SR-SIHKS：一种非刚体全局形状特征

非刚体由于姿态变化会产出多样的形变,因此非刚体的形状检索比刚体更具挑战性。形状特征提取是非刚体三维模型形状检索的关键问题。为了提高非刚体形状检索的准确度,提出了一种非刚体全局形状特征提取方法。此方法的核心思想是将稀疏表示（Sparse Representation,SR）理论用于对尺度无关的热核特征（Scale Invariant Heat Kernel Signature,SIHKS）进行稀疏编码,因此被称为SR-SIHKS。改进了SIHKS局部特征的提取方法,根据所处理的模型库来自适应地确定热扩散时间参数;采用K-SVD算法来训练字典,借助Batch-OMP算法实现局部特征的稀疏编码;将非刚体三维模型的所有局部特征的稀疏编码汇聚为全局形状特征。实验结果表明,SR-SIHKS具有比SIHKS和HKS更优的检索效果。     

Non‐negative sparse‐based SemiBoost for software defect prediction

Software defect prediction is an important decision support activity in software quality assurance. The limitation of the labelled modules usually makes the prediction difficult, and the class‐imbalance characteristic of software defect data leads to negative influence on decision of classifiers. Semi‐supervised learning can build high‐performance classifiers by using large amount of unlabelled modules together with the labelled modules. Ensemble learning achieves a better prediction capability for class‐imbalance data by using a series of weak classifiers to reduce the bias generated by the majority class. In this paper, we propose a new semi‐supervised software defect prediction approach, non‐negative sparse‐based SemiBoost learning. The approach is capable of exploiting both labelled and unlabelled data and is formulated in a boosting framework. In order to enhance the prediction ability, we design a flexible non‐negative sparse similarity matrix, which can fully exploit the similarity of historical data by incorporating the non‐negativity constraint into sparse learning for better learning the latent clustering relationship among software modules. The widely used datasets from NASA projects are employed as test data to evaluate the performance of all compared methods. Experimental results show that non‐negative sparse‐based SemiBoost learning outperforms several representative state‐of‐the‐art semi‐supervised software defect prediction methods. Copyright © 2016 John Wiley & Sons, Ltd.     

字典重建和空间分布关系约束下的特征选择与图像拼接

目的 针对大型图像检索领域中,复杂图像中SIFT特征描述子的冗余和高维问题,提出了一种基于字典重建和空间分布关系约束的特征选择的方法,来消除冗余特征并保留最具表现力的、保留原始空间结构性的SIFT特征描述子。方法 首先,实验发现了特征选择和字典学习方法在稀疏表示方面的内在联系,将特征选择问题转化为字典重构任务;其次,在SIFT特征选择问题中,为了保证特征空间中特征的鲁棒性,设计了新型的字典学习模型,并采用模拟退火算法进行迭代求解;最后,在字典学习的过程中,加入熵理论来约束特征的空间分布,使学习到的特征描述子能最大限度保持原始SIFT特征空间的空间拓扑关系。结果 在公开数据集Holiday大型场景图片检索数据库上,通过与国际公认的特征选择方法进行实验对比,本文提出的特征选择方法在节省内存空间和提高时间效率（30%~ 50%）的同时,还能保证所筛选的特征描述子的检索准确率比同类特征提高8%~ 14.1%;在国际通用的大型场景图片拼接数据库IPM上,验证本文方法在图像拼接应用中特征提取和特征匹配上的有效性,实验表明本文方法能节省（50% ~70%）图像拼接时间。结论 与已有的方法比较,本文的特征选择方法既不依赖训练数据集,也不丢失重要的空间结构和纹理信息,在大型图像检索、图像拼接领域和3D检索领域中,能够精简特征,提高特征匹配效率和准确率。     

Identifying composite crosscutting concerns through semi‐supervised learning

Aspect mining improves the modularity of legacy software systems through identifying their underlying crosscutting concerns (CCs). However, a realistic CC is a composite one that consists of CC seeds and relative program elements, which makes it a great challenge to identify a composite CC. In this paper, inspired by the state‐of‐the‐art information retrieval techniques, we model this problem as a semi‐supervised learning problem. First, the link analysis technique is adopted to generate CC seeds. Second, we construct a coupling graph, which indicates the relationship between CC seeds. Then, we adopt community detection technique to generate groups of CC seeds as constraints for semi‐supervised learning, which can guide the clustering process. Furthermore, we propose a semi‐supervised graph clustering approach named constrained authority‐shift clustering to identify composite CCs. Two measurements, namely, similarity and connectivity, are defined and seeded graph is generated for clustering program elements. We evaluate constrained authority‐shift clustering on numerous software systems including large‐scale distributed software system. The experimental results demonstrate that our semi‐supervised learning is more effective in detecting composite CCs. Copyright © 2013 John Wiley & Sons, Ltd.     

基于词包和特征融合的目标识别算法

针对现有词包模型对目标识别性能的不足,对特征提取、图像表示等方面进行改进以提高目标识别的准确率。首先,以密集提取关键点的方式取代SIFT关键点提取,减少了计算时间并最大程度地描述了图像底层信息。然后采用尺度不变特征变换(Scale-invariant feature transform, SIFT)描述符和统一模式的局部二值模式(Local binary pattern,LBP)描述符描述关键点周围的形状特征和纹理特征,引入K-Means聚类算法分别生成视觉词典,然后将局部描述符进行近似局部约束线性编码,并进行最大值特征汇聚。分别采用空间金字塔匹配生成具有空间信息的直方图,最后将金字塔直方图相串联,形成特征的图像级融合,并送入SVM进行分类识别。在公共数据库中进行实验,实验结果表明,本文所提方法能取得较高的目标识别准确率。     

Data‐Driven Sparse Priors of 3D Shapes

We present a sparse optimization framework for extracting sparse shape priors from a collection of 3D models. Shape priors are defined as point‐set neighborhoods sampled from shape surfaces which convey important information encompassing normals and local shape characterization. A 3D shape model can be considered to be formed with a set of 3D local shape priors, while most of them are likely to have similar geometry. Our key observation is that the local priors extracted from a family of 3D shapes lie in a very low‐dimensional manifold. Consequently, a compact and informative subset of priors can be learned to efficiently encode all shapes of the same family. A comprehensive library of local shape priors is first built with the given collection of 3D models of the same family. We then formulate a global, sparse optimization problem which enforces selecting representative priors while minimizing the reconstruction error. To solve the optimization problem, we design an efficient solver based on the Augmented Lagrangian Multipliers method (ALM). Extensive experiments exhibit the power of our data‐driven sparse priors in elegantly solving several high‐level shape analysis applications and geometry processing tasks, such as shape retrieval, style analysis and symmetry detection.     

基于改进稀疏栈式编码的车型识别

为了提高稀疏栈式编码对车型识别确率,提出了一种基于改进稀疏栈式编码的车型识别方法。使用逐层无监督方法来训练网络结构,并从大量的无标记的数据集中学习得到特征字典,在稀疏栈式编码的基础上引入卷积和池化模块,把学习得到的特征字典作为卷积核,通过对含有车辆的图像进行卷积和池化操作获得图像的特征图;最后通过使用softmax分类器在少量标签数据集上进行有监督的微调。在BIT-Vehicle数据集上的实验结果表明,改进后的算法优于传统稀疏栈式编码算法,在标注较少的数据集中,识别的准确率优于神经网络算法。     

Learning optimized features for hierarchical models of invariant object recognition

There is an ongoing debate over the capabilities of hierarchical neural feedforward architectures for performing real-world invariant object recognition. Although a variety of hierarchical models exists, appropriate supervised and unsupervised learning methods are still an issue of intense research. We propose a feedforward model for recognition that shares components like weight sharing, pooling stages, and competitive nonlinearities with earlier approaches but focuses on new methods for learning optimal feature-detecting cells in intermediate stages of the hierarchical network. We show that principles of sparse coding, which were previously mostly applied to the initial feature detection stages, can also be employed to obtain optimized intermediate complex features. We suggest a new approach to optimize the learning of sparse features under the constraints of a weight-sharing or convolutional architecture that uses pooling operations to achieve gradual invariance in the feature hierarchy. The approach explicitly enforces symmetry constraints like translation invariance on the feature set. This leads to a dimension reduction in the search space of optimal features and allows determining more efficiently the basis representatives, which achieve a sparse decomposition of the input. We analyze the quality of the learned feature representation by investigating the recognition performance of the resulting hierarchical network on object and face databases. We show that a hierarchy with features learned on a single object data set can also be applied to face recognition without parameter changes and is competitive with other recent machine learning recognition approaches. To investigate the effect of the interplay between sparse coding and processing nonlinearities, we also consider alternative feedforward pooling nonlinearities such as presynaptic maximum selection and sum-of-squares integration. The comparison shows that a combination of strong competitive nonlinearities with sparse coding offers the best recognition performance in the difficult scenario of segmentation-free recognition in cluttered surround. We demonstrate that for both learning and recognition, a precise segmentation of the objects is not necessary.     

深度特征融合的非刚性三维形状局部匹配

针对海量、异构三维形状匹配与智能检索技术的需求,提出了一种基于级联卷积神经网络(F-PointCNN)深度特征融合的三维形状局部匹配方法.首先,采用特征袋模型,提出几何图像表示方法,该几何图像不仅能够有效区分同类异构的非刚性三维模型,而且能够揭示大尺度不完整三维模型的结构相似性.其次,构建级联卷积神经网络学习框架F-PointCNN,其中,BoF-CNN从几何图像中学习深度全局特征,建立融合局部特征与全局特征的点特征表示;进而对Point-CNN进行点特征的细化与提纯,生成具有丰富信息的深度融合特征,有效提高形状特征的区分性与鲁棒性.最终,通过交叉矩阵度量方法高效实现非刚性三维模型的局部形状匹配.在公开的非刚性三维模型数据库的实验结果表明,该方法提取的特征在大尺度变换的形状分类及局部形状匹配中具有更强的识别力与更高的匹配精度.     

基于多视觉词典的显著性加权图像检索方法

针对视觉词典在图像表示与检索方面的应用需求,本文提出了一种基于多视觉词典与显著性加权相结合的图像检索方法,实现了图像多特征的显著性稀疏表示。该方法首先划分图像为小块,提取图像块的多种底层特征,然后将其作为输入向量,通过非负稀疏编码分别学习图像块多种特征对应的视觉词典,将得到的图 像块稀疏向量经过显著性汇总方法引入空间信息并作显著性加权处理,形成整幅图像的稀疏表示,最后采用提出的SDD距离计算方式进行图像检索。在Corel和Caltech通用图像集上进行仿真实验,与单一视觉词典的方法对比,结果表明本文方法能够有效提高图像检索的准确率。     

基于深度网络的可学习感受野算法在图像分类中的应用

作为图像检索,图像组织和机器人视觉的基本任务,图像分类在计算机视觉和机器学习中受到了广泛的关注.用于目标识别及图像分类的多种基于深度学习的模型同样引发了该领域内的极大兴趣.本文提出了一种取代尺度不变特征变换(SIFT)和方向梯度直方图(HOG)描述子的算法,即利用深度分层结构,按层级学习有效的图像表示,直接从原始像素点学习特征.该方法分别利用K--奇异值分解(K--SVD)和正交匹配追踪(OMP)进行字典训练和编码.此外,本文采用了同时学习分类器和用于池化的感受野方案.实验结果证明,上述算法在目标(Oxford flowers)和事件(UIUC--sports)图像分类测试集中取得了更好的分类性能.