基于深度特征的快速人脸图像检索方法

针对计算机视觉领域的人脸图像检索问题,提出了一种基于深度特征的快速人脸图像检索方法。该方法首先使用人脸图像训练集对深度卷积神经网络模型进行人脸分类训练;在此基础上采用三元组损失方法对已训练好的人脸分类网络模型进行微调,使得网络能够更加有效地提取人脸特征构建高效的特征向量进行人脸检索初步过滤;最后,为了进一步提高系统检索性能,提出一阶段查询扩展方法对待检索人脸图像特征向量进行融合加强。在两个公用人脸数据集(CASIA-3DFaceV1和Labeled Faces in the Wild dataset)上进行详尽的实验验证,结果表明,基于深度特征的人脸图像检索方法不仅能够显著提高检索结果的准确率,而且该方法简单可靠,能够快速地实现人脸检索任务。     

基于RFID技术的计算机身份认证系统设计

随着信息时代的发展,计算机得到了广泛应用,计算机中的信息安全成为一个极为重要的问题;针对计算机的性息泄漏问题,设计了基于RFID技术的计算机身份认证系统;系统由USB-Lock和无线Key两个硬件设备和软件组成,当无线Key处在USB-Lock的感应区域时,双方保持通信,计算机处于可用状态;当无线Key超出USB-Lock的感应区域时,双方通信中断,计算机进入不可用状态,当用户回到计算机附近时,双方通信得到恢复实现计算机信息保护。     

基于深度学习的多模光纤通信系统的模式与模群识别

基于模式/模群复用的多模光纤通信系统是目前光通信领域的研究热点.系统中存在多个模式/模群,如何准确识别它们是提升传输系统性能的关键问题之一.提出了一种基于深度学习的多模光纤模式与模群的智能识别模型,通过引入全卷积神经网络(CNN),对噪声影响情况下线偏振模式及其模群进行仿真和实验研究.首先,基于多平面光转换模式复用器件...     

基于DPCA与LSSVM的飞机发动机异常状态识别

针对飞机发动机异常状态识别精度差、效率低和易误诊漏诊等问题,提出了一种基于动态主元分析 (Dynamic Principal Component Analysis, DPCA)和最小二乘支持向量机(Least Square Support Vector Machine, LSSVM)的飞机发动机润滑系统异常状态识别方法。首先对发动机润滑系统参数进行DPCA处理以及在线检测是否有故障发生,如果有故障发生,再采用LSSVM方法进行异常状态识别。以某型飞机发动机润滑系统为例,对文中所提方法的准确性进行试验验证,由试验结果得出文中方法能有效提高飞机发动机异常状态识别准确率。     

基于物联网和PCA支持向量机的交通流量预测系统

为了解决已有交通流量监测系统存在的数据采集分散、车辆识别度低、实时性差和流量预测误差大等问题,设计了一种基于物联网技术和最小二乘支持向量机(Least Squares Support Vector Machine, LSSVM)的交通流量预测系统;首先,描述了系统原理和部署模型,然后对系统的硬件即车载传感器节点和Sink节点进行了设计,同时对系统的软件流程进行了描述,通过在监控中心执行PCA主成分分析方法实现对采集数据提取独立主成分,消除无关冗余数据,在此基础上采用LSSVM实现道路交流流量预测;最后,在十字路口布置实验环境,实验结果表明:文章方法能实时精确地实现交通流量预测,与其它方法相比,具有拟合精度高和的泛化能力强的优点,具有很强的实用性。     

云计算环境下智能图书借还终端系统设计与实现

针对传统的图书借还系统只能通过条码扫描,获取信息,一直存在工作效率低、用户信任度下降的问题。提出并设计了一种基于RFID技术的智能图书借还终端系统,该系统利用RFID无线射频识别技术采集馆内图书、读者以及书架等信息,采用天线条码标签对智能图书馆内的图书进行监控,实现对图书借还信息进行终端操作,设计了系统软件,并通过实验进行了对比分析,实验表明对RFID系统的硬件和软件测试对传统条码技术的问题有了相对应的解决,从而达到提高智能图书馆借还书和借还终端系统效率的目的。     

基于深度自动编码器的机场安检人脸识别系统设计

由于现有的机场安检系统通常只针对行李和旅客携带的违禁物品进行检测,没有考虑到对于正在通缉的罪犯进行监控和核查,设计了一种基于Gabor小波滤波和深度自动编码器的机场安检人脸识别系统。首先,以ATmega128L为处理器核心,SA7111作为模数转换器,MAX7000作为全局逻辑控制单元设计了机场人脸识别系统硬件,然后采用Gabor小波函数作为卷积核函数,在对原始图像分块的基础上进行卷积,采用多个RBM堆叠组成的自动编码器,通过比较差异算法训练RBM从而自动提取人脸特征,最后构建一个三层的BP神经网络,将自动提取的人脸特征作为输入,将图像标签作为输出层,并通过反向传播算法训练网络进行人脸识别。通过部署仿真实验环境对文中方法进行验证,仿真结果表明：文中系统能较为精确地实现人脸识别,与其它方法相比,具有识别率高和收敛速度快的优点。     

基于Map-Reduce并行构架和AE的大数据指纹监控识别算法

传统的指纹识别监控方法在应用到以海量、在线和增量为特征的大数据环境中时,不能自动高效地进行识别,且识别率和识别精度都不高。由此设计了一种基于Map-Reduce并行框架和AE的大数据智能监控指纹识别算法。首先,描述了Hadoop和Map-Reduce实现并行计算的原理;然后,设计了基于AE和BP神经网络的识别模型,采用AE进行指纹图像自动特征提取,并提出了一种基于比较差异算法对AE进行参数初始化的训练算法,采用BP神经网络进行具体识别;最后,将识别过程分解为Map函数和Reduce函数,并对函数的具体功能进行了详细定义。在Map-Reduce并行框架下对FVC2004中的指纹数据库进行实验,实验结果表明了文中方法能自动、高效地进行指纹识别,与其他方法相比,具有识别效率高和识别精度高的优点,具有较大的优越性。     

基于透明介质成像的光学散射神经网络

近年来,随着神经网络的发展,多种光电神经网络框架相继提出,在图像和语音处理等方面表现出强大的应用潜力.设计一种新型的基于透明介质成像的光学散射神经网络框架.描述透明介质双向散射传播的物理特性,采用多层堆叠散射介质构建神经网络单层智能单元,并利用非线性光电材料薄膜实现非线性激活,级联单层智能单元构建深度网络物理模型;根据...     

弱光照环境下人脸表情图像识别方法研究

对弱光照环境下人脸表情图像进行识别,可以更好地对人类的情感进行分类,有利于人类在现实社会中的沟通。当前方法利用提取人脸表情图像的一维特征完成对弱光照环境下人脸表情图像的识别,该方法无法对人脸表情图像进行详细地描述,导致人脸表情图像在识别时经常出现识别精度低、速度慢的问题。为此,提出一种基于BP神经网络的弱光照环境下人脸表情图像识别方法。该方法首先利用自相似性对带有噪声的图像进行图像区域划分,并依据统计学习获得线性空间,通过对空间的投影获得不含噪声的人脸表情图像区域向量,将人脸表情图像进行重组,得到去噪后的图像,然后利用Cabor变换对人脸表情图像特征进行提取,采用AdaBoost对弱分类器以及人脸表情图像样本进行训练,并通过多次弱分类器的迭代,得到最终的人脸表情图像强分类器,完成对弱光照环境下人脸表情图像的识别。实验结果证明,所提方法可以提高人脸表情图像的识别准确率,加快识别速度,为该领域的研究发展提供强有力依据。     

Guided-Wave Two-Dimensional Acousto-Optic Scanner Using Proton-Exchanged Lithium Niobate Waveguide

Two-dimensional scanning of a 0.6328 mum guided-light beam has been realized using noncolinear acousto-optic (AO) coplanar Bragg diffraction together with colinear AO guided-mode to substrate radiation-mode conversion in a Z-cut Xpropagation LiNbO3 proton-exchanged (PE) waveguide. The two surface acoustic (SAW) waves utilized are at the center frequencies of 500 and 200 MHz, propagating in the Y and X axes, respectively. Two-dimensional scanning of approximately 720 resolvable light beam spots, namely, 18 40 (horizontal vertical) scanning, has been demonstrated using a light beam of 1.0 mm aperture. The total number of resolvable beam spots can be greatly increased from 720 by simply utilizing SAW transducers of larger bandwidth and a light beam of greater aperture. It should also be possible to significantly increase the diffraction efficiency from 3 % by optimizing the parameters of the PE waveguide and the SAWs.     

Hybrid Wavelength and Code Division Multiple Access in Optical Networks

A review of schemes for multiple access in fiber optic networks shows that a hybrid of wavelength and code division multiple access (WCDMA) combines the best features of both. In particular, the hybrid scheme retains the large information carrying capacity of wavelength division multiple access (WDMA) and flexibility of code division multiple access (CDMA). In this paper WDMA, optical CDMA (OCDMA), and WCDMA networks are discussed. In OCDMA networks, concept of incoherent and coherent coding including inverse decoding and matched filter is introduced. The delay performance of both WDMA and WCDMA networks, under the simple suboptimum access protocols based on cyclic search, is computed. It has been shown quantitatively that tuning delay significantly affects the delay performance of both WDMA and WCDMA networks. Futhermore, delay performance of WCDMA networks is always better than the WDMA networks for the same tuning delay, load, and number of users.     

Femtosecond Transform-Limited Pulse Generation by Compensating for the Linear Chirp of SPM Spectra in Dispersion Shifted Fibers

A simple technique of pulse compression, based on the linear chirp compensation of self-phase modulation (SPM) spectra in dispersion shifted fibers, is demonstrated. The optimization procedure is carried out, for a short span of a single-mode fiber, using a parabolic law, which describes the behavior of the squared output pulse width versus the pump peak power in the case of Gaussian pulses. The experimental results give a minimum pulse duration of 233 fs, which is in good agreement with the model. Shorter and coherent pulses, down to 90 fs, have been obtained by inserting an interference filter at the optical output.     

Effect ofγ-radiation on the spectral luminescence characteristics of impure cadmium tungstate crystals

Results of a study of the effect of γ-radiation on the spectral luminescence properties of cadmium tungstate crystals doped with silver, bismuth, and molybdenum cations are presented. Spectral characteristics of the nondnnnoped crystals are briefly described. Absorption and photo and X-ray luminescence spectra of the crystals taken before and after exposure to γ-radiation (5.5·10⁴ Gy) are compared. It is found that the spectral characteristics of the crystals doped with silver, bismuth, and molybdenum cations do not change markedly after the exposure. The relation between the type of impurity-induced defects, individual characteristics of the impurity cations, and the character of the effect of γ-radiation on the spectral luminescence properties of impure crystals is analyzed (preliminarily). Translated from Zhurnal Prikladnoi Spektroskopii, Vol. 64, No. 1, pp. 55–60, January–February, 1997.     

Research on beamforming method for dual-line array with space mismatch between the two line arrays

The performance of port/starboard discrimination of dual-line array will be seriously degraded when the space between the two line arrays of the dual-line array is mismatched. The directivity function of the delay-sum and delay-subtract beamforming is deduced and the port/starboard discrimination of the delay-sum and delay-subtract beamforming is also studied both under the ideal status and the status under which the space between the two line arrays of the dual-line array is mismatched. Analysis results show the delay-subtract beamforming has better performance of port/starboard discrimination. At last, the sea trial results demonstrate the theoretical results.     

Sorting of bending magnets for the SSRF booster

The Shanghai Synchrotron Radiation Facility(SSRF)booster ring,a full energy injector for the storage ring,is deigned to accelerate the electron beam energy from 150MeV to 3.5GeV that demands high extraction efficiency at the extraction energy with low beam loss rate when electrons are ramping.Closed orbit distortion(COD)caused by bending magnet field uniformity errors which affects the machine performance harmfully could be effectively reduced by bending magnet location sorting.Considering the affections of random errors in measurement,both ideal sorting and realistic sorting are studied based on measured bending magnet field uniformity errors and one reasonable combination of bending magnets which can reduce the horizontal COD by a factor of 5is given as the final installation sequence of the booster bending magnets in this paper.     

Retrieval of ultraviolet skylight radiances and O3 slant column densities from balloon-borne limb spectrometer

With a novel light-weight and absolutely calibrated ultraviolet （UV） spectrometer, UV skylight radiances and O3 slant column densities are measured by balloon-borne limb measurements in Xinjiang area, China. UV skylight radiances measured at the height of 31 km are compared with the results from Modtran in the wavelength range from 290 to 420 nm. O3 slant column densities are derived from radiance spectra in the Huggins bands （320 - 335 nm） using differential optical absorption spectroscopy method. And the parameter exhibits a good correlation with the same value simulated by radiative transfer model （Tracy）. The O3 profile simultaneously measured by an O3 sonde is used as input in Tracy calculations. The O3 sonde is launched on the same balloon.     

Design optimization of highly sensitive LSPR enhanced surface plasmon resonance biosensors with nanoholes

For breaking through the sensitivity limitation of conventional surface plasmon resonance (SPR) biosensors, novel highly sensitive SPR biosensors with Au nanoparticles and nanogratings enhancement have been proposed recently.But in practice, these structures have obvious disadvantages.In this study, a nanohole based sensitivity enhancement SPR biosensor is proposed and the influence of different structural parameters on the performance is investigated by using rigorous coupled wave analysis (RCWA).Electromagnetic field distributions around the nanohole are also given out to directly explain the performance difference for various structural parameters.The results indicate that significant sensitivity increase is associated with localized surface plasmons (LSPs) excitation mediated by nanoholes.Except to outcome the weakness of other LSP based biosensors, larger resonance angle shift, reflectance amplitude, and sharper SPR curves' width are obtained simultaneously under optimized structural parameters.     

Polymer gratings based on photopolymerization for low-order distributed feedback polymer lasers

Novel polymer distributed feedback(DFB)gratings are fabricated based on photopolymerization to reduce lasing threshold of polymer lasers.A photopolymer formulation sensitive to 355-nm ultraviolet(UV)light is proposed for the fabrication of polymer gratings and it can be used to form polymer films by spin-coating process.A very low surface-relief depth ranging from 12.5 to about 1.0 nm has been demonstrated with a refractive-index modulation of about 0.012.The experimental results indicate that such polymer gratings have promising potentials for the fabrication of low-order DFB organic semiconductor lasers.