神经网络技术在激光脉冲解码领域的应用研究

为提高激光脉冲解码过程的准确性和识别效率,采用神经网络技术对激光脉冲编码解码进行了仿真研究.应用线性神经网络对有规律的编码,如周期型编码和等差型编码,进行了识别.仿真结果表明,对于PCM码,需要约2个周期的脉冲就可准确预测下一个脉冲到达的时间;对于等差型码,需要4个脉冲就可以达到精度要求.然后,应用概率神经网络对伪随机型编码的最小周期进行了识别.仿真结果表明,可以在信息量较少的情况下准确识别此类型编码的最小周期.     

一种新的相位编码幅值调节联合变换相关器

给出了一种对经典联合变换相关器进行相位编码和幅值调节的新方法,使联合变换相关器具有优化的相关输出信号和很强的抗干扰能力.在相位编码幅值调节联合变换相关器中,输入的待识别信号首先通过相位模板进行相位编码,然后对联合功率谱进行幅值调节滤波.在进行幅值调节滤波时采用了增强型幅值调节滤波器,其调节因子可根据输信号的噪音干扰情况进行调节变化.相位编码幅值调节有效地祛除了多目标识别联合变换相关器的冗余信号,可广泛的应用于多目标识别.     

一种激光制导信号分选识别算法的研究

为了对制导武器实现有效的干扰, 必须进行码型的识别及预测。针对现有可查的激光制导武器, 通过对其编码技术的分析, 深入讨论了激光脉冲信号的分选技术和码型识别技术, 结合雷达信号的重频分选算法(PRI算法), 提出了一种新的制导脉冲分选识别算法, 该算法融合了脉冲的分选及编码的识别流程, 并通过Matlab进行了仿真验证, 达到了预期解码识别的目的。基于FPGA, 在硬件上对该干扰流程进行了实现, 提供了简单的可行性方案。     

基于复杂性度量与多尺度运动编码的图像动作识别算法

人体动作的识别与理解是人机交互、机器人应用的关键技术之一,为了提高人体各种复杂动作的识别精度与鲁棒性,研究了基于复杂性度量与多尺度运动编码的动作识别技术。通过不同长度的滑动窗口对视频序列获取子序列;通过时间序列复杂性来度量人体运动轨迹,设计了一种多尺度的滑动窗口,从而选择出有效子序列;基于有效子序列,引入k-均值聚类分析算法,对人体运动进行编码,获取运动编码直方图;引入条件随机场对动作分类学习,完成动作识别与理解。所提出的算法在人机交互、智能家居、视频监控等领域具有较好的参考价值。     

用于多阶光盘游长检测的PRML系统

对用于多阶光盘游长检测的部分响应最大似然（PRML）检测器的设计和实现进行了详细研究。分析了多阶光盘的编码形式,并将编码进行简化以减小维特比检测器的路径数和运算复杂度。为了提高PR均衡器和维特比检测器的性能,分析了目标PR多项式系数和记忆长度的选择。阐述了多阶光盘游长识别的维特比算法,对算法进行仿真,分析了维特比算法的识别效果,并与与传统识别算法的效果进行了比较。     

声表面波无源应答器原理及其应用

本文讨论了声表面波无源应答器(亦称s识别卡或无线标鉴)实现相位编码调制和幅度编码调制应答的原理及技术,并对由此应答器而引出的声表面波电子识别系统的性能及用途进行了介绍。     

基于多分类支持向量机的船舶桨叶数识别研究

分析了目前常用的支持向量机多分类方法以及存在的不足,本文提出了一种混合纠错输出编码的多分类支持向量机改进算法,并应用于利用船舶目标辐射噪声DEMON谱进行船舶桨叶数分类的实验。理论分析与实验结果表明,该改进算法编码明确、具备纠错能力,是一种有效的多分类支持向量机方法,在船舶桨叶数识别中,其分类性能优于一对余、一对一及最小输出编码支持向量机等多分类方法,可适用于船舶桨叶数的分类识别。     

基于Transformer的普通话语声识别模型位置编码选择

具有自注意机制的Transformer网络在语声识别研究领域渐渐得到广泛关注.该文围绕着将位置信息嵌入与语声特征相结合的方向,研究更加适合普通话语声识别模型的位置编码方法.实验结果得出,采用卷积编码的输入表示代替正弦位置编码,可以更好地融合语声特征上下文联系和相对位置信息,获得较好的识别效果.训练的语声识别系统是在Tr...     

多尺度膨胀卷积神经网络资源三号卫星影像云识别

为提高影像云识别精度,提出一种多尺度膨胀卷积深层神经网络云识别方法。结合卫星影像特征,设计云识别卷积神经网络结构,该结构包含深层特征编码模块、局部多尺度膨胀感知模块以及云区预测解码模块。首先,编码模块中通过基础卷积层获取深度特征;其次,联合多尺度膨胀卷积和池化层共同感知,每层操作连接非线性函数,以提升网络模型的表达能力;最后,云区预测解码模块中融合对应编码模块的特征,再利用L1正则化上采样算法实现端对端的像素级云识别结果。选用典型云遮挡区域影像进行云识别实验,并与Otsu算法和FCN-8S算法进行对比。结果表明,本文所提算法的检测精度较高,Kappa系数显著提升。     

一种基于局部信息统计的虹膜分块编码方法

由于虹膜自身的稳定性、非侵犯性、不可更改性等优点,虹膜识别已经成为生物特征身份鉴别领域中的研究热点。但虹膜丰富的纹理和复杂的结构给特征提取和编码带来了很大困难。为尽可能地简化特征提取和编码方法,提高虹膜识别效率,提出了一种基于局部信息统计的虹膜分块编码方法。对原始人眼图像进行虹膜定位等预处理操作,得到归一化的虹膜纹理图像;分别根据虹膜局部信息与全局信息、局部信息与局部信息之间的比较关系进行分块编码;计算了不同虹膜代码之间的汉明(Hamming)距离。根据汉明距离给出识别结果。实验证明该方法有效、可行,具有较高的识别率和识别速度。     

Word and Face Recognition Processing Based on Response Times and Ex-Gaussian Components

The face is a fundamental feature of our identity. In humans, the existence of specialized processing modules for faces is now widely accepted. However, identifying the processes involved for proper names is more problematic. The aim of the present study is to examine which of the two treatments is produced earlier and whether the social abilities are influent. We selected 100 university students divided into two groups: Spanish and USA students. They had to recognize famous faces or names by using a masked priming task. An analysis of variance about the reaction times (RT) was used to determine whether significant differences could be observed in word or face recognition and between the Spanish or USA group. Additionally, and to examine the role of outliers, the Gaussian distribution has been modified exponentially. Famous faces were recognized faster than names, and differences were observed between Spanish and North American participants, but not for unknown distracting faces. The current results suggest that response times to face processing might be faster than name recognition, which supports the idea of differences in processing nature.     

Template matching of mixed quantum states

We consider the problem of optimal classification of an unknown input mixed quantum state with respect to a set of predefined patterns C_i, each represented by a known mixed quantum template . The performance of the matching strategy is addressed within a Bayesian formulation where the cost function, as suggested by the theory of monotone distances between quantum states, is chosen to be the fidelity or the relative entropy between the input and the templates. We investigate various examples of quantum template matching for the case of a finite number of copies of a two-level input state and for a generic, group covariant, set of two-level template states.     

发光型主体分子胍基芘识别二羧酸根阴离子

在质子性溶剂甲醇中，发光型主体分子胍基芘通过氢键与二羧酸根阴离子结合，自组装形成2：1的主客体超分子复合物，本文采用前表面反射荧光检测，通过跟踪主体分子结合客体前后芘的激基二聚体与单体荧光强度比值的变化，研究了胍基芘对不同酸根数目，不同取代位置的苯取代羧酸盐，磺酸盐，长链二羧酸盐以及双羧基氨基酸的识别能力和识别选择性，结果表明，胍基芘对二羧酸根阴离子的识别能力与客体分子中两个羧基间的距离，分子的平面构型以及取代基的种类密切相关，1，2，4，5－苯四甲酸根的识别效果远远好于其他二羧酸根阴离子。     

道地山药红外指纹图谱和聚类分析的鉴别研究

运用模式识别技术的SIMCA法对不同产地的45种山药样品进行了道地性与非道地性的模式识别方法学研究。凭借红外光谱具有的指纹特性,构建山药样品的红外指纹图谱,作为模式识别提取的特征数据,以随机分取的22个样品为训练集,剩余23个样品为试验集,该方法的正确识别率为70％,取得了满意的分类效果。     

一种改进的DNN-HMM的语音识别方法*

针对深度神经网络与隐马尔可夫模型(DNN-HMM)结合的声学模型在语音识别过程中建模能力有限等问题,提出了一种改进的DNN-HMM模型语音识别算法。首先根据深度置信网络(DBN)结合深度玻尔兹曼机(DBM),建立深度神经网络声学模型,然后提取梅尔频率倒谱系数(MFCC)和对数域的Mel滤波器组系数(Fbank)作为声学特征参数,通过TIMIT语音数据集进行实验。实验结果表明:结合了DBM的DNN-HMM模型相比DNN-HMM模型更具优势,其中,使用MFCC声学特征在词错误率与句错误率方面分别下降了1.26%和0.20%。此外,使用默认滤波器组的Fbank特征在词错误率与句错误率方面分别下降了0.48%和0.82%,并且适量增加滤波器组可以降低错误率。总之,研究取得句错误率与词错误率分别降低到21.06%和3.12%的好成绩。     

Iris segmentation for visible wavelength and near infrared eye images

State-of-the-art iris segmentation algorithms exhibit poor performance for non-ideal data, which is mainly because of the noise such as low contrast, non-uniform illumination, reflections, and among others. To address this issue, a robust iris segmentation scheme is proposed that includes the following: First, a set of the Seed-pixels in a preprocessed eye image is marked adaptively. Next, a two-fold scheme based on a Circu-differential accumulator (CDA) and gray statistics is adopted to localize coarse iris region robustly. Notably, the proposed CDA has close resemblance with the Hough transform; however, it consumes relatively less memory and is free from thresholding as well. Similarly, pupillary boundary is localized, which is verified through an intensity test as well. Next, a refine estimate for the limbic boundary is extracted. After that, iris boundaries are regularized using the Fourier series. Finally, the eyelids are localized using a Para-differential accumulator (PDA), and eyelashes and reflections are also localized adaptively in the polar form of iris. Experimental results on the near infrared (NIR) and visible wavelength (VW) iris databases show that the proposed technique outperforms contemporary approaches.     

基于血液中微量元素LM-BP神经网络模式识别冠心病患者方法

选择微量元素Sr,Cu,Mg和Zn在血液中的含量作为判别冠心病患者的指标,建立了Levenberg Marquardt Backpropagation神经网络识别模式。网络的第一层传输函数为Tansig函数,第二层传输函数为线性的Purelin函数,输入有4个向量,隐含层有8个神经元,输出层有1个神经元。选择4个样本(测试元素含量在训练元素范围内)作为测试集,余下22个样本为训练集。给出了神经网络的权重(Weight)和偏置(Bias)值,对给定的数据能完全识别,预示着可通过血液中的微量元素,可能作为冠心病患者诊断的一种辅助手段。     

Quaternion-based improved LPP method for color face recognition

In recent years, pattern recognition and computer vision have increasingly become the focus of research. Locality preserving projection (LPP) is a very important learning method in these two fields and has been widely used. Using LPP to perform face recognition, we usually can get a high accuracy. However, the face recognition application of LPP suffers from a number of problems and the small sample size is the most famous one. Moreover, though the face image is usually a color image, LPP cannot sufficiently exploit the color and we should first convert the color image into the gray image and then apply LPP to it. Transforming the color image into the gray image will cause a serious loss of image information. In this paper, we first use the quaternion to represent the color pixel. As a result, an original training or test sample can be denoted as a quaternion vector. Then we apply LPP to the quaternion vectors to perform feature extraction for the original training and test samples. The devised quaternion-based improved LPP method is presented in detail. Experimental results show that our method can get a higher classification accuracy than other methods.     

Integrating the original face images and “symmetrical faces” to perform face recognition

Using the original and ‘symmetrical face’ training samples to perform representation based face recognition was first proposed in [1]. It simultaneously used the original and ‘symmetrical face’ training samples to perform a two-step classification and achieved an outstanding classification result. However, in [1] the “symmetrical face” is devised only for one method. In this paper, we do some improvements on the basis of [1] and combine this “symmetrical faces” transformation with several representation based methods. We exploit all original training samples, left “symmetrical face” training samples and right “symmetrical face” training samples for classification and use the score fusion for ultimate face recognition. The symmetry of the face is first used to generate new samples, which is different from original face image but can really reflect some possible appearance of the face. It effectively overcomes the problem of non-sufficient training samples. The experimental results show that the proposed scheme can be used to improve a number of traditional representation based methods including those that are not presented in the paper.     

A novel method for recognizing face with partial occlusion via sparse representation

In this paper, we propose a novel method to recognize the partially occluded face images based on sparse representation. Generally, occlusions, such as glasses and scarf, fall on some random patch of image's pixels of test images, but which is known to be connected. In our method, all images are divided into several blocks and then an indicator based on linear regression technique is presented to determine whether a block is occluded. We utilize those uncontaminated blocks as the new feature of an image. Finally, the sparse representation-based classification (SRC) method serves as the classifier to recognize unknown faces. In the original work of SRC, the extended SRC (eSRC) scheme is presented to deal with occlusions, which has very heavy computational cost. The experimental results show that our method can achieve good recognition accuracy and has much lower computational cost than eSRC.