人脸识别特征提取方法和相似度匹配方法研究

横向比较特征提取方法，综合考虑认证率和特征提取时间两方面因素，该文认为特征脸结合线性判别分析方法是研究的4种特征提取方法中最优的方法。通过对投影空间维数的研究，最佳投影空间维数同数据库本身类内图像的相似程度和每一类的样本数目同方向增长，它们之间存在定性关系而非定量关系。相似度匹配方法的研究结果表明余弦距离分类器分类效果最佳。     

深度学习人脸特征点自动定位综述

人脸特征点定位是根据输入的人脸数据自动定位出预先按人脸生理特征定义的眼角、鼻尖、嘴角和脸部轮廓等面部关键特征点,在人脸识别和分析等系统中起着至关重要的作用。本文对基于深度学习的人脸特征点自动定位进行综述,阐释了人脸特征点自动定位的含义,归纳了目前常用的人脸公开数据集,系统阐述了针对2维和3维数据特征点的自动定位方法,总结了各方法的研究现状及其应用,分析了当前人脸特征点自动定位技术在深度学习应用中的现状、存在问题及发展趋势。在公开的2维和3维人脸数据集上对不同方法进行了比较。通过研究可以看出,基于深度学习的2维人脸特征点的自动定位方法研究相对比较深入,而3维人脸特征点定位方法的研究在模型表示、处理方法和样本数量上都存在挑战。未来基于深度学习的3维人脸特征点定位方法将成为研究趋势。     

Improving SVM classification on imbalanced time series data sets with ghost points

Imbalanced data sets present a particular challenge to the data mining community. Often, it is the rare event that is of interest and the cost of misclassifying the rare event is higher than misclassifying the usual event. When the data is highly skewed toward the usual, it can be very difficult for a learning system to accurately detect the rare event. There have been many approaches in recent years for handling imbalanced data sets, from under-sampling the majority class to adding synthetic points to the minority class in feature space. However, distances between time series are known to be non-Euclidean and non-metric, since comparing time series requires warping in time. This fact makes it impossible to apply standard methods like SMOTE to insert synthetic data points in feature spaces. We present an innovative approach that augments the minority class by adding synthetic points in distance spaces. We then use Support Vector Machines for classification. Our experimental results on standard time series show that our synthetic points significantly improve the classification rate of the rare events, and in most cases also improves the overall accuracy of SVMs. We also show how adding our synthetic points can aid in the visualization of time series data sets.     

最优几何匹配程序下重建时间连贯3D动画的研究

对RGB-D数据的三维重建进行优化,由此提出基于时间连贯的重建策略。在完成数据收集之后,对其中的RGB数据进行光学特征点的提取,由此获取两帧相互之间的初始系数3D关系。在对这些特征点进行细化时,则运用了最优几何匹配系统,然后利用特征点对连续帧的三维点云展开匹配,这个过程与帧分辨率独立;最后完成时间连贯的3D动画重建,具体是借助于运动向量对齐策略。通过实验得出,本文提出的策略能够对该3D动画进行重建。相较于其他方法,数据利用率更高,同时还有较高的精准度,在计算效率方面也具有一定优势。     

基于经验分布的打车概率和等待时间预测

提出了一种预测乘客在指定位置和指定时间预测打车概率和等待时间的方法。设计了一种将地图离散化,使用特征点修复GPS轨迹的解决方案,且适用于大数据问题;在修复的GPS数据基础上提出了基于经验分布在等待特征点和时间点的打车概率和等待时间模型;并基于该模型预测用户指定位置和指定时间的打车概率。另外给出了基于该模型的增量学习的方法。大规模GPS轨迹数据使用Hadoop平台实现了管理和分析计算,证明了该方案的可行性;预测结果在仿真实验中取得了良好的效果,证明了模型具有较高的准确性,同时可以期望准确性随着数据量的增大而提升;另外该模型得到的特征点和特征时间概率和等待时间的参考表并不会随着GPS轨迹数据的增大而增大,证明了模型有良好的可扩展性。     

基于CNN-LSTM的活动识别方法

在识别活动时,传统的循环神经网络RNN识别方法不考虑传感器活动数据之间依赖性强的问题,导致识别准确率降低。为了提高识别准确率,解决活动数据依赖性强的问题,用长短期记忆网络LSTM进行活动识别,LSTM在考虑当前点输入的同时考虑先前点的输出,能够保持数据之间的强依赖性。但是,LSTM在处理传感器活动数据的特征提取方面时间效率不高,而卷积神经网络CNN能共享卷积核,且可以从杂乱无章的数据中提取出明显特征向量。提出一种基于CNN-LSTM的活动识别方法CLAR,利用CNN能够很好地提取出活动序列数据中的特征向量,并将提取出的特征向量作为LSTM的输入,利用LSTM门限之间的相互作用进行活动识别,使得依赖性很强的活动数据成为活动识别的优势,进而提高活动识别的准确率和时间效率。实验表明,CLAR方法的识别准确率比单一神经网络活动识别方法的准确率提高了9%,时间平均缩短了10%。     

Performing event detection in time series with SwiftEvent: an algorithm with supervised learning of detection criteria

The automated detection of points in a time series with a special meaning to a user, commonly referred to as the detection of events, is an important aspect of temporal data mining. These events often are points in a time series that can be peaks, level changes, sudden changes of spectral characteristics, etc. Fast algorithms are needed for event detection for online applications or applications with huge time series data sets. In this article, we present a very fast algorithm for event detection that learns detection criteria from labeled sample time series (i.e., time series where events are marked). This algorithm is based on fast transformations of time series into low-dimensional feature spaces and probabilistic modeling techniques to identify criteria in a supervised manner. Events are then found in one, single fast pass over the signal (therefore, the algorithm is called SwiftEvent) by evaluating learned thresholds on Mahalanobis distances in the feature space. We analyze the run-time complexity of SwiftEvent and demonstrate its application in some use cases with artificial and real-world data sets in comparison with other state-of-the-art techniques.     

OPTICS聚类与目标区域概率模型的多运动目标跟踪

目的 针对多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题,本文提出了一种基于OPTICS聚类与目标区域概率模型的方法。方法 首先引入了Harris-Sift特征点检测,完成相邻帧特征点匹配,提高了特征点跟踪精度和鲁棒性;再根据各运动目标与背景运动向量不同这一点,引入了改进后的OPTICS加注算法,在构建的光流图上聚类,从而准确的分离出背景,得到各运动目标的估计区域;对每个运动目标建立一个独立的目标区域概率模型(OPM),随着检测帧数的迭代更新,以得到运动目标的准确区域。结果 多运动目标在移动背景情况下跟踪性能下降和准确度不高的问题通过本文方法得到了很好地解决,Harris-Sift特征点提取、匹配时间仅为Sift特征的17%。在室外复杂环境下,本文方法的平均准确率比传统背景补偿方法高出14%,本文方法能从移动背景中准确分离出运动目标。结论 实验结果表明,该算法能满足实时要求,能够准确分离出运动目标区域和背景区域,且对相机运动、旋转,场景亮度变化等影响因素具有较强的鲁棒性。     

High dimensional similarity joins: algorithms and performanceevaluation

Current data repositories include a variety of data types, including audio, images, and time series. State-of-the-art techniques for indexing such data and doing query processing rely on a transformation of data elements into points in a multidimensional feature space. Indexing and query processing then take place in the feature space. We study algorithms for finding relationships among points in multidimensional feature spaces, specifically algorithms for multidimensional joins. Like joins of conventional relations, correlations between multidimensional feature spaces can offer valuable information about the data sets involved. We present several algorithmic paradigms for solving the multidimensional join problem and we discuss their features and limitations. We propose a generalization of the size separation spatial join algorithm, named multidimensional spatial join (MSJ), to solve the multidimensional join problem. We evaluate MSJ along with several other specific algorithms, comparing their performance for various dimensionalities on both real and synthetic multidimensional data sets. Our experimental results indicate that MSJ, which is based on space filling curves, consistently yields good performance across a wide range of dimensionalities     

基于Web挖掘的Web服务器入侵检测研究

针对传统的防火墙技术和网络检测技术不再能准确、及时地发现对服务器的攻击行为提出了基于Web数据挖掘技术的一种服务器入侵检测方法：首先由目前已经掌握的对服务器攻击行为特征作为样本点,采用k-均值聚类分析算法进行无监督学习,生成K个聚类的特征攻击库;其次采用邻近分类算法,根据计算访问样本点与特征攻击库中心的距离对样本点进行归并;最后对特征攻击库中心点进行重新调整,确保对新的样本点行为分析更加准确。     

一种基于Markov链模型的动态聚类方法

对单变量时间序列的聚类，是一类有着广泛应用背景的特殊的聚类问题。由于该问题的特殊性，现有的聚类方法无法直接使用，故提出了一种新的基于Markov链模型的动态聚类方法。该方法首先对每一个时间序列建立一个描述其动态特征的Markov链模型，从而把对时间序列的聚类问题转化为对Markov链模型的聚类问题。然后通过定义各个Markov链之间的“距离”，采用动态聚类算法完成对这些Markov链模型的聚类，使用该方法，分别对一经真实数据和仿真数据进行了聚类试验，都获得了比较好的聚类结果。     

基于改进快速鲁棒性特征的导弹视频特征匹配

利用电视制导导弹视频图像确定导弹落点,从而开展精确目标毁伤评估研究,是目前全新的一种评估手段。图像特征匹配是利用视频图像确定导弹落点的关键步骤。针对导弹视频图像的特点及其作战应用,在特征匹配阶段,依据准确性和实时性两个原则,对快速鲁棒性特征算法做了两方面的改进:一是限制特征点提取区域,定义了图像区域限制算子;二是限制特征点数量,利用算法阈值和随机抽样一致性算法对特征点进行限制。实验结果表明,提出的算法对典型视频片段进行处理,较原算法在匹配时间上平均减少12.6%,匹配准确率平均提升13.4%,较尺度不变特征变换算法匹配时间平均提升了74.9%,同时,有效消除伪匹配点。通过对三段视频进行测试仿真,改进算法在整体上较原算法的匹配时间加快14.9%,且通用性较强,适用于视频图像的特征点匹配。     

显著度可控的DEM地形特征线提取

目的 基于数字高程模型（DEM）的地形山脊线和山谷线提取对地形模型简化、基于样本的地形合成和地形地貌研究有重要意义,针对许多传统算法无法对所提取特征线的显著度进行方便准确的控制,以及不支持环形特征线提取的问题,提出一种新的显著度可控的DEM地形特征线提取算法。方法 首先利用全局断面扫描算法提取特征点并计算各特征点的显著度,然后根据特征点的特征方向进行特征延伸以增强特征连通性,接着采用改进的Hilditch细线化算法对特征点集合进行细线化处理,之后为相邻特征点添加特征边,构成特征图,利用环路检测与破环算法检测特征图中的环路,并破除冗余小环路,最后根据分支显著度的相似度和分支方向一致性进行特征图分解,计算分解得到特征线的显著度并筛选得到最终特征线。结果 使用真实DEM数据提取最显著的若干条特征线,与现有的基于特征显著度的地形特征线提取算法进行对比,本文算法对特征图的分解能够更准确地提取主干特征线,而基于显著度的特征线筛选控制也更加准确合理。对提出的环路检测与破环算法进行实验验证,该算法能保留大的山脊线环路,破除小的冗余环路。结论 实验结果表明,本文算法能有效实现显著度可控的山脊线和山谷线自动提取,提取结果与人眼观察结果基本一致,同时能够支持含有环形特征的地形。     

基于Hausdorff距离图象配准方法研究

图象配准是图象融合的一个重要步骤，为此提出了一种自动图象配准算法，该算法从两幅待配准的图象中分别抽取特征点，然后选用Hausdorff距离对两特征点集进行匹配，得到点集间的仿射变换，从而实现图象的自动配准，此算法以特征点而不是物体边缘计算仿射变换，大大降低了计算Hausdorff距离的运算量；同时，基于Hausdorff距离的图象匹配只需要点集之间的对应，而无须点与点的对应，因而可以使用于存在较大物体形变的情况，即完成两幅差异较大图象的配准，实验结果证明了算法的有效性。     

Improvements and critique on Sugeno's and Yasukawa's qualitative modeling

Investigates Sugeno's and Yasukawa's (1993) qualitative fuzzy modeling approach. We propose some easily implementable solutions for the unclear details of the original paper, such as trapezoid approximation of membership functions, rule creation from sample data points, and selection of important variables. We further suggest an improved parameter identification algorithm to be applied instead of the original one. These details are crucial concerning the method's performance as it is shown in a comparative analysis and helps to improve the accuracy of the built-up model. Finally, we propose a possible further rule base reduction which can be applied successfully in certain cases. This improvement reduces the time requirement of the method by up to 16% in our experiments.     

一种支持多版权的地理数据增量水印方法

目前地理数据水印方法有很多,但大都缺少对地理数据同步保护的考虑,同时没有在同步保护的基础上进行多版权水印嵌入的方法。分析了地理数据增量水印和多版权水印的问题,基于量化调制技术,提出了一种能兼顾增量水印和多版权水印的地理数据水印方法。该方法采用基于距离划分的策略,将特征点集划分成两个可重现的不相交子集,通过分别缩放两个子集嵌入双重水印,保证了所有顶点都只在精度范围内修改一次,使保真性得到控制。此外,缩放调制策略使地理数据形状尽可能得到保证。实验表明,该方法能满足增量水印和多版权水印的要求,同时具有很好的鲁棒性。     

遥感影像空间分治快速匹配

目的 图像匹配是遥感图像镶嵌拼接的重要环节,图像匹配技术通常采用两步法,首先利用高维描述子的最近和次近距离比建立初始匹配,然后通过迭代拟合几何模型消除错误匹配。尽管外点过滤算法大幅提高了时间效率,但其采用传统的两步法,构建初始匹配的方法仍然非常耗时,导致整个遥感图像拼接的速度提升仍然有限。为了提高遥感图像匹配的效率,本文提出了一种基于空间分治思想的快速匹配方法。方法 首先,通过提取图像的大尺度特征生成少量的初始匹配,并基于初始匹配在两幅图像之间构建成对的分治空间中心点;然后,基于范围树搜索分治空间中心点一定范围内的相邻特征点,构造成对分治空间点集;最后,在各个分治空间点集内分别进行遥感图像特征的匹配。结果 通过大量不同图像尺寸和相对旋转的遥感图像的实验表明,与传统的和其他先进方法相比,本文方法在保证较高精度的同时将匹配时间缩短到1/1001/10。结论 利用初始种子匹配构建分治匹配中心以将图像匹配分解在多个子区间进行的方法有助于提高遥感影像匹配的效率,该算法良好的时间性能对实时遥感应用具有实际价值。     

Misleading architecting tradeoffs [DVD hard-disk architecture tradeoff analysis method]

A DVD hard-disk recorder case study shows how system architects can fall prey to ill-founded qualitative reasoning, which can lead them to favor unsupported tradeoffs that are based on incorrect assumptions. A tradeoff assumes that an improvement in one dimension negatively affects others. Sound, valid tradeoffs do exist, but not every decision calls for one. A bold improvement in one dimension can improve other dimensions of the design space, even though these possibilities can contradict major opinions or general heuristics. The product chosen for the development project, a Philips DVD hard-disk recorder, is called a combi because it combines a hard-disk recorder function with a DVD recorder function. Combining the two recorders provided the main added value of having the strong points of one compensate for the weak points of the other.     

Efficient Near Neighbor Searching Using Multi-Indexes for Content-Based Multimedia Data Retrieval

Many content-based multimedia data retrieval problems can be transformed into the near neighbor searching problem in multidimensional feature space. An efficient near neighbor searching algorithm is needed when developing a multimedia database system. In this paper, we propose an approach to efficiently solve the near neighbor searching problem. In this approach, along each dimension an index is constructed according to the values of feature points of multimedia objects. A user can pose a content-based query by specifying a multimedia query example and a similarity measure. The specified query example will be transformed into a query point in the multi-dimensional feature space. The possible result points in each dimension are then retrieved by searching the value of the query point in the corresponding dimension. The sets of the possible result points are merged one by one by removing the points which are not within the query radius. The resultant points and their distances from the query point form the answer of the query. To show the efficiency of our approach, a series of experiments are performed to compare with the related approaches.