有效用于人脸识别的光照不变特征表示算法

在光照变化环境下,人脸识别的鲁棒性是人脸识别系统中一大挑战。针对光照变化对人脸识别的影响,对经典光照不变特征表示算法进行了研究,提出一种基于局部标准差光照不变的人脸特征表示算法及其加权形式。结合完备线性鉴别分析（Complete-Linear Discriminant Analysis,C-LDA）算法提取特征,在Extended Yale-B与YALE 人脸库中,与其他处理光照变化的经典方法相比,如多尺度Retinex（Multi Scale Retinex,MSR）、韦伯脸（Weber-Face,WF）和局部归一化（Local Normalization,LN）,提出的算法能获得更高识别率。     

用于目标快速识别的特征选取方法

现有的基于图像局部特征的目标识别算法,在保证较高识别率的情况下无法满足实时性要求。针对这个问题,考虑到多数局部特征是不稳定、不可靠或与目标无关的,可通过正确匹配的训练图像,对图像局部特征选取一个子集用于目标识别。提出一种在特征包方法基础上,通过无监督地选取鲁棒性强及足够特殊、稳定的局部特征用于目标识别的新方法并应用于目标识别实验。实验结果证实该方法在仅仅使用原图像约4%的局部特征的情况下获得了与使用全部局部特征几乎相近的目标识别率,目标识别时间由秒缩短至几十毫秒,满足了目标识别实时性要求。     

基于改进极限学习机算法的行为识别

重点研究了极限学习机ELM对行为识别检测的效果。针对在线学习和行为分类上存在计算复杂性和时间消耗大的问题,提出了一种新的行为识别学习算法(ELM-Cholesky)。该算法首先引入了基于Cholesky分解求ELM的方法,接着依据在线学习期间核函数矩阵的更新特点,将分块矩阵Cholesky分解算法用于ELM的在线求解,使三角因子矩阵实现在线更新,从而得出一种新的ELM-Cholesky在线学习算法。新算法充分利用了历史训练数据,降低了计算的复杂性,提高了行为识别的准确率。最后,在基准数据库上采用该算法进行了大量实验,实验结果表明了这种在线学习算法的有效性。     

Efficient semiparametric estimation via Cholesky decomposition for longitudinal data

Semiparametric methods for longitudinal data with dependence within subjects have recently received considerable attention. Existing approaches that focus on modeling the mean structure require a correct specification of the covariance structure as misspecified covariance structures may lead to inefficient or biased mean parameter estimates. Besides, computation and estimation problems arise when the repeated measurements are taken at irregular and possibly subject-specific time points, the dimension of the covariance matrix is large, and the positive definiteness of the covariance matrix is required. In this article, we propose a profile kernel approach based on semiparametric partially linear regression models for the mean and model covariance structures simultaneously, motivated by the modified Cholesky decomposition. We also study the large-sample properties of the parameter estimates. The proposed method is evaluated through simulation and applied to a real dataset. Both theoretical and empirical results indicate that properly taking into account the within-subject correlation among the responses using our method can substantially improve efficiency.     

目标识别中的稳定图像特征组合发掘

针对图像局部特征组合稳定性差和区分力不足的问题,通过对由图像半局部邻域特征挖掘得到的频繁项集进行统计学过滤、模式分解、模式总结及模式组成项间几何关系的建模,提出两种具有较强表征力和区分力的图像中层表示模型:类间共用稳定模式(inter-class common stable pattern)和类内特殊稳定模式(intra-class special stable pattern)。在将这两种模式引入目标识别框架后,得到了相比同类方法较好的结果。     

基于RGB-D图像核描述子的物体识别方法

针对传统的颜色-深度（RGB-D）图像物体识别的方法所存在的图像特征学习不全面、特征编码鲁棒性不够等问题,提出了基于核描述子局部约束线性编码（KD-LLC）的RGB-D图像物体识别方法。首先,在图像块间匹配核函数基础上,应用核主成分分析法提取RGB-D图像的3D形状、尺寸、边缘、颜色等多个互补性核描述子;然后,分别对它们进行LLC编码及空间池化处理以形成相应的图像编码向量;最后,把这些图像编码向量融合成具有鲁棒性、区分性的图像表示。基于RGB-D数据集的仿真实验结果表明,作为一种基于人工设计特征的RGB-D图像物体识别方法,由于所提算法综合利用深度图像和RGB图像的多方面特征,而且对传统深度核描述子的采样点选取和紧凑基向量的计算这两方面进行了改进,使得物体类别识别率达到86.8%,实体识别率达到92.7%,比其他同类方法具有更高的识别准确率。     

广义Hermitian特征问题标准化转换的有效并行块算法

广义Hermitian特征问题并行求解器的性能依赖于所选择的并行算法和矩阵的分布策略等诸多方面.基于块存储和快算法策略,提出了一个新的标准化转化的并行算法,该并行算法将Cholesky分解结合到广义特征问题标准化转换中, 降低了已有并行算法的通信开销,并增加了算法的并行性.新算法可显著改善已有并行算法的性能和可扩展性.另外给出了一个有效求解具有多个右端项的三角矩阵方程AX=B的并行块算法.通过自主开发的特征问题并行软件包PSEPS的测试结果表明,并行算法比传统的并行算法快大约1倍,并具有较好的可扩展性.     

红外图像中的道路识别与表示

对机器人视觉导航而言，道路识别和表示是一个非常重要的环节，它直接影响到后续的路径规划。该文针对红外道路图像，提出了基于区域方法的一套处理方案，该方法首先通过分割获得道路区域，利用链码跟踪获取道路边缘的链码。采用了一种通用的道路模型，然后基于链码以及该道路模型，设计了一种有效的道路边界拟合方法。在拟合过程中，首先依据一定的准则把链码分为两段，对于每一段再递归执行该分段过程，直到不能分为止，然后用分段直线去描述道路边界。该拟合算法可以有效地处理直道和非直道的情况。文中给出了相关的实验结果。     

Spatially dependent regularization parameter selection in total generalized variation models for image restoration

In this paper, the automated spatially dependent regularization parameter selection framework for multi-scale image restoration is applied to total generalized variation (TGV) of order 2. Well-posedness of the underlying continuous models is discussed and an algorithm for the numerical solution is developed. Experiments confirm that due to the spatially adapted regularization parameter, the method allows for a faithful and simultaneous recovery of fine structures and smooth regions in images. Moreover, because of the TGV regularization term, the adverse staircasing effect, which is a well-known drawback of the total variation regularization, is avoided.     

基于小波分解的高温物体图像快速识别方法*

摘要：提出了一种基于小波分解和多分辨率分析的高温图像快速识别方法。首先通过小波分解降低原始图像直方图的灰度级,从而减小了分割阈值的搜索范围,再结合最大类间方差法计算分割阈值,这样可以快速找到分割阈值。实验结果表明,该方法能够显著提高分割速度并准确分割出目标图像。     

A stochastic graph grammar for compositional object representation and recognition

This paper illustrates a hierarchical generative model for representing and recognizing compositional object categories with large intra-category variance. In this model, objects are broken into their constituent parts and the variability of configurations and relationships between these parts are modeled by stochastic attribute graph grammars, which are embedded in an And-Or graph for each compositional object category. It combines the power of a stochastic context free grammar (SCFG) to express the variability of part configurations, and a Markov random field (MRF) to represent the pictorial spatial relationships between these parts. As a generative model, different object instances of a category can be realized as a traversal through the And-Or graph to arrive at a valid configuration (like a valid sentence in language, by analogy). The inference/recognition procedure is intimately tied to the structure of the model and follows a probabilistic formulation consisting of bottom-up detection steps for the parts, which in turn recursively activate the grammar rules for top-down verification and searches for missing parts. We present experiments comparing our results to state of art methods and demonstrate the potential of our proposed framework on compositional objects with cluttered backgrounds using training and testing data from the public Lotus Hill and Caltech datasets.     

A syntactic method for image segmentation and object recognition

In this paper, image segmentation and object recognition using syntactic methods are investigated. The segmentation process is embedded in the parsing algorithm. The approach can be described by a syntax-directed relaxation process. Previous error-correcting parsing algorithms, however, have not tackled the segmentation problem satisfactorily. Experimental results using Synthetic Aperture Radar (SAR) images are given.     

A feature construction method for general object recognition

This paper presents a novel approach for object detection using a feature construction method called Evolution-COnstructed (ECO) features. Most other object recognition approaches rely on human experts to construct features. ECO features are automatically constructed by uniquely employing a standard genetic algorithm to discover series of transforms that are highly discriminative. Using ECO features provides several advantages over other object detection algorithms including: no need for a human expert to build feature sets or tune their parameters, ability to generate specialized feature sets for different objects, and no limitations to certain types of image sources. We show in our experiments that ECO features perform better or comparable with hand-crafted state-of-the-art object recognition algorithms. An analysis is given of ECO features which includes a visualization of ECO features and improvements made to the algorithm.     

Query-expanded collaborative representation based classification with class-specific prototypes for object recognition

Linear representation based classifiers (LinearRCs) assume that a query image can be represented as a linear combination of dictionary atoms or prototypes with various priors (e.g., sparsity), which have achieved impressive results in face recognition. Recently, a few attempts have been made to deal with more general cases (e.g., multi-view or multi-pose objects, more generic objects, etc.) but with additional requirements. In this paper, we present a query-expanded collaborative representation based classifier with class-specific prototypes (QCRC_CP) from the general perspective. First, we expand a single query in a multi-resolution way to cover rich variations of object appearances, thereby generating a query set. We then condense the gallery images to a small amount of prototypical images by maximizing canonical correlation in a class-specific way, in which the implicit query-dependent data locality discards the outliers. Given the query set, we finally propose a multivariate LinearRC with collaborative prior to identify the query according to the rule of minimum normalized residual (MNR). Experiments on four object recognition datasets (FERET pose, Swedish leaf, Chars74K, and ETH-80) show that our method outperforms the state-of-the-art LinearRCs with performance increases at least 3.1%, 3.8%, 10.4% and 3.1% compared to other classifiers.     

Using an ICA representation of local color histograms for object recognition

This paper applies a Bayesian classification scheme to the problem of object recognition through probabilistic modeling of local color histograms. In this context, the density estimation is generally performed via nonparametric kernel methods and the high dimensionality does not allow precision in the results. We propose a local independent component analysis (ICA) representation of the data. Within this representation, the components can be assumed statistically independent and, for this particular problem, sparsity of the independent components is observed. We show how these two characteristics simplify and add accuracy to the density estimation and develop a Bayesian decision scheme within this representation. We propose a set of possible density estimations for supergaussian densities, the density type associated with a sparse representation. Two experiments were performed. The first one illustrates the properties of the ICA representation for local color histograms. The second experiment tests the ICA classification model for a large set of pharmaceutical products and compares this scheme with a nonparametric technique based on Gaussian Kernels, two nearest-neighbor techniques and global histogram approach.     

多尺度Transformer与层次化边界引导的显著性目标检测

针对显著性目标检测算法中全局和局部信息难以联合表征和目标边界难以细化的问题,提出了一种多尺度Transformer与层次化边界引导的显著性目标检测算法。首先,构建Transformer模型提取全局信息,同时通过自注意力机制获取有判别性的浅层局部特征,对全局和局部信息进行联合表征。然后,引入Tokens-to-Token方法提取多尺度特征,使模型实现尺度变换平滑的编解码。进一步,提出了一种层次化的边界学习策略,引导模型在每个解码特征层提取精细化的显著性目标边界特征,提升显著性目标边界的预测准确性。实验结果表明,提出的算法在四个公开显著性目标检测数据集上均优于八种主流的显著性目标检测算法,并且通过消融实验验证了提出模型和边界学习策略的有效性。     

改进的矩形NAM图像表示算法

为了提高图像的表示效率,提出了一种改进的矩形非对称逆布局模式表示模型(NAM)图像编码算法IRNAM。该算法采用双矩形子模式对灰度图像进行表示,结合位平面优化策略,并顺序存储各子模式的数据,使得子模式数目大幅减少。实验结果表明：与矩形NAM算法和其他改进的NAM算法相比, IRNAM算法使表示图像的子模式数明显减少了,从而有效地节省了数据存储空间,是一种高效的图像表示方法。