共查询到20条相似文献,搜索用时 31 毫秒
1.
2.
为快速有效地进行手指静脉识别,针对双向二维主成分分析算法降维的特点,并对该算法进行改进,提出在经过图像预处理的手指静脉图像基础上,特征值归一化并双向加权(2D)2PCA的手指静脉识别方法((OW2D)2PCA).分析了累积特征率对(2D)2PCA的影响,以及加权值、特征值归一加权值和累积特征率对W(2D)2PCA、OW(2D)2PCA、(W2D)2PCA、(OW2D)2PCA的影响.通过建立手指静脉图像库的实验结果表明,文中提出方法能够取得较好的识别效果;对(2D)2PCA提取特征向量中的冗余信息有很强的抑制作用,双向加权比单向加权效果更好;而且(OW2D)2PCA的平均识别率高于2DPCA、(2D)2PCA、W(2D)2PCA、(W2D)2PCA和OW(2D)2PCA. 相似文献
3.
梁华 《计算机工程与应用》2010,46(20):84-85
利用Gray映射Φ的性质,研究了环F2+uF2和Z4上的任意长循环码。证明了环F2+uF2上任意长码是循环码当且仅当它的Gray象是域F2上的准循环码,得到了Z4上任意长码是循环码的一个充分必要条件。特别的,环F2+uF2上长为n的线性循环码的Gray象是域F2上指标为2长为2n的线性准循环码,环Z4上长为n的线性循环码的Gray象是域F2上指标为2长为2n的准循环码。 相似文献
4.
区间二型模糊集合将次隶属度做了简化,基于KM降阶算法的区间二型模糊控制器实现起来相对简单.虽然区间二型模糊控制器在一定程度上优于传统的一型模糊控制器或者PI控制器等,但区间二型模糊控制器并没有充分利用二型模糊集合的次隶属度信息.为解决这些问题,研究了普通二型模糊控制器的一般结构,提出了一种等价于PI的二型模糊控制器.该... 相似文献
5.
本文对157百合进行了染色体核型研究,结果表明:157百合体细胞染色体数为2n=2x=24;染色组成为R(2n)=2x=2m(SAT)+2m+2Sm(SAT)+16St+2t;在第1,2,对染色体上有随体;其核型分类属于3B型。 相似文献
6.
提出一种基于对等网的流媒体数据分配算法(DA2SMp2p),可根据网络环境的变化动态调整数据分配,在提供节点中途失效时,可以比MBDAp2p算法、OTSp2p算法和Algorithm_1算法保持更好的流媒体连续性,提供节点没有失效时,所取得的段缓冲延迟与MBDAp2p算法相同,比OTSp2p算法和Algorithm_1算法小。DA2SMp2p算法、MBDAp2p算法和OTSp2p算法保持连续播放的最小缓冲延迟相同,都比Algorithm_1算法小。 相似文献
7.
为了让P2P技术能够在高校远程教育中等到更好的应用,提出了完全对称结构的P2P体系结构.通过大量的调查研究,分析了传统的主从结构的P2P体系结构存在的问题,包括性能上的瓶颈和管理上的局限性.在此基础上,提出了完全对称结构的P2P体系结构,并设计和构建主从结构的P2P体系结构和完全对称结构的P2P体系结构算法模型.在建立算法模型后,进行了大量的模拟测试.通过效果对比,验证了完全对称的P2P体系结构不仅进一步提高资源搜索效率和数据传输效率,还能大幅度提高整个系统的高可用性,更重要是能让远程教育系统的处理能力进行线性扩展. 相似文献
8.
Haixian Wang 《Machine Vision and Applications》2011,22(2):433-438
In this paper, a new technique called structural two-dimensional principal component analysis (S2DPCA) is proposed for image
recognition. S2DPCA is a subspace learning method that identifies the structural information for discrimination. Different
from conventional two-dimensional principal component analysis (2DPCA) that only reflects within-row information of images,
the goal of S2DPCA is to discover structural discriminative information contained in both within-row and between-row of the
images. By contrast with 2DPCA, S2DPCA is directly based on the augmented images encoding corresponding row membership, and
the projection directions of S2DPCA are obtained by solving an eigenvalue problem of the augmented image covariance matrix.
Computationally, S2DPCA is straightforward and comparative with 2DPCA. Like 2DPCA, the singularity problem is completely avoided
in S2DPCA. Experiments on face recognition and handwritten digit recognition are presented to show the effectiveness of the
proposed approach. 相似文献
9.
10.
11.
SnO_2/SiO_2双层薄膜的湿敏特性 总被引:2,自引:0,他引:2
本实验是在单晶硅片上热生长一层SiO2,然后用真空淀积的方法获得一层超微粒SnO2薄膜,通过对SnO2/SiO2薄膜电阻与相对湿度关系的测试,发现阻湿的线性特性和灵敏度明显优于SnO2薄膜和SiO2薄膜,测湿范围明显展宽。 相似文献
12.
《IEEE transactions on systems, man, and cybernetics. Part B, Cybernetics》2008,38(6):1537-1548
13.
为了判断二维非对称受限编码的信道容量是否为正,提出了扫描方法.若满足限制(d1,k1,d2,k2)矩阵中的每个位置都可以通过已知的标志来决定并且被扫描,则限制(d1,k1,d2,k2)的信道容量为0.通过对特定二维受限编码信道容量的证明,验证了扫描方法比代数与组合方法更为有效.同时采用证明信道容量大于零常用的技术,找到满足(d1,k1,d2,k2)受限的两个m×n矩阵,若两矩阵在各种变形下都满足(d1,k1,d2,k2)限制,则信道容量Cd1,k1,d2,k2≥1/mn.这一方法对信道容量为正的区域进行扩展. 相似文献
14.
15.
16.
17.
模块2DPCA是2DPCA的推广,在识别性能上比2DPCA更具鲁棒性。本文分析了模块2DPCA在计算训练样本总体散布矩阵和本征向量选取方面的缺陷,提出了一种改进的模块2DPCA算法。实验结果表明,改进后的算法能更好地选取本征向量,更有效地提取人脸特征。 相似文献
18.
Zhi Liu C. L. Philip Chen Yun Zhang Han-xiong Li 《Soft Computing - A Fusion of Foundations, Methodologies and Applications》2012,16(11):1945-1957
A type-2 hierarchical fuzzy system (T2HFS) is presented for the high-dimensional data-based modeling with uncertainties. Type-2 fuzzy logic system (T2FLS) is a powerful tool to handle uncertainties in complex processes. However, the operation of type-reduction has greatly increased the computational burden of T2FLSs. By integrating the T2FLS with hierarchical structure, a systematic design methodology of T2HFS is proposed to avoid the rule explosion and to simplify the computation complexity. The design methodology has included several procedures to establish the T2HFS. Firstly, the PCA-based method is developed to capture the prominent component from training data, and to determine the hierarchical structure of T2HFS. Furthermore, a novel clustering method is proposed to design the basic type-2 fuzzy logic unit (T2FLU) in uncertain environments. Finally, a hybrid-learning method is presented to fine-tune the parameters for the global optimization where the statistical and deterministic optimization methods are developed for the nominal and auxiliary performance, respectively. Simulation results have shown that the proposed T2HFS is very effective for the high-dimensional data-based modeling and control in uncertain environment. 相似文献
19.
基于FPSO的电力巡检机器人的广义二型模糊逻辑控制 总被引:1,自引:1,他引:0
针对电力巡检机器人(Power-line inspection robot, PLIR)的平衡调节问题, 设计了广义二型模糊逻辑控制器(General type-2 fuzzy logic controller, GT2FLC); 针对GT2FLC中隶属函数参数难以确定的问题, 通过模糊粒子群(Fuzzy particle swarm optimization, FPSO)算法来优化隶属函数参数. 将GT2FLC的控制性能与区间二型模糊逻辑控制器(Interval type-2 fuzzy logic controller, IT2FLC)和一型模糊逻辑控制器(Type-1 fuzzy logic controller, T1FLC) 的控制性能进行对比. 除此之外, 还考虑了外部干扰对三种控制器控制效果的影响. 仿真结果表明, GT2FLC具有更好的性能和处理不确定性的能力. 相似文献
20.
《国际计算机数学杂志》2012,89(3-4):171-188
The node-visit optimal (NVO) and the space-cost optimal (SCO) height-balanced (HB) 2-3 brother trees are defined. The characterization of the NVO HB 2-3 brother trees is developed. This characterization leads to a linear-time algorithm for constructing an NVO HB 2-3 brother tree for an ordered set of keys. The minimum space-cost of an N-key NVO HB2-3 brother tree and the space-cost of an N-key SCO HB 2-3 brother tree is analysed. It is shown that the minimum space-cost of an NVO HB 2-3 brother tree is never more than one plus the space-cost of an SCO HB 2-3 brother tree. Further, the minimum node-visit cost of an SCO HB 2-3 brother tree is at most one plus the node-visit cost of an NVO HB 2-3 brother tree. It is also shown that there exists an HB 2-3 brother tree which is both SCO and NVO for just over half the possible values of keys. Finally, an outline for constructing an SCO HB 2-3 brother tree is presented. 相似文献