EMG-based speech recognition using hidden markov models with global control variables

It is well known that a strong relationship exists between human voices and the movement of articulatory facial muscles. In this paper, we utilize this knowledge to implement an automatic speech recognition scheme which uses solely surface electromyogram (EMG) signals. The sequence of EMG signals for each word is modelled by a hidden Markov model (HMM) framework. The main objective of the work involves building a model for state observation density when multichannel observation sequences are given. The proposed model reflects the dependencies between each of the EMG signals, which are described by introducing a global control variable. We also develop an efficient model training method, based on a maximum likelihood criterion. In a preliminary study, 60 isolated words were used as recognition variables. EMG signals were acquired from three articulatory facial muscles. The findings indicate that such a system may have the capacity to recognize speech signals with an accuracy of up to 87.07%, which is superior to the independent probabilistic model.     

基于Kinect和金字塔特征的行为识别算法

提出了一种基于Kinect和金字塔特征的行为识别算法。在算法中,Kinect不仅能够获得RGB信息,还能获得与RGB信息对应的深度信息;而金字塔特征不仅描述了人体行为的全局形状和局部细节信息,而且还描述了人体行为的空间信息。通过不同核函数的支持向量机(SVM)分类器在具有挑战性的DHA数据集的试验结果表明,金字塔特征在RGB和深度图上都能获得令人满意的性能,且当深度特征和RGB特征融合时,其性能获得了进一步的提高,识别率达到96.2%,远高于一些具有代表性的行为描述子。     

Planar shape recognition based on hidden Markov models

A new deformed shape recognition method based on hidden Markov models (HMMs), which is very resistant against transformations and non-rigid deformations, is presented. Since shape features are not referred to an absolute point, the method is also resistant to severe shape distortions. The method has been successfully tested using different databases     

基于不同隐马尔科夫模型的图像识别方法

为了更详细地研究隐马尔科夫模型在图像识别中的应用,以指纹识别为例,纵向总结了几种基于隐马尔科夫模型的指纹图像识别算法,包括一维隐马尔科夫模型、伪二维隐马尔科夫模型、二维模型及一维模型组。分别从时间复杂度、识别精确度等方面总结出这四种隐马尔科夫模型在图像识别时的优缺点,得出不同待识别图像适合使用的识别模型的结论。     

Curvature based image recognition using hidden Markov models

A new deformed shape recognition method that relies on hidden Markov models to evaluate the sequentiality of the relevant points of the shape is proposed. These points are extracted from its adaptively calculated curvature function to give stability against noise transformations and deformations. The proposed method is very fast. Comparative tests for different shapes have been successful.     

基于HMM的信源—信道迭代联合译码

提出一种在接收端利用Turbo译码软输出,结合HMM（隐马尔可夫模型）中的Baum-Welch重估算法获取信源模型参数并进行信源-信道迭代联合译码的算法.通过含噪接收序列信道译码后的软输出对信源模型参数进行估计,并将迭代估计获得的信源精确概率结构和信道译码结合进行信源-信道联合迭代译码.同时从信息论角度提出用鉴别信息来度量估计获得的信源模型参数的精度,以及确定迭代估计终止的条件.     

基于多时空特征的人体动作识别算法

针对基于单时空特征的人体动作识算法的不足,提 出了一种基于多时空特征的人体动 作识别算法。通过在KTH与YouTube action公共动作数据集上的实验表明,本文提出的多时空特征的动作识别算法在较小码书的 情况下,具有 较好的区分性、鲁棒性以及实时性,且比一些且具有代表性的算法性能更好。     

Human gait recognition based on Haralick features

This paper proposes a supervised feature extraction approach that is capable of selecting distinctive features for the recognition of human gait under clothing and carrying conditions, thus improving the recognition performances. The principle of the suggested approach is based on the Haralick features extracted from gait energy image (GEI). These features are extracted locally by dividing vertically or horizontally the GEI locally into two or three equal regions of interest, respectively. RELIEF feature selection algorithm is then employed on the extracted features in order to select only the most relevant features with a minimum redundancy. The proposed method is evaluated on CASIA gait database (Dataset B) under variations of clothing and carrying conditions for different viewing angles, and the experimental results using k-NN classifier have yielded attractive results of up to 80% in terms of highest identification rate at rank-1 when compared to existing and similar state-of-the-art methods.     

基于三维虚拟警戒空间的异常入侵行为自动识别

针对目前视频异常入侵行为识别的不足,提 出了基于三维虚拟警戒空间的异常入侵行 为自动识别方法。基于人头检测与跟踪方法,根据视频监控场景中单一行人目标信息,建立 行人三维平面方程, 构建视频监控场景三维立体虚拟警戒空间,从而将行人是否进入二维场景警戒区域,转化为 行人是否闯入三维 立体虚拟空间,并基于行人头部投影射线的滑动滤波统计,实现行人是否入侵敏感保护区域 的有效识别。所提 方法不受设定警戒区域的规则形状限制,也无需对场景内容事先学习。对不同视频场景 的实验验证及同类方法的定量对比结果表明, 所提方法有效、 可行。     

基于动作标准序列的3D视频人体动作识别

基于3D视频的人体动作识别近年来受到越来越广泛的关注。基于动态时间规整的算法考虑了动作的时序信息,并能较好地解决人体运动在时间上的不确定性,但是随着训练样本增加,效率会变得较低。本文提出了一种基于动作标准序列的动作识别方法。通过特征提取将3D动作视频样本构建为动作序列,在动态时间规整度量下将动作标准序列学习建模成一个序列平均的优化问题,并使用动态时间规整重心平均算法(DBA)求解。对于动作类别类中存在显著差异的场景,研究了多重动作标准序列学习,并针对无监督学习的情况,提出了DBA-K-means聚类算法。实验结果表明,该方法可进一步提高动作识别的效率和准确率。     

基于小波域多状态隐马尔科夫树模型多尺度文本图像分割

该文基于小波域多状态隐马尔科夫树（HMT）模型，引入一种新的文本分割方法。该分割方法是在H.Choi et al.(2001)工作的基础上，将文本按纹理分为背景、文字与图片3种类型，分别建立多状态HMT模型。另外，基于平滑图像将上述方法又作了进一步的改进，引入了多状态IHMT分割方法，最后通过实例阐明了方法的有效性。     

结合小波域马尔可夫树模型的压缩采样图像重建

已有的研究表明基于模型的压缩采样信号重建可以取得更好的重建效果。本文提出一种结合小波域马尔可夫树模型的压缩采样图像重建方法。马尔可夫树模型很好的匹配了图像小波变换后的系数在尺度间的持续性。这种统计特性可以在正交匹配追踪算法中协助原子的选取,从而更准确的选取具有大幅值系数的原子。在本文提出的新算法中,每次迭代新增的原子是从与残差信号较匹配的候选原子中选取。候选原子中使模型的状态似然函数最大的原子被选出。实验结果表明,新算法可以更准确选出具有大系数原子,重建的图像质量好于其它传统方法。     

Human skeleton representation for 3D action recognition based on complex network coding and LSTM

3D skeleton sequences contain more effective and discriminative information than RGB video and are more suitable for human action recognition. Accurate extraction of human skeleton information is the key to the high accuracy of action recognition. Considering the correlation between joint points, in this work, we first propose a skeleton feature extraction method based on complex network. The relationship between human skeleton points in each frame is coded as a network. The changes of action over time are described by a time series network composed of skeleton points. Network topology attributes are used as feature vectors, complex network coding and LSTM are combined to recognize human actions. The method was verified on the NTU RGB + D60, MSR Action3D and UTKinect-Action3D dataset, and have achieved good performance, respectively. It shows that the method of extracting skeleton features based on complex network can properly identify different actions. This method that considers the temporal information and the relationship between skeletons at the same time plays an important role in the accurate recognition of human actions.     

基于加速度传感器和神经网络的人体活动行为识别

人体活动行为识别在医疗、安全、娱乐等方面有着广泛的应用,为了高效、准确地获取人体活动的行为信息,提出一种基于加速度传感器和神经网络的个人活动行为识别方法。该方法通过在个人手上佩戴加速度传感器,实时采集个人活动的行为数据;再通过BP神经网络分析相关行为数据并建立个人活动行为模型,分类识别个人的行走、坐着、躺卧、站立和突然跌倒等活动行为特征。实验结果表明,该方法能够有效检测到个人活动的行为特征参数,并可准确识别出人体活动的五种典型行为。     

基于循环神经网络的人体异常行为识别模型

传统识别模型在进行人体异常行为识别时,无法准确地定位到识别目标的IP地址与目标源.针对此问题,设计了一种基于循环神经网络的人体异常行为识别模型.根据人体异常行为在循环神经网络中的传播方式,计算人体规律性异常行为、重复性异常行为在网络中占用的流量,并通过Lex.net技术提取网络规则,对比人体行为执行规则与循环神经网络规则,描述人体异常行为网络执行规则;同时,引进CNN标记方式,对异常信息进行标记,引入卷积神经网络标记异常信息,将标记结果按照高语义特征与低语义特征,以此实现对行为的有效识别.实验证明,本文设计的识别模型,可以在有限时间内输出所有人体异常行为,并能在完成对异常行为的识别后,追踪到行为对应的目标个体.     

基于RealSense的三维物体识别算法研究

分析比较了Intel推出的RealSense摄像头,与热门的Kinect摄像头之间的异同。针对RealSense没有全平台点云库支持的问题,给出基于Librealsense的数据获取转换流程。针对三维物体识别算法实时性较差的问题,根据目标物体颜色空间的特性,提出了改进的快速点特征直方图描述符算法。新算法利用目标物体的HSV颜色空间特征,提升了描述符间匹配的准确率,同时利用物体色调位图降低了场景描述符计算量。除此以外,利用综合滤波的方式,显著地提升了图像的有效信息量。     

基于自适应3DLBP特征的人脸深度图像识别

针对人脸深度图像的分类识别问题展开研究,提出一种自适应3DLBP(3D Local Binary Pattern,3DLBP)特征提取算法.该特征提取算法以机器学习理论为基础,首次将反馈学习理论与3DLBP特征提取过程相结合,以保证特征提取算法对训练样本集的变化具有理想的普适性;同时,为了提高自适应特征提取算法的稳定性,提出使用多分类器对反馈学习过程进行优化.实验结果表明,自适应3DLBP特征对训练样本集的变化具有较好的有效性和稳定性,在FRGCv2.0人脸数据库上取得了理想的识别效果.     

一种采用高斯隐马尔可夫随机场模型的遥感图像分类算法

该文研究了无监督遥感图像分类问题。文中构造了图像的隐马尔可夫随机场模型(HiddenMarkov Random Fleid,HMRF),并且提出了基于该模型的图像分类算法。该文采用有限高斯混合模型(Finite Gaussian Mixture,FGM)描述图像像素灰度的条件概率分布,使用EM(Expectation-Maximization)算法解决从不完整数据中估计概率模型参数问题。针对遥感图像分布的不均匀特性,该文提出的算法没有采用固定的马尔可夫随机场模型参数,而是在递归分类算法中分级地调整模型参数以适应区域的变化。实验结果表明了该文算法的有效性,分类算法处理精度高于C-Means聚类算法.。     

Multi-pose 3D face recognition based on 2D sparse representation

The increasing availability of 3D facial data offers the potential to overcome the difficulties inherent with 2D face recognition, including the sensitivity to illumination conditions and head pose variations. In spite of their rapid development, many 3D face recognition algorithms in the literature still suffer from the intrinsic complexity in representing and processing 3D facial data. In this paper, we propose the intrinsic 3D facial sparse representation (I3DFSR) algorithm for multi-pose 3D face recognition. In this algorithm, each 3D facial surface is first mapped homeomorphically onto a 2D lattice, where the value at each site is the depth of the corresponding vertex on the 3D surface. Each 2D lattice is then interpolated and converted into a 2D facial attribute image. Next, the sparse representation is applied to those attribute images. Finally, the identity of each query face can be obtained by using the corresponding sparse coefficients. The innovation of our approach lies in the strategy of converting irregular 3D facial surfaces into regular 2D attribute images such that 3D face recognition problem can be solved by using the sparse representation of those attribute images. We compare the proposed algorithm to three widely used 3D face recognition algorithms in the GavabDB database, to six state-of-the-art algorithms in the FRGC2.0 database, and to three baseline algorithms in the NPU3D database. Our results show that the proposed I3DFSR algorithm can substantially improve the accuracy and efficiency of multi-pose 3D face recognition.