视觉位置识别中代表地点的标识牌算法

针对视觉位置识别中因检索全局图片而带来大量的时间消耗情况,以及不同地点的视觉图像存在相似和同一地点从不同视角看起来会不尽相同而导致感知混淆的问题.本文提出一种基于显著性算法提取候选对象并生成代表地点的标识牌算法.该方法对在位置识别系统中每个地点其对应的视频序列段上的关键帧使用显著性算法,生成大量的视觉显著的候选对象,并用对这些候选对象有效计算其之间的评价函数,再使用层次聚类算法计算出每一段序列上具有代表性的对象,最后将这些对象组合成具有代表视频序列的标识牌.使用标识牌代表地点的方式,插入位置识别系统中搜索地点对应的大量图像集的前一个步骤中,以此来缩小搜索范围,避免感知混淆所带来的全局搜索不确定的困惑.     

有效的协方差判别学习算法

在基于视频的图像集分类中,类内样本多样性问题是影响算法分类性能的一个主要原因.为了尝试解决该问题,提出了一种图像集分类算法,其目标体现在2个方面:(1)使得算法在时间效率上相较于协方差判别学习(CDL)等具有代表性的图像集分类算法有进一步的提升;(2)使得算法在分类精度上也仍然具有可比性.首先利用双向二维主成分分析对原始的协方差特征进行降维,使其变得更加紧凑.同时,为了抽取到更具判别性的特征信息,对每一个低维紧凑的协方差矩阵应用QR分解,使其变换成一个正交基矩阵和一个非奇异的上三角矩阵.考虑数据分布空间的黎曼流形特性,通过定义函数的方式使得上三角矩阵仍然分布在由对称正定(SPD)矩阵张成的SPD流形之上.此时,原始的样本空间就转化成了一个由正交基矩阵张成的Grassmann流形和一个特征分布更加紧凑的新的SPD流形.为了更好地整合这2种黎曼流形特征,首先利用Stein散度以及对数欧氏距离导出一个黎曼流形测地线距离度量;然后,利用该度量设计一个正定的核函数将上述特征映射到一个高维Hilbert核空间;最后,利用核判别分析算法进行判别子空间特征学习.文中算法在5个基准视频集YTC, Honda, ETH-80, MDSD以及AFEW上均取得了较好的分类结果,同时在计算效率上也优于CDL等对比算法,从而表明了其可行性和有效性.     

基于双稀疏正则的图像集距离学习

随着视频采集和网络传输技术的快速发展,以及个人移动终端设备的广泛使用,大量图像数据以集合形式存在.由于集合内在结构的复杂性,使得图像集分类的一个关键问题是如何度量集合间距离.为了解决这一问题,本文提出了一种基于双稀疏正则的图像集距离学习框架（DSRID）.在该框架中,两集合间距离被建模成其对应的内部典型子结构间的距离,从而保证了度量的鲁棒性和判别性.根据不同的集合表示方法,本文给出了其在传统的欧式空间,以及两个常见的流形空间,即对称正定矩阵流形（symmetric positive definite matrices manifold,SPD manifold）和格林斯曼流形（Grassmann manifold）上的实现.在一系列的基于集合的人脸识别、动作识别和物体分类任务中验证了该框架的有效性.     

一种基于QPSO优化的流形学习的视频人脸识别算法

视频场景复杂多变,视频采集设备不一致等原因,导致无约束视频中充斥着大量的遮挡和人脸旋转,视频人脸识别方法的准确率不高且性能不稳定.为解决上述问题,本文提出了一种基于QPSO优化的流形学习的视频人脸识别算法.该算法将视频人脸识别视为图像集相似度度量问题,首先帧图像对齐后提取纹理特征并进行融合,再利用带有QPSO优化的黎曼流形大幅度简约维度以获得视频人脸的内在表示,相似度则由凸包距离表示,最后利用SVM分类器获得分类结果.通过在Youtube Face数据库和Honda/UCSD数据库上与当前主流算法进行的对比实验,验证了本文算法的有效性,所提算法识别精度较高,误差较低,并且对光照和表情变化具有较强的鲁棒性.     

基于局部线性判别器融合的非线性流形判别分析

提出一种基于局部线性判别器融合的方法,在非线性流形上展开判别分析.首先根据Gabriel图对整体流形作局部区域划分,并构造局部线性判别器.然后通过局部判别器融合获取整体非线性判别器:基于边界准则函数,以迭代优化的方式为每个局部判别器分配最佳的权重系数.基于边界准则函数的融合算法,克服小样本问题,消除整体判别器的性能对样本分布的依赖性.在人工合成数据集以及人脸图像库上的实验证明本文算法的有效性.     

增强Kernel学习优化最大边缘投影的人脸识别

针对传统的流形学习算法通常只考虑样本类内几何结构而忽略类间判别信息的问题,提出一种基于增强核学习的最大边缘投影(MMP)算法。首先使用基于增强核学习非线性扩展的MMP采集人脸图像的非线性结构;然后利用核变换技术加强原始输入核函数的判别能力,并且借助于特征向量选择算法改善算法的计算效率;最后,利用基于乘性规则训练的支持向量机完成人脸的识别。在Yale、ORL、PIE三大通用人脸数据库的组合数据集及AR上的实验验证了该算法的有效性。实验结果表明,相比其他几种核学习算法,该算法取得了更好的识别效果。     

图正则化稀疏判别非负矩阵分解

非负矩阵分解是一种流行的数据表示方法,利用图正则化约束能有效地揭示数据之间的局部流形结构。为了更好地提取图像特征,给出了一种基于图正则化的稀疏判别非负矩阵分解算法（graph regularization sparse discriminant non-negative matrix factorization,GSDNMF-L_2,1）。利用同类样本之间的稀疏线性表示来构建对应的图及权矩阵;以L_2,1范数进行稀疏性约束;以最大间距准则为优化目标函数,利用数据集的标签信息来保持数据样本之间的流形结构和特征的判别性,并给出了算法的迭代更新规则。在若干图像数据集上的实验表明,GSDNMF-L_2,1在特征提取方面的分类精度优于各对比算法。     

基于局部邻域多流形度量的人脸识别

针对人脸识别中特征的提取,提出了一种基于局部邻域多流形度量的人脸识别方法。针对人脸识别的小样本问题,用特征脸对人脸图像预处理。对预处理后的人脸数据集中每个流形内的数据点采用欧氏距离来选择各数据点的近邻点,由此得到局部权重矩阵,并计算重构数据点与原始数据点之间的误差距离;同时,采用图像集建模流形,用affine hull表示流形对应的数据集信息,计算多流形间的距离度量矩阵。通过最大化流形间距离以及最小化数据点与重构数据点误差距离来寻找投影降维矩阵。在人脸数据集上的大量比较实验,验证了该方法的准确性和有效性。     

基于改进的多流形算法的人脸图像集识别

一个图像集由大量变化不一的图像组成,而且这些图像都表示同一个人.现实中的图像集数据是非线性的,造成这些现象的因素有人脸的角度不同、光线的明暗等,因此图像集中的每幅图像都是变化的,如果近似的将一个图像集建模为线性子空间,而忽略了集合中数据结构的变化,很显然是不合理的,这也必然会影响到最后的识别率.受流形理论知识的启发,可以将图像集建模为一个流形,这与传统的将图像集建模为子空间的方法有着本质区别.本文在基于流形的人脸图像集识别方法的基础上进行改进,提出新的计算样子空间距离方法,最后采用所有最短子空间距离的平均值作为流形之间的距离,称为改进的多流形方法(Improved multi-manifold method,IMM).IMM方法在CMU PIE数据库上进行实验,结果表明该方法相比其他方法具有更高识别率.     

视频数据库的聚类索引方法

理想的视频库组织方法应该把语义相关并且特征相似的视频的特征向量相邻存储.针对大规模视频库的特点,在语义监督下基于低层视觉特征对视频库进行层次聚类划分,当一个聚类中只包含一个语义类别的视频时,为这个聚类建立索引项,每个聚类所包含的原始特征数据在磁盘上连续存储.统计低层特征和高层特征的概率联系,构造Bayes分类器.查询时对用户的查询范例,首先确定最可能的候选聚类,然后在候选聚类范围内查询相似视频片段.实验结果表明,文中的方法不仅提高了检索速度而且提高了检索的语义敏感度.     

黎曼流形上的保局投影在图像集匹配中的应用

目的提出了黎曼流形上局部结构特征保持的图像集匹配方法。方法该方法使用协方差矩阵建模图像集合,利用对称正定的非奇异协方差矩阵构成黎曼流形上的子空间,将图像集的匹配转化为流形上的点的匹配问题。通过基于协方差矩阵度量学习的核函数将黎曼流形上的协方差矩阵映射到欧几里德空间。不同于其他方法黎曼流形上的鉴别分析方法,考虑到样本分布的局部几何结构,引入了黎曼流形上局部保持的图像集鉴别分析方法,保持样本分布的局部邻域结构的同时提升样本的可分性。结果在基于图像集合的对象识别任务上测试了本文算法,在ETH80和YouTube Celebrities数据库分别进行了对象识别和人脸识别实验,分别达到91.5%和65.31%的识别率。结论实验结果表明,该方法取得了优于其他图像集匹配算法的效果。     

基于虚拟样本图像集的多流形鉴别学习算法

为了丰富训练样本的类内变化信息,提出了基于通用训练样本集的虚拟样本生成方法。进一步,为了利用生成的虚拟样本中的类内变化信息有效地完成单样本人脸识别任务,提出了基于虚拟样本图像集的多流行鉴别学习算法。该算法首先将每类仅有的单个训练样本图像和该类的虚拟样本图像划分为互补重叠的局部块并构建流形,然后为每个流形学习一个投影矩阵,使得相同流形内的局部块在投影后的低维特征空间间隔最小化,不同流形中的局部块在投影后的低维特征空间中间隔最大化。实验结果表明,所提算法能够准确地预测测试样本中的类内变化,是一种有效的单样本人脸识别算法。     

Orthogonal discriminant vector for face recognition across pose

Recognizing face images across pose is one of the challenging tasks for reliable face recognition. This paper presents a new method to tackle this challenge based on orthogonal discriminant vector (ODV). The result of our theoretical analysis shows that an individual’s probe image captured with a new pose can be represented by a linear combination of his/her gallery images. Based on this observation, in contrast to the conventional methods which model face images of different individuals on a single manifold, we propose to model face images of different individuals on different linear manifolds. The contribution of our approach includes: (1) to prove that the orthogonality to ODVs is a pose-invariant feature.; (2) to categorize each person with a set of ODVs, where his/her face images posses zero projections while other persons’ images are characterized by maximum projections; (3) to define a metric to measure the distance between a face image and an ODV, and classify the face images based on this metric. Our experimental results validate the feasibility of modeling the face images of different individuals on different linear manifolds. The proposed method achieves higher accuracy on face recognition and verification than the existing techniques.     

Discriminative transfer learning with sparsity regularization for single-sample face recognition

Discriminant analysis is an important technique for face recognition because it can extract discriminative features to classify different persons. However, most existing discriminant analysis methods fail to work for single-sample face recognition (SSFR) because there is only a single training sample per person such that the within-class variation of this person cannot be estimated in such scenario. In this paper, we present a new discriminative transfer learning (DTL) approach for SSFR, where discriminant analysis is performed on a multiple-sample generic training set and then transferred into the single-sample gallery set. Specifically, our DTL learns a feature projection to minimize the intra-class variation and maximize the inter-class variation of samples in the training set, and minimize the difference between the generic training set and the gallery set, simultaneously. To make the DTL be robust to outliers and noise, we employ a sparsity regularizer to regularize the DTL and further propose a novel discriminative transfer learning with sparsity regularization (DTLSR) method. Experimental results on three face datasets including the FERET, CAS-PEAL-R1, and real-world LFW datasets are presented to show the efficacy of the proposed methods.     

Open-set face recognition across look-alike faces in real-world scenarios

The open-set problem is among the problems that have significantly changed the performance of face recognition algorithms in real-world scenarios. Open-set operates under the supposition that not all the probes have a pair in the gallery. Most face recognition systems in real-world scenarios focus on handling pose, expression and illumination problems on face recognition. In addition to these challenges, when the number of subjects is increased for face recognition, these problems are intensified by look-alike faces for which there are two subjects with lower intra-class variations. In such challenges, the inter-class similarity is higher than the intra-class variation for these two subjects. In fact, these look-alike faces can be created as intrinsic, situation-based and also by facial plastic surgery. This work introduces three real-world open-set face recognition methods across facial plastic surgery changes and a look-alike face by 3D face reconstruction and sparse representation. Since some real-world databases for face recognition do not have multiple images per person in the gallery, with just one image per subject in the gallery, this paper proposes a novel idea to overcome this challenge by 3D modeling from gallery images and synthesizing them for generating several images. Accordingly, a 3D model is initially reconstructed from frontal face images in a real-world gallery. Then, each 3D reconstructed face in the gallery is synthesized to several possible views and a sparse dictionary is generated based on the synthesized face image for each person. Also, a likeness dictionary is defined and its optimization problem is solved by the proposed method. Finally, the face recognition is performed for open-set face recognition using three proposed representation classifications. Promising results are achieved for face recognition across plastic surgery and look-alike faces on three databases including the plastic surgery face, look-alike face and LFW databases compared to several state-of-the-art methods. Also, several real-world and open-set scenarios are performed to evaluate the proposed method on these databases in real-world scenarios.     

Simultaneous Learning of Nonlinear Manifolds Based on the Bottleneck Neural Network

Manifold learning methods are important techniques for nonlinear extraction of high-dimensional data structures. These methods usually extract a global manifold for data. However, in many real-world problems, there is not only one global manifold, but also additional information about the objects is shared by a large number of manifolds. These manifolds can share information for data reconstruction. To simultaneously extract these data manifolds, this paper proposes a nonlinear method based on the deep neural network (NN) named nonlinear manifold separator NN (NMSNN). Unlike unsupervised learning of bottleneck NN, data labels were used for simultaneous manifold learning. This paper makes use of NMSNN for extracting both expression and identity manifolds for facial images of the CK+ database. These manifolds have been evaluated by different metrics. The identity manifold is used for changing image identity. The result of identity recognition by K-nearest neighbor classifier shows that virtual identities are exactly sanitized. The virtual images for different expressions of test subjects are generated by expression manifold. The facial expression recognition rate of 92.86 % is achieved for virtual expressions of test persons. It is shown that NMSNN can be used to enrich datasets by sanitizing virtual images. As a result, 8 and 19 % improvements are gained in the face recognition task by a single image of each person on CK+ and Bosphorus databases, respectively.     

Improved discriminant locality preserving projections for face and palmprint recognition

We propose in this paper two improved manifold learning methods called diagonal discriminant locality preserving projections (Dia-DLPP) and weighted two-dimensional discriminant locality preserving projections (W2D-DLPP) for face and palmprint recognition. Motivated by the fact that diagonal images outperform the original images for conventional two-dimensional (2D) subspace learning methods such as 2D principal component analysis (2DPCA) and 2D linear discriminant analysis (2DLDA), we first propose applying diagonal images to a recently proposed 2D discriminant locality preserving projections (2D-DLPP) algorithm, and formulate the Dia-DLPP method for feature extraction of face and palmprint images. Moreover, we show that transforming an image to a diagonal image is equivalent to assigning an appropriate weight to each pixel of the original image to emphasize its different importance for recognition, which provides the rationale and superiority of using diagonal images for 2D subspace learning. Inspired by this finding, we further propose a new discriminant weighted method to explicitly calculate the discriminative score of each pixel within a face and palmprint sample to duly emphasize its different importance, and incorporate it into 2D-DLPP to formulate the W2D-DLPP method to improve the recognition performance of 2D-DLPP and Dia-DLPP. Experimental results on the widely used FERET face and PolyU palmprint databases demonstrate the efficacy of the proposed methods.