引入中心近邻距离代替两样本点之间的直接距离作为权系数函数的输入;然后再保持中心近邻的几何结构不变的情况下把高维数据嵌入到低维坐标系中。通过中心近邻嵌入学习算法与其他3种人脸识别方法(即主成分分析、线形判别分析及保局映射)在ORL、Yale及UMIST人脸库上进行的比较实验结果表明,它在高维数据低维可视化和人脸识别效果等方面均较其他3种方法取得了更好的效果。     

Kernel Self-optimized Locality Preserving Discriminant Analysis for feature extraction and recognition

We propose Kernel Self-optimized Locality Preserving Discriminant Analysis (KSLPDA) for feature extraction and recognition. The procedure of KSLPDA is divided into two stages, i.e., one is to solve the optimal expansion of the data-dependent kernel with the proposed kernel self-optimization method, and the second is to seek the optimal projection matrix for dimensionality reduction. Since the optimal parameters of data-dependent kernel are achieved automatically through solving the constraint optimization equation, based on maximum margin criterion and Fisher criterion in the empirical feature space, KSLPDA works well on feature extraction for classification. The comparative experiments show that KSLPDA outperforms PCA, LDA, LPP, supervised LPP and kernel supervised LPP.     

模糊非相关判别转换及其应用

线性判别分析是一种特征提取和维数缩减的方法,广泛应用于人脸识别,语音识别和手写字母识别等领域。但是许多线性判别分析都是“硬”线性判别分析,每个数据点都严格地属于这一类或那一类。在非相关判别转换(UDT)基础上,提出了模糊非相关判别转换(FUDT)。FUDT是利用模糊集理论的有监督学习方法,其判别向量满足广义瑞利商方程,同时也满足样本到模糊非相关优化判别向量上的投影是非相关的。通过FUDT和UDT对公共数据库MSTAR的实验结果可看出,FUDT在处理SAR图像的特征提取方面优于UDT。     

大间距无监督正交特征提取算法

以主成分分析和局部保持投影为理论基础,提出了一种同时考虑数据样本的全局和局部特性的大间距无监督正交特征提取算法,算法的目标函数采用大间距准则,避免了由于矩阵求逆带来的小样本问题,同时为了进一步增强算法的识别性能,对所求取的投影矩阵进行了正交化约束,最后人脸库上的实验结果表明所提方法的有效性.     

Locality preserving and global discriminant projection with prior information

Existing supervised and semi-supervised dimensionality reduction methods utilize training data only with class labels being associated to the data samples for classification. In this paper, we present a new algorithm called locality preserving and global discriminant projection with prior information (LPGDP) for dimensionality reduction and classification, by considering both the manifold structure and the prior information, where the prior information includes not only the class label but also the misclassification of marginal samples. In the LPGDP algorithm, the overlap among the class-specific manifolds is discriminated by a global class graph, and a locality preserving criterion is employed to obtain the projections that best preserve the within-class local structures. The feasibility of the LPGDP algorithm has been evaluated in face recognition, object categorization and handwritten Chinese character recognition experiments. Experiment results show the superior performance of data modeling and classification to other techniques, such as linear discriminant analysis, locality preserving projection, discriminant locality preserving projection and marginal Fisher analysis.     

Discriminant Analysis with Local Gaussian Similarity Preserving for Feature Extraction

In this paper, we propose a novel discriminant analysis with local Gaussian similarity preserving (DA-LGSP) method for feature extraction. DA-LGSP can be viewed as a linear approximation of manifold learning based approach which seeks to find a linear projection that maximizes the between-class dissimilarities under the constraint of locality preserving. The local geometry of each point is preserved by the Gaussian coefficients of its neighbors, meanwhile the between-class dissimilarities are represented by Euclidean distances. Experiments are conducted on USPA data, COIL-20 dataset, ORL dataset and FERET dataset. The performance of the proposed method demonstrates that DA-LGSP is effective in feature extraction.     

基于QR分解的扩展监督局部保留映射

针对局部保留映射(LPP)算法不能提供数据集的差异信息问题,提出一种基于QR分解的扩展有监督LPP算法。该方法对训练数据矩阵进行QR分解,采用有监督的LPP算法进行降维,利用类别信息对降维后的数据进行Fisher线性判别式分析,得到最终的映射矩阵以提高判别性能。实验结果表明,该方法较主成分分析法和LPP方法有更好的判别性能。     

基于POEM_SLPP的人脸识别算法

针对方向边缘幅值模式(Patterns of Oriented Edge Magnitudes,POEM)提取的人脸特征维数过高和计算复杂度较大的问题,提出了结合方向边缘幅值模式和有监督的局部保持投影(Patterns of Oriented Edge Magnitudes _Supervised Locality Preserving Projections,POEM_SLPP)的人脸识别算法。首先,采用POEM算子进行特征提取;其次,将高维特征数据投影到SLPP算法求出的低维样本空间进行降维;最后,采用最近邻法对测试样本进行分类。在CAS-PEAL-R1人脸库上的实验结果表明,在姿态、背景、修饰、年龄、距离测试集上,该算法的平均识别率较POEM LPP算法提高了22%,较POEM PCA提高了2%。