基于低秩特征脸与协同表示的人脸识别算法

在人脸识别中,人脸图像往往受到表情、光照、遮挡、姿态变化的影响,对此本文提出一种基于低秩特征脸与协同表示的人脸识别算法。该算法先用低秩矩阵恢复算法分解出训练样本图像的误差图像,再分别对训练样本与误差图像提取特征构造特征字典,计算测试样本图像特征字典下的协同表示系数,最后通过重构误差进行分类。通过AR和ORL人脸库进行实验,结果表明,本文提出的人脸识别算法的识别率、识别速率得到有效提高。     

基于Gabor特征的稀疏表示纹理分割研究

稀疏表示和字典学习在图像去噪、图像重建和模式识别等应用上取得了良好的效果,其利用稀疏系数和重构误差来作为模式分类的判别准则。稀疏表示纹理分割方法是将图像分割问题转换为像素点的分类问题。但通常稀疏表示分类方法是基于图像块特征,难以准确表征图像纹理信息。为了解决上述问题,提出基于Gabor特征的稀疏表示纹理分割方法。因为Gabor特征对图像纹理信息的鲁棒性,算法首先从每类纹理中选择一些像素点作为训练样本,计算其不同尺度和方向下的Gabor特征,将其作为初始化字典,通过判别性的字典学习算法(D-KSVD)更新字典,该字典学习算法在KSVD基础上使得字典更具有类别判别能力,最后以待分割图像的每个像素点作为测试样本,计算其Gabor特征。利用OMP算法得到测试样本在字典下的稀疏系数,根据稀疏系数得到类标签,进而对像素点进行分类,完成分割。通过在Brodatz纹理库上的实验结果表明,该方法有效提高了稀疏表示算法对纹理图像分割的正确率。     

基于低秩子空间恢复的联合稀疏表示人脸识别算法

 针对阴影、反光及遮挡等原因破坏图像低秩结构这一问题,提出基于低秩子空间恢复的联合稀疏表示识别算法.首先将每个个体的所有训练样本图像看作矩阵 D ,将矩阵 D 分解为低秩矩阵 A 和稀疏误差矩阵 E ,其中 A 表示某类个体的'干净’人脸,严格遵循子空间结构, E 表示由阴影、反光、遮挡等引起的误差项,这些误差项破坏了人脸图像的低秩结构.然后用低秩矩阵 A 和误差矩阵 E 构造训练字典,将测试样本表示为低秩矩阵 A 和误差矩阵 E 的联合稀疏线性组合,利用这两部分的稀疏逼近计算残差,进行分类判别.实验证明该稀疏表示识别算法有效,识别精度得到了有效提高.     

基于稀疏表示与特征融合的人脸识别方法

针对人脸识别在有遮挡、表情、光照的变化或受到噪声污染时鲁棒性变差问题,提出一种基于稀疏表示与特征融合的人脸识别算法。首先采用低秩恢复算法得到训练样本和测试样本的干净人脸图像,提取干净人脸图像的LBP,HOG,Gabor三种特征向量;然后对部分训练样本进行SRC分类测试,根据SRC的识别结果与分类残差定义一个损失函数,再利用正则化最小二乘法计算出使损失函数最小的权重向量;最后根据该权重向量重构规则化残差进行分类。在ORL,Extended Yale B和AR数据库上进行实验,结果表明,该算法优于利用单一特征识别的方法,并且对光照、噪声、遮挡等因素产生的影响有较好的泛化性能。     

近邻类加权结构稀疏表示图像识别算法

针对如何将近邻、子空间学习与稀疏表示结合起来解决稀疏分类计算量较大的问题。由于子空间中样本的类内散度小,类间散度大,且同类中所有样本对重构的影响相似,因此按类而非样本处理的思想更符合基于类重构误差进行分类的算法要求,为此提出一种基于近邻类加权结构稀疏表示算法用于图像识别。该算法首先利用线性类重构误差选取 个最近邻类,并将其对应的系数作为权值对投影后的近邻类加权,其次在投影子空间上,用 个类的加权训练样本集对测试样本进行结构稀疏表示,最后根据最小类重构误差得出分类结果。在AR,Yale B,MNIST,PIE数据库上的实验结果表明该方法在训练样本数较少的情况下获得较高的识别率且具有一定的鲁棒性。      

基于Gabor特征和字典学习的高斯混合稀疏表示图像识别

为了克服图像识别中光照,姿态等变化带来的识别困难,同时提高稀疏表示图像识别的鲁棒性,本文提出了一种基于Gabor特征和字典学习的高斯混合稀疏表示图像识别算法.高斯混合稀疏表示是基于最大似然估计准则,将稀疏保真度表示为余项的最大似然函数,最终识别问题转化为求解加权范数的优化逼近问题.本文算法首先提取图像的Gabor特征;然后对Gabor特征集进行字典学习,由于在学习过程中引入了Fisher准则作为约束,学习得到具有类别标签的新字典;最后使用高斯混合稀疏表示识别方法进行分类识别.在3个公开数据库(人脸数据库AR库和FERET库以及USPS手写数字库)上的实验结果验证了该算法的有效性和鲁棒性.     

有监督低秩子空间恢复的正则鲁棒稀疏表示人脸识别算法

针对训练样本和测试样本均存在光照及遮挡时,破坏图像低秩结构问题,本文提出基于监督低秩子空间恢复的正则鲁棒稀疏表示人脸识别算法。首先,将所有训练样本构造成矩阵D,对矩阵D进行监督低秩矩阵分解,分解为低秩类相关结构A,低秩类内差异结构B和稀疏误差结构E;然后用主成分分析方法找到类相关结构A低秩子空间的变换矩阵;再通过变换矩阵将训练样本和测试样本投影到低秩子空间;最后,在低秩子空间中,通过正则鲁棒稀疏编码进行加权分类识别。在AR和Extended Yale B公开人脸数据库上的实验结果验证本文算法的有效性及鲁棒性。      

改进SRC算法在人脸识别中的应用

稀疏表示分类算法(Sparse Representation-based Classification,SRC)在人脸数据库上有很高的识别性能。然而,对于姿态变化,SRC的识别效果并不理想。针对SRC算法不能解决测试样本与训练样本存在偏移误差的问题,本文提出了基于SRC的改进算法。该算法将每一类的训练样本单独作为训练字典,利用迭代校正和基于金字塔分层机构的运动偏移估计方法得到最终的偏移量,最后对校正后的测试样本使用SRC算法实现分类。实验结果表明该方法对于有偏移误差的人脸图像具有较好的鲁棒性及识别率。     

基于HOG低秩恢复与协同表征的人脸识别方法

在获取到的人脸图像不完备以及人脸图像在有遮挡、光照、表情的变化或受到噪声污染时,识别率就会变得十分低,针对这一问题,本文提出了一种基于HOG低秩恢复与协同表征的人脸识别算法HLRR_CRC.首先采用低秩恢复算法得到训练样本和测试样本的干净人脸图像,然后对测试样本中干净的人脸图像和训练样本中干净的人脸图像分别进行HOG特征提取,得到HOG特征向量,以此特征向量为基础,得到测试样本特征矢量的协同表示,最后,通过规则化残差进行分类.在ORL、Extended Yale B和AR数据库上进行测试,实验结果表明,本文算法对光照、噪声较鲁棒,相比于当前的人脸识别算法,本文算法在恶劣光照和噪声下的识别率平均提高29.6％.     

原子-分子字典结合的联合扩展加权稀疏表示人脸识别算法

针对训练样本字典学习仅包含全局信息、缺乏局部信息的不足,引入与类别相关的原子字典, 提出基于原子与分子字典联合扩展的加权稀疏表示人脸识别方法。首先,对各类训练样本进行PCA学习,得到带标记的训练样本基,构造PCA基原子字典,同时将训练样本字典作为分子字典。进而,利用原子字典与分子字典结合得到扩展字典模型。测试时,根据测试样本与扩展字典基之间的距离进行加权得到与当前测试样本关联的重构字典集,最后对测试样本稀疏重构,利用残差进行分类判别。为验证本文方法有效性,分别在AR、Georgia Tech和CMU PIE人脸数据库上进行实验。      

Cost-effective test solutions for smart card and other integrated flash applications

From its emergence in the late 1980s as a lower cost alternative to early EEPROM technologies, flash memory has evolved to higher densities and speedsand rapidly growing acceptance in mobile applications.In the process, flash memory devices have placed increased test requirements on manufacturers. Today, as flash device test grows in importance in China, manufacturers face growing pressure for reduced cost-oftest, increased throughput and greater return on investment for test equipment. At the same time, the move to integrated flash packages for contactless smart card applications adds a significant further challenge to manufacturers seeking rapid, low-cost test.     

An improved parallel thinning algorithm with two subiterations

The parallel thinning algorithm with two subiterations is improved in this paper. By analyzing the notions of connected components and passes, a conclusion is drawn that the number of passes and the number of eight-connected components are equal. Then the expression of the number of eight-connected components is obtained which replaces the old one in the algorithm. And a reserving condition is proposed by experiments, which alleviates the excess deletion where a diagonal line and a beeline intersect. The experimental results demonstrate that the thinned curve is almost located in the middle of the original curve connectivelv with single pixel width and the processing speed is high.     

Theoretical analysis of the relationship between the Brillouin gain coefficient and the strain in the optical-fiber sensors

The relation between the power of the Brillouin signal and the strain is one of the bases of the distributed fiber sensors of temperature and strain. The coefficient of the Bfillouin gain can be changed by the temperature and the strain that will affect the power of the Brillouin scattering. The relation between the change of the Brillouin gain coefficient and the strain is thought to be linear by many researchers. However, it is not always linear based on the theoretical analysis and numerical simulation. Therefore, errors will be caused if the relation between the change of the Brillouin gain coefficient and the strain is regarded as to be linear approximately for measuring the temperature and the strain. For this reason, the influence of the parameters on the Brillouin gain coefficient is proposed through theoretical analysis and numerical simulation.     

Novel fiber-optical interferometer with miniaturized probe for in-hole measurements

Today, micro-system technology and the development of new MEMS （Micro-Electro-Mechanical Systems） are emerging rapidly. In order for this development to become a success in the long run, measurement systems have to ensure product quality. Most often, MEMS have to be tested by means of functionality or destructive tests. One reason for this is that there are no suitable systems or sensing probes available which can be used for the measurement of quasi inaccessible features like small holes or cavities. We present a measurement system that could be used for these kinds of measurements. The system combines a fiber optical, miniaturized sensing probe with low-coherence interferometry, so that absolute distance measurements with nanometer accuracy are possible.     

Teleportation of an arbitrary unknown N-qubit entangled state under the controlling of M controllers

A new quantum protocol to teleport an arbitrary unknown N-qubit entangled state from a sender to a fixed receiver under M controllers(M < N) is proposed. The quantum resources required are M non-maximally entangled Greenberger-Home-Zeilinger (GHZ) state and N-M non-maximally entangled Einstein-Podolsky-Rosen (EPR) pairs. The sender performs N generalized Bell-state measurements on the 2N particles. Controllers take M single-particle measurement along x-axis, and the receiver needs to introduce one auxiliary two-level particle to extract quantum information probabilistically with the fidelity unit if controllers cooperate with it.     

Diode-end-pumped Nd:YVO4/LBO lasers with 4.2W continuous-wave output at 457 nm

A continuous-wave (CW) 457 nm blue laser operating at the power of 4.2 W is demonstrated by using a fiber coupled laser diode module pumped Nd: YVO4 and using LBO as the intra-cavity SHG crystal With the optimization of laser cavity and crystal parameters, the laser operates at a very high efficiency. When the pumping power is about 31 W, the output at 457nm reaches 4.2 W, and the optical to optical conversion efficiency is about 13.5% accordingly. The stability of the out putpower is better than 1.2% for 8 h continuously working.     

Call for Papers

正Wireless Body-area Networks The last decade has witnessed the convergence of three giant worlds:electronics,computer science and telecommunications.The next decade should follow this convergence in most of our activities with the generalization of sensor networks.In particular with the progress in medicine,people live longer and the aging of population will push the development of wireless personal networks     

Call for Papers—Feature Topic,Vol.12,No.7,2015

正Information Centric Networking Information-Centric Networking(ICN) is an emerging direction in Future Internet architecture research,gaining significant tractions among academia and industry.Aiming to replace the conventional host-to-host communication model by a data-centric model,ICN treats data content as the first     

JOURNAL OF ELECTRONICS(CHINA)

正~~     

NEXT GENERATION WIRELESS NETWORKS–ESPECIALLY THE USE OF MILLI-MICROWAVE BANDS

The global bandwidth shortage of wireless communications has motivated the exploration of the naillimeter wave （ram-wave） frequency spectrum for the next generation wireless communications. Recent advances in RF CMOS technology and high speed baseband signal processing technologies have enabled tile extensive research and development of turn-wave wireless communications. The multi gigabit per second data rate of ram-wave system will lead to applications in many important scenarios, such as WPAN, WLAN,back-haul for cellular system. And the frequency bands include 28 GHz, 38 GHz, 45GHz, 60GHz, E-BAND and even beyond 100 GHz. The propagation and the imitation of the RF circuits design in these frequency bands make the directional antennas be inevitable for mm-wave communications.