高阶统计量方法在谐波恢复中的应用

谐波恢复是信号处理中的重要问题,谐波恢复就是在噪声中分析组成信号的各次谐波.噪声分为加性噪声和乘性噪声,本文分析加性噪声和乘性噪声的特点,提出采用高阶统计量的方法抑制噪声,恢复谐波.通过四阶统计量的切片抑制乘性噪声,采用二阶累积量谱抑制加性噪声.仿真结果表明,本方法具有很好的抑制噪声效果.     

在线手写签名认证研究

手写签名认证是人工智能领域的一个重要课题,对它的深入研究具有重要的现实意义。文章采用基于概率统计的方法表示手写签名的速度特征,用vague集相似度表示书写压力特征,并通过细分的拐点表示笔画特征进行签名认证,最后,构造了一个在线手写签名认证系统。实验证明了该方法的有效性。     

中国图像工程：2009

该文是关于中国图像工程的年度文献综述系列之十五。为了使国内广大从事图像工程研究和图像技术应用的科技人员能够较全面地了解国内图像工程研究和发展的现状,并能够方便地查询有关文献,现从2009年在国内15种有关图像工程重要中文期刊的共134期上发表的3604篇学术研究和技术应用文献中,选取出1008篇属于图像工程领域的文献,并根据各文献的主要内容将其分别归入图像处理,图像分析,图像理解,技术应用和综述五个大类,然后进一步分入23个专业小类（与去年相同）。在此基础上还进行了各期刊各类文献的统计和分析。根据统计分析结果可看到我国图像工程在2009年许多新进展的情况。特别值得指出,在上述15种期刊上所发表的图像工程文献数量在2009年继续增加并达到历史最高,显示了图像工程在中国继续蓬勃发展的趋势。另外,借此综述系列15年之际,还将这15年分成3个5年的阶段,分别对3个阶段的图像工程文献选取情况和各类图像工程文献数量进行了统计和对比分析,以为读者提供更全面和可信的发展动态信息。     

Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface

In order to characterize the non-Gaussian information contained within the EEG signals, a new feature extraction method based on bispectrum is proposed and applied to the classification of right and left motor imagery for developing EEG-based brain-computer interface systems. The experimental results on the Graz BCI data set have shown that based on the proposed features, a LDA classifier, SVM classifier and NN classifier outperform the winner of the BCI 2003 competition on the same data set in terms of either the mutual information, the competition criterion, or misclassification rate.     

Using space windowing for a preliminary analysis of complex time data in human component system studies. Examples with eye-tracking in advertising and car/head movements in driving

Empirical studies of human systems often involve recording multidimensional signals because the system components may require physical measurements (e.g., temperature, pressure, body movements and/or movements in the environment) and physiological measurements (e.g., electromyography or electrocardiography). Analysis of such data becomes complex if both the multifactor aspect and the multivariate aspect are retained. Three examples are used to illustrate the role of fuzzy space windowing and the large number of data analysis paths. The first example is a classic simulated data set found in the literature, which we use to compare several data analysis paths generated with principal component analysis and multiple correspondence analysis with crisp and fuzzy windowing. The second example involves eye-tracking data based on advertising, with a focus on the case of one category variable, but with the possibility of several space windowing models and time entities. The third example concerns car and head movement data from a driving vigilance study, with a focus on the case involving several quantitative variables. The notions of analysis path multiplicity and information are discussed both from a general perspective and in terms of our two real examples.     

An extension of likelihood-ratio-test for testing linear hypotheses in the baseline-category logit model

A new family of test statistics for testing linear hypotheses in baseline-category logit models is introduced and its asymptotic distribution is obtained. The new family is a natural extension of the classical likelihood ratio test. A simulation study is carried out to find new test statistics that offer an attractive alternative to the classical likelihood ratio test in terms of both exact size and exact power.     

基于顺序统计滤波的实时语音端点检测算法

针对嵌入式语音识别系统,提出了一种高效的实时语音端点检测算法. 算法以子带频谱熵为语音/噪声的区分特征, 首先将每帧语音的频谱划分成若干个子带, 计算出每个子带的频谱熵, 然后把相继若干帧的子带频谱熵经过一组顺序统计滤波器获得每帧的频谱熵, 根据频谱熵的值对输入的语音进行分类. 实验结果表明, 该算法能够有效地区分语音和噪声, 可以显著地提高语音识别系统的性能. 在不同的噪声环境和信噪比条件下具有鲁棒性. 此外, 本文提出的算法计算代价小, 简单易实现, 适合实时嵌入式语音识别系统的应用.     

基于统计模型的书法创作模拟

人们对抽象思维与形象思维的认识极不平衡,对形象思维过程的研究尚属阙如.书法创作是典型的形象思维过程.文中给出基于带参数的统计模型(X=M(b))的书法笔划变形方法,通过调节参数可生成新风格的笔划.其过程包括从笔划轮廓获得训练点集、利用广义Procrustes分析法对齐、由主成分分析法得到特征等,并以隶书中典型的"一"划为例,讨论模拟创作结果.要实现人工智能,形象思维的模拟、模式和模型是逐步要考虑的问题.目前的工作只是第一步.     

Nonparametric Bayesian Image Segmentation

Image segmentation algorithms partition the set of pixels of an image into a specific number of different, spatially homogeneous groups. We propose a nonparametric Bayesian model for histogram clustering which automatically determines the number of segments when spatial smoothness constraints on the class assignments are enforced by a Markov Random Field. A Dirichlet process prior controls the level of resolution which corresponds to the number of clusters in data with a unique cluster structure. The resulting posterior is efficiently sampled by a variant of a conjugate-case sampling algorithm for Dirichlet process mixture models. Experimental results are provided for real-world gray value images, synthetic aperture radar images and magnetic resonance imaging data.     

一维统计量的椭圆检测法

数字影像中目标的识别是十分关键的,该文以椭圆作为研究对象,在对于基于二维随机变量的以HU不变矩为代表的不变矩算法上,提出了基于动差方法建立一维的随机统计量,并且证明该随机变量的三级动差和四级动差均为一常量。由于本算法只使用一维随机变量且该统计量又很容易获得,成为了其突现的优越性。