基于连续隐马尔可夫模型的人脸识别方法

提出了一种基于连续隐马尔可夫模型的人脸图像识别方法,主要内容包括以下方面:①由于奇异值向量具有稳定性.转置不变性等特点,对归一化的人脸图像,采用奇异值分解抽取人脸图像特征作为观察值序列;②在人脸识别中应用连续隐马尔可夫模型,采用双高斯概率密度函数训练,建立HMM模型,再利用建好的HMM模型进行识别.实验结果显示,所提出的方法减少了数据计算量,运行速度快,并提高了识别率,完全满足人脸识别系统实时性要求.     

基于视觉的动态手势识别

采用隐马尔可夫模型（Hidden Markov Model）算法的缺点，采用纠错算法对其修正，提高了识别率。了对机器人控制的目的，优化了人机交互的接口。训练并识别手势样本，针对HMM的经典训练算法Baum-Welch将识别结果应用于“基于Internet远程机器人控制”项目，达到了对机器人控制的目的，优化了人机交互的接口。     

基于Hu-GLCM的手势识别方法研究

针对手势识别过程中单一手势特征对手势描述的不足,提出了一种基于改进Hu矩和灰度共生矩阵GLCM的手势识别方法 Hu-GLCM。首先利用肤色模型对采集的图像分割出手势区域;其次采用数学形态学和多边形拟合的方法提取手势的单连通轮廓,利用改进Hu-GLCM算法提取手势的几何形状特征和纹理特征并建立模板数据库;最后通过扩展的Canberra距离对手势图像进行识别和分类。实验结果表明,该改进算法对7种手势的平均识别率达到95%以上,且计算速度快,能够满足实时性的需求。     

基于隐马尔可夫模型的运动目标轨迹识别 *

引入改进的隐马尔可夫模型算法,针对真实场景中运动目标轨迹的复杂程度对各个轨迹模式类建立相应的隐马尔可夫模型,利用训练样本训练模型得到可靠的模型参数;计算测试样本对于各个模型的最大似然概率,选取最大概率值对应的轨迹模式类作为轨迹识别的结果,对两种场景中聚类后的轨迹进行训练与识别。实验结果表明,平均识别率分别达到87.76 %和94. 19%。     

基于改进粒子群算法的隐马尔可夫模型训练

针对隐马尔可夫模型传统训练算法易收敛于局部极值的问题,提出一种带极值扰动的自适应调整惯性权重和加速系数的粒子群算法,将改进后的粒子群优化算法引入到隐马尔可夫模型的训练中,分别对隐马尔可夫模型的状态数与参数进优化.通过对手写数字识别的实验说明,提出的基于改进粒子群优化算法的隐马尔可夫模型训练算法与传统隐马尔可夫模型训练算法Baum-Welch算法相比,能有效地跳出局部极值,从而使训练后的隐马尔可夫模型具有较高的识别能力.     

A model-based hand gesture recognition system

This paper introduces a model-based hand gesture recognition system, which consists of three phases: feature extraction, training, and recognition. In the feature extraction phase, a hybrid technique combines the spatial (edge) and the temporal (motion) information of each frame to extract the feature images. Then, in the training phase, we use the principal component analysis (PCA) to characterize spatial shape variations and the hidden Markov models (HMM) to describe the temporal shape variations. A modified Hausdorff distance measurement is also applied to measure the similarity between the feature images and the pre-stored PCA models. The similarity measures are referred to as the possible observations for each frame. Finally, in recognition phase, with the pre-trained PCA models and HMM, we can generate the observation patterns from the input sequences, and then apply the Viterbi algorithm to identify the gesture. In the experiments, we prove that our method can recognize 18 different continuous gestures effectively. Received: 19 May 1999 / Accepted: 4 September 2000     

Feature fusion for 3D hand gesture recognition by learning a shared hidden space

Hand gesture recognition has been intensively applied in various human-computer interaction (HCI) systems. Different hand gesture recognition methods were developed based on particular features, e.g., gesture trajectories and acceleration signals. However, it has been noticed that the limitation of either features can lead to flaws of a HCI system. In this paper, to overcome the limitations but combine the merits of both features, we propose a novel feature fusion approach for 3D hand gesture recognition. In our approach, gesture trajectories are represented by the intersection numbers with randomly generated line segments on their 2D principal planes, acceleration signals are represented by the coefficients of discrete cosine transformation (DCT). Then, a hidden space shared by the two features is learned by using penalized maximum likelihood estimation (MLE). An iterative algorithm, composed of two steps per iteration, is derived to for this penalized MLE, in which the first step is to solve a standard least square problem and the second step is to solve a Sylvester equation. We tested our hand gesture recognition approach on different hand gesture sets. Results confirm the effectiveness of the feature fusion method.     

基于深度信息的实时手势识别和虚拟书写系统

鉴于无接触体感交互技术在人机交互领域的成功应用,提出了一种基于Kinect深度相机的实时隔空虚拟书写方法。结合颜色和深度数据检测和分割出手掌区域;进一步,通过修改的圆扫描转换算法获得手指的个数,以识别不同的手势指令;根据指尖检测从指尖的运动轨迹分割出独立的字符或汉字运动轨迹,并采用随机森林算法识别该字符或汉字。这种基于深度信息的手势检测和虚拟书写方法可以克服光照和肤色重叠的影响,可靠实时地检测和识别手势和隔空书写的文字,其识别率达到93.25%,识别速度达到25 frame/s。     

Exploring the state sequence space for hidden Markov and semi-Markov chains

The knowledge of the state sequences that explain a given observed sequence for a known hidden Markovian model is the basis of various methods that may be divided into three categories: (i) enumeration of state sequences; (ii) summary of the possible state sequences in state profiles; (iii) computation of a global measure of the state sequence uncertainty. Concerning the first category, the generalized Viterbi algorithm for computing the top L most probable state sequences and the forward-backward algorithm for sampling state sequences are derived for hidden semi-Markov chains and hidden hybrid models combining Markovian and semi-Markovian states. Concerning the second category, a new type of state (and state change) profiles is proposed. The Viterbi forward-backward algorithm for computing these state profiles is derived for hidden semi-Markov chains and hidden hybrid models combining Markovian and semi-Markovian states. Concerning the third category, an algorithm for computing the entropy of the state sequence that explains an observed sequence is proposed. The complementarity and properties of these methods for exploring the state sequence space (including the classical state profiles computed by the forward-backward algorithm) are investigated and illustrated with examples.     

隐马尔可夫模型的多序列比对研究

研究一种关于隐马尔可夫模型的多序列比对,利用值和特征序列的保守性,通过增加频率因子,改进传统隐马尔可夫模型算法的不足。实验表明,新算法不但提高了模型的稳定性,而且应用于蛋白质家族识别,平均识别率比传统隐马尔可夫算法提高了3.3个百分点。     

基于手势识别的人机交互发展研究

近年来手势识别技术的快速发展,基于手势识别技术的人机交互应用系统的建立使得人机交互的发展前景广阔.从手形、手势和手形手势的建模出发,介绍了模板匹配、特征提取、神经网络和隐马尔可夫模型4种手势识别的方法,并且综述了基于手势识别技术人机交互的发展,详细介绍了3类人机交互系统：漫游型系统、编辑型系统和操作型系统.     

A modified hidden Markov model

This paper considers two discrete time, finite state processes X$X$ and Y$Y$. In the usual hidden Markov model X$X$ modulates the values of Y$Y$. However, the values of Y$Y$ are then i.i.d. given X$X$. In this paper a new model is considered where the Markov chain X$X$ modulates the transition probabilities of the second, observed chain Y$Y$. This more realistically can represent problems arising in DNA sequencing. Algorithms for all related filters, smoothers and parameter estimations are derived. Versions of the Viterbi algorithms are obtained.     

A novel approach for dynamic hand gesture recognition using contour-based similarity images

A novel approach is proposed for the recognition of moving hand gestures based on the representation of hand motions as contour-based similarity images (CBSIs). The CBSI was constructed by calculating the similarity between hand contours in different frames. The input CBSI was then matched with CBSIs in the database to recognize the hand gesture. The proposed continuous hand gesture recognition algorithm can simultaneously divide the continuous gestures into disjointed gestures and recognize them. No restrictive assumptions were considered for the motion of the hand between the disjointed gestures. The proposed algorithm was tested using hand gestures from American Sign Language and the results showed a recognition rate of 91.3% for disjointed gestures and 90.4% for continuous gestures. The experimental results illustrate the efficiency of the algorithm for noisy videos.     

基于手势识别的工业机器人操作控制方法

针对目前操作工人与工业机器人之间的交互还是采用比较机械化的交互方式,设计使用Kinect传感器作为手势采集设备,并使用人的手势来对工业机器人进行控制的方法。首先,使用深度阈值法与手部骨骼点相结合的方法,从Kinect传感器获取的数据中准确地提取出手部图像。在提取过程中,操作员无需佩戴任何设备,对操作员所站位置没有要求,对背景环境也没要求。然后,用稀疏自编码网络与Softmax分类器结合的方法对手势图像进行识别,手势识别过程包含预训练和微调,预训练是用逐层贪婪训练法依次训练网络的每一层,微调是将整个神经网络看成一个整体微调整个网络的参数,手势识别的准确率达到99.846%。最后,在自主研发的工业机器人仿真平台上进行实验,在单手和双手手势下都取得了不错的效果,实验结果验证了手势控制工业机器人的可行性和可用性。     

Hand gesture recognition based on dynamic Bayesian network framework

In this paper, we propose a new method for recognizing hand gestures in a continuous video stream using a dynamic Bayesian network or DBN model. The proposed method of DBN-based inference is preceded by steps of skin extraction and modelling, and motion tracking. Then we develop a gesture model for one- or two-hand gestures. They are used to define a cyclic gesture network for modeling continuous gesture stream. We have also developed a DP-based real-time decoding algorithm for continuous gesture recognition. In our experiments with 10 isolated gestures, we obtained a recognition rate upwards of 99.59% with cross validation. In the case of recognizing continuous stream of gestures, it recorded 84% with the precision of 80.77% for the spotted gestures. The proposed DBN-based hand gesture model and the design of a gesture network model are believed to have a strong potential for successful applications to other related problems such as sign language recognition although it is a bit more complicated requiring analysis of hand shapes.     

用于手势识别的时空融合网络以及虚拟签名系统

由于新型冠状病毒的流行,非接触式个人签名可以在一定程度上降低感染的风险,其将在人们日常的生活中发挥重要作用。因此,提出了一种简单而有效的时空融合网络来实现基于骨架的动态手势识别,并以此为基础开发了一款虚拟签名系统。时空融合网络主要由基于注意力机制的时空融合模块构成,其核心思想是以增量的方式同步实现时空特征的提取与融合。该网络采用不同编码的时空特征作为输入,并在实际应用中采用双滑动窗口机制来进行后处理,从而确保结果更加的稳定与鲁棒。在2个基准数据集上的大量对比实验表明,该方法优于最先进的单流网络方法。另外,虚拟签名系统在一个普通的RGB相机下表现优异,不仅大大降低了交互系统的复杂性,还提供了一种更为便捷、安全的个人签名方式。     

Estimation of the fundamental matrix from uncalibrated stereo hand images for 3D hand gesture recognition

All 3D hand models employed for hand gesture recognition so far use kinematic models of the hand. We propose to use computer vision models of the hand, and recover hand gestures using 3D reconstruction techniques. In this paper, we present a new method to estimate the epipolar geometry between two uncalibrated cameras from stereo hand images. We first segmented hand images using the RCE neural network based color segmentation algorithm and extracted edge points of fingers as points of interest, then match them based on the topological features of the hand. The fundamental matrix is estimated using a combination of techniques such as input data normalization, rank-2 constraint, linear criterion, nonlinear criterion as well as M-estimator. This method has been tested with real calibrated and uncalibrated images. The experimental comparison demonstrates the effectiveness and robustness of the method.     

基于双目视觉的人手定位与手势识别系统研究

提出了一种新的人手特征点提取方法,该方法将人手的质心作为匹配点,根据双目视觉定位数学模型计算目标位置信息,同时通过图像分割获取人手轮廓,利用轮廓凸包点特征来识别不同手势.在此基础上,研究设计了一种光学人手定位与手势识别系统,该系统在实时定位空间人手三维位置的同时,能够识别出相应的手势,可将其作为虚拟手的驱动接口,实现对虚拟物体的抓取、移动和释放操作.     

双层隐马尔可夫链的突发流合成

网络流模型被广泛用于构建网络与网络服务的测试环境,其准确性直接影响各种业务的性能评估结果及在实际网络环境中的鲁棒性.随着电子商务及新型网络应用的普及,突发流现象已经成为现代互联网的主要特征之一.针对平稳网络流而设计的传统网络流模型已经难以有效地描述现代网络中突发流的时间结构性及统计属性,从而不能准确反映现代网络流的行为特征.为此,提出一种新的结构化双层隐马尔可夫模型用于模拟实际网络环境下的突发流,并设计了有效的模型参数推断算法及突发流合成方法.该模型通过结构化的2层隐马尔可夫过程描述突发流并实现仿真合成,使合成流可以重现实际突发流的时间结构性、统计特性及自相似性.实验表明,该模型可以有效合成突发流.     

基于隐马尔可夫模型的股票价格预测组合模型

提出了一种用于股票价格预测的人工神经网络(ANN),隐马尔可夫模型(HMM)和粒子群优化算法(PSO)的组合模型-APHMM模型.在APHMM模型中,ANN算法将股票的每日开盘价、最高价、最低价与收盘价转换为相互独立的量并作为HMM的输入.然后,利用PSO算法对HMM的参数初始值进行优化,并用Baum-Welch算法进行参数训练.经过训练后的HMM在历史数据中找出一组与今天股票的上述4个指标模式最相似数据,加权平均计算每个数据与它后一天的收盘价格差,则今天的股票收盘价加上这个加权平均价格差便为预测的股票收盘价.实验结果表明,APHMM模型具有良好的预测性能.