基于头皮和表面肌电信号假手控制系统

提出了一种假手控制系统,该系统能够综合利用头皮和表面肌电信号的信息,实时地解码手部运动的速度、加速度和轨迹,从而实现对假手的灵活控制,且无需植入电极,便于维护。     

Structure and Parameter Adaptive Pattern Recognition With Supervised Learning: A New Formulation

A new formulation of the problem of structure and parameter adaptive pattern recognition with supervised learning yielding significant computational advantages is presented.     

一种应用于人脸识别的有监督NMF算法

为了提高非负矩阵分解(NMF)算法识别率,提出了一种有监督的NMF(SNMF)方法.该算法对NMF基图像进行判别分析,然后选择主要反应类内差异的基图像来构造子空间,最后在子空间上进行识别.通过UMIST人脸库和CMU PIE人脸库上的实验结果表明,该方法对光照、姿态和表情变化具有一定的鲁棒性,识别率高于NMF方法和其它子空间分析法.     

一种数字控制的可编程多功能滤波器

设计了一种并行数字控制的多功能可编程滤波器，可以用数字信号控制滤波器的时间常数，实现低通、带通、高通滤波器，该设计简单合理、可靠性好，经实践证实控制精度较高。     

基于相关性分析和支持向量机的手部肌电信号动作识别

为了有效提取表面肌电信号(SEMG)的特征,该文提出了一种基于相关性分析的改进的特征提取方法。首先用空域相关法对两路SEMG信号进行消噪预处理,然后对处理后的SEMG信号进行四尺度小波变换,并通过相关性分析提取SEMG信号的重要边缘在各尺度上的小波系数,以各尺度上的这些系数的平方和构建六维特征向量输入支持向量机分类器,对手部的多个动作进行分类。实验结果表明,基于相关性分析和小波变换构筑的特征向量结合支持向量机的方法能够以较高识别率区分伸腕、屈腕、展拳、握拳4种动作,能够得到比传统的神经网络分类器更为准确的分类结果。     

Correlation Pattern Recognition for Face Recognition

Two-dimensional (2-D) face recognition (FR) is of interest in many verification (1:1 matching) and identification (1:N matching) applications because of its nonintrusive nature and because digital cameras are becoming ubiquitous. However, the performance of 2-D FR systems can be degraded by natural factors such as expressions, illuminations, pose, and aging. Several FR algorithms have been proposed to deal with the resulting appearance variability. However, most of these methods employ features derived in the image or the space domain whereas there are benefits to working in the spatial frequency domain (i.e., the 2-D Fourier transforms of the images). These benefits include shift-invariance, graceful degradation, and closed-form solutions. We discuss the use of spatial frequency domain methods (also known as correlation filters or correlation pattern recognition) for FR and illustrate the advantages. However, correlation filters can be computationally demanding due to the need for computing 2-D Fourier transforms and may not match well for large-scale FR problems such as in the Face Recognition Grand Challenge (FRGC) phase-II experiments that require the computation of millions of similarity metrics. We will discuss a new method [called the class-dependence feature analysis (CFA)] that reduces the computational complexity of correlation pattern recognition and show the results of applying CFA to the FRGC phase-II data     

基于序列比对的多功能雷达搜索规律识别方法

对多功能雷达信号规律的识别是电子侦察领域的难点问题之一,本文将多功能雷达搜索方式下的工作规律表示为一个任务序列,提出了一种基于序列比对的识别方法.该方法引入了生物信息学领域的生物序列分析技术,通过将两次不同观测时间段的信号进行比对,提取其中的相似部分来达到识别多功能雷达搜索规律的目的.仿真结果证明了该方法的有效性.     

Real‐Time Locomotion Mode Recognition Employing Correlation Feature Analysis Using EMG Pattern

This paper presents a new locomotion mode recognition method based on a transformed correlation feature analysis using an electromyography (EMG) pattern. Each movement is recognized using six weighted subcorrelation filters, which are applied to the correlation feature analysis through the use of six time‐domain features. The proposed method has a high recognition rate because it reflects the importance of the different features according to the movements and thereby enables one to recognize real‐time EMG patterns, owing to the rapid execution of the correlation feature analysis. The experiment results show that the discriminating power of the proposed method is 85.89% when walking on a level surface, 96.47% when going up stairs, and 96.37% when going down stairs for given normal movement data. This makes its accuracy and stability better than that found for the principal component analysis and linear discriminant analysis methods.     

模式识别技术在传感器中的应用

<正> 一、引言 随着传感器的应用日益广泛,传感器的选择性与多功能化问题显得越来越重要。为了得到高灵敏、高精度的敏感器件,就要研究传感器对被测参量(物理量、化学量和生物量)的选择性,即从多个敏感参量中选择出所需的被测量;为了检测同时存在的几种参量(例如工作环境的温度与湿度,气体的成分与浓度和流体的流量、温度与压力等等),就要研究传感器的多功能化。同时,对传感器多功能化的研究,又能促进单一功能传感器性能的提高。     

一种有监督的LPP算法及其在人脸识别中的应用

为了提高局部保持投影算法(Locality Preserving Projections,LPP)对光照、姿态等外部因素的鲁棒性,该文对传统的LPP算法进行改进,提出了一种有监督的LPP(SLPP)方法。首先对LPP子空间进行判别分析,然后选择主要反应类内差异的基向量来构造子空间,最后在子空间上进行识别。通过Havard人脸库和Umist人脸库上的实验,结果表明该方法能够对光照和姿态的变化具有一定的鲁棒性和较高的识别率,比传统的LPP方法和其它子空间分析法识别率提高了10%以上。     

A Direction‐Based Vascular Pattern Extraction Algorithm for Hand Vascular Pattern Verification

This paper proposes an improved vascular pattern extraction algorithm for person verification applications. The proposed direction‐based vascular pattern extraction (DBVPE) algorithm is based on the directional information of vascular patterns. It applies two different filters to the input images: row vascular pattern extraction filter (RVPEF) for effective extraction of the abscissa vascular patterns and column vascular pattern extraction filter (CVPEF) for effective extraction of the ordinate vascular patterns. We use the combined output of both filters to obtain the final hand vascular patterns. Unlike the conventional hand vascular pattern extraction algorithm, the directional extraction approach prevents loss of the vascular pattern connectivity. To validate the DBVPE algorithm, we used a prototype system with a DSP processor. The prototype system shows approximately a three‐times better false acceptance rate (FAR) than the conventional single filter algorithm.     

基于视觉手势识别的研究—综述

手势是一种自然而直观的人际交流模式.基于视觉的手势识别是实现新一代人机交互所不可缺少的一项关键技术.然而,由于手势本身具有的多样性、多义性、以及时间和空间上的差异性等特点,加之人手是复杂变形体及视觉本身的不适定性,因此基于视觉的手势识别是一个极富挑战性的多学科交叉研究课题.本文从手势建模、手势分析和手势识别等三个方面综述了基于视觉手势识别的研究现状及其应用.     

基于监督局部线性嵌入的飞机目标识别方法

维数约简是目标识别的一个重要预处理步骤.由于飞机目标图像对各种空间变换(包括平移、尺度、旋转等变换)和观察角度、位置以及光照等因素都比较敏感,使得很多线性维数约简算法不能有效地用于飞机目标识别.局部线性嵌入(LLE)是一种有效的非线性维数约简方法,提出了一种基于LLE的监督LLE算法,并应用于多种条件下的飞机目标识别中...     

Achievable Rates for Pattern Recognition

Biological and machine pattern recognition systems face a common challenge: Given sensory data about an unknown pattern, classify the pattern by searching for the best match within a library of representations stored in memory. In many cases, the number of patterns to be discriminated and the richness of the raw data force recognition systems to internally represent memory and sensory information in a compressed format. However, these representations must preserve enough information to accommodate the variability and complexity of the environment, otherwise recognition will be unreliable. Thus, there is an intrinsic tradeoff between the amount of resources devoted to data representation and the complexity of the environment in which a recognition system may reliably operate. In this paper, we describe a mathematical model for pattern recognition systems subject to resource constraints, and show how the aforementioned resource-complexity tradeoff can be characterized in terms of three rates related to the number of bits available for representing memory and sensory data, and the number of patterns populating a given statistical environment. We prove single-letter information-theoretic bounds governing the achievable rates, and investigate in detail two illustrative cases where the pattern data is either binary or Gaussian.     

改进BP神经网络的EMG手指运动识别

在基于肌电信号(EMG)手指运动的模式识别中,稳定性和识别率是两个主要问题,为此提出了一种新的EMG模式识别算法。该算法采用现代信号处理理论中的AR模型和改进的BP神经网络相结合的算法,有效的解决了BP网络识别中落入局部极值问题。进行试验,将提取到的特征值输入MATLAB建立一个改进多层BP神经网络,识别三个不同类型的手指运动。实验表明,改进BP算法较传统BP算法获得了更高的识别精度,达到94%左右。     

一种用于模式识别的新型开关电流Hamming神经网络

本文首次提出了一种用于模式识别的新型开关电流Ｈａｍｍｉｎｇ神经网络，它采用电流镜计算待识模式与标准模式的匹配度，然后，通过开关电流型排序电路进行匹配度的比较并输出识别结果，该Ｈａｍｍｉｎｇ神经网络可以按匹配度大小的顺序依次输出匹配度以及相应的标准模式，这将十分有利于改善系统的性能同时，该Ｈａｍｍｉｎｇ网络还可以进行绝对拒识和相对拒识的判断，这大大地提高了系统的可靠性，通过ＰＳＰＩＣＥ模拟，结果表明     

EMG Pattern Analysis and Classification for a Prosthetic Arm

This paper deals with the statistical analysis and pattern classification of electromyographic signals from the biceps and triceps of a below-the-humerus amputated or paralyzed person. Such signals collected from a simulated amputee are synergistically generated to produce discrete lower arm movements. The purpose of this study is to utilize these signals to control an electrically driven prosthetic or orthotic arm with minimum extra mental effort on the part of the subject. The results show very good separability of classes of movements when a learning pattern classification scheme is used, and a superposition principle seems to hold which may provide a means of decomposition of any composite motion to the six basic primitive motions, e.g., humeral rotation in and out, elbow flexion and extension, and wrist pronation and supination. Since no synergy was detected for the hand movements, different inputs have to be provided for a grip. The method described is not limited by the location of the electrodes. For amputees with shorter stumps, synergistic signals could be obtained from the shoulder muscles. However, the presentation in this paper is limited to bicep-tricep signal classification only.     

一种基于最大似然Hausdorff距离的手势识别算法

针对字母手势的检测和跟踪问题,文章提出一种基于最大似然准则Hausdorff距离的手势识别算法。该算法首先对字母手势图像进行二值化处理,并由字母手势图像的边缘信息中提取字母手势的关键点(指根和指尖);然后采用基于最大似然准则的Hausdorff距离对手势进行识别,搜索策略采用类似于Rucklidge提出的多分辨率搜索方法,在不影响成功率和目标定位精度的情况下,可以显著地缩短搜索时间。实验结果表明此方法可以较好地识别字母手势,同时对部分变形(旋转和缩放)手势也有良好的效果。     

一种用于模式识别的电流型模糊处理器

本语文提出了一种用于模式识别的电波型模糊处理器。该处理器采用“加权求和”的函数,并且权重可以调节,以利于系统的自适应处理。另外,该处理器可以按综合录属度大小的顺序依次输出综合录属度以及相应的标准模式,这将十分有利于改善硬件系统的性能,尤其是多级联系统的性能。我们采用单支多晶的２μｍ Ｎ阱标准数字ＣＭＯＳ工艺成功地制作了模糊处理器芯片。测试结果表明,该处理器芯片的性能很好。