一种有效的快速指纹预处理算法与仿真

针对自动指纹识别系统中,关于时间复杂度高的指纹图像预处理算法进行研究,为了提高识别速度,有效去除噪声,提出一种有效的快速指纹预处理算法。算法基于指纹的方向场,采用查表的方法,对指纹图像进行8方向滤波增强,并采用混合式快速细化算法完成指纹的细化。对100幅URU4000B指纹采集仪采集的指纹图像在Matlab中进行仿真,结果表明92%的图像都能达到较好的处理效果。算法速度快,适用于配置一般的基于嵌入式平台的指纹自动识别系统。     

基于区域分割的水下目标实时识别系统

提出了一种基于最优阈值分割算法的水下目标自动实时识别系统。该系统首先运用去噪、图像均衡等方法对实时摄取的水下图像进行预处理。然后运用基于遗传算法优化的 Otsu(即大津方法)最优阈值分割算法对所得图像进行区域分割并提取图像的特征向量。最后采用 BP 神经网络对提取的特征向量进行自动分类从而最终确定了水下目标的类型。水槽仿真试验表明该方法能够在恶劣的环境下自动地检测水下目标,而且该方法具有较强的抗光线干扰能力和较高的准确度。     

改进的指纹图像预处理在指纹识别中的应用

指纹图像的预处理在计算机指纹自动识别系统(AFIS)中有着非常重要的作用,直接制约着系统的识别率和识别速度.在总结现有常用预处理算法的基础上,结合指纹图像的特点,通过实验提出并实现了一些改进的预处理算法,即先计算出指纹的脊线方向,然后将脊线方向应用到预处理的各个算法中.结果表明,基于脊线方向的预处理算法能明显改善指纹图像的处理效果,可以很好的提高指纹图像的质量,在同样的特征提取算法和匹配条件下,改进的预处理方法的识别率高于传统方法.     

基于深度置信网络的目标识别方法

针对合成孔径雷达图像预处理鲁棒性不足、特征提取及利用不充分等问题,提出了一种基于深度置信网络的合成孔径雷达(SAR)图像目标自动识别算法。首先提出一种基于双树复小波变换（DT-CWT）的非局部均值图像降斑算法,并结合目标方位角估计实现对原始数据鲁棒的预处理;最后,引入多层深度置信网络提取针对合成孔径雷达目标的深度抽象视觉信息作为特征并完成识别任务。采用3类运动与静止目标的获取与识别(MSTAR)实测数据进行的仿真实验结果表明,所提算法具有较高鲁棒性和识别率。     

基于形态学变换等技术的川南石刻图像预处理方法研究

川南石刻图像自动识别系统中的预处理是十分关键的一步,预处理效果的好坏直接关系到后面特征提取与识别的质量.论文详细讨论了图像预处理的方法与过程,并在此基础上提出基于数学形态学的川南石刻图像分割、灰度、二值化、增强、边缘提取等预处理方法,最后在仿真实验中证明了该方法的有效性.     

基于改进SPCNN模型的机场跑道胶痕检测方法

针对机场跑道胶痕形态特征多样性和跑道环境复杂性导致胶痕检测效率低下的问题,提出了基于改进简化脉冲耦合神经网络模型的机场跑道胶痕图像分割算法。首先在利用邻域灰度关系优化反馈输入的基础上,将神经元点火阈值机制从传统的指数衰减改进为线性分层步长衰减。然后引入杜鹃搜索算法,结合最小交叉熵对改进模型进行参数寻优。最后根据点火映射区域的平均灰度值构建自适应迭代终止条件。实验结果表明,该算法具有更高的胶痕检测精度,且在光照条件较差和标志线影响的情况下具有更好的抗干扰性。     

基于Lab颜色模型的聚类舌图像分割

舌图像分割是舌诊客观化的基础,针对舌图像的特点,提出了一种基于Lab颜色模型的聚类舌图像分割算法,该算法对原始图像进行ROI提取、均值滤波等预处理;对预处理过后的图像进行偏色校正和Lab颜色模型转换,以改善环境、人为等外界因素带来的影响;用K-means算法完成舌图像的自动分割.     

一种复杂环境下的跑道识别的新方法

针对机场在遥感图像中成像的复杂性与多样性,提出一种新的机场跑道的自动识别方法。该方法将跑道识别分为定位和识别两个步骤。首先在定位步骤中基于变形模板模型理论,建立了跑道的平行线模型及似然函数,并采用Meropolis算法确定跑道的准确边界;其次,通过分析跑道的标志特征和结构特征确立了跑道识别的通用性判别规则。通过对Spot图像的实验证明,该方法能够实现复杂环境下的跑道自动识别。     

汽车牌照自动识别系统算法研究

该文章研究基于计算机车牌自动识别的算法:图像预处理,车牌定位,字符分割,字符识别。运用模式识别、人工智能等技术,对采集到的汽车图像,实时准确的自动识别出车牌的数字、字母以及汉字字符,并以计算机可直接运行的数据形式给出识别结果。     

基于区域分割的水下目标实时识别系统

在真实水下环境中,检测和识别水下日标一致是研究的重点。介绍了一种基于最优阈值分割算法的水下目标自动实时识别系统。首先运用去噪、图像均衡等方法对实时摄取的水下图像进行预处理,接着运用基于遗传算法优化的Otsu（即大津方法）最优阈值分割算法对所得图像进行区域分割,提取图像的特征向量,最后采用BP神经网络对提取的特征向量进行自动分类从而最终确定了水下目标的类型。水槽仿真试验表明系统能够在恶劣的环境下自动地检测水下目标,而且该方法具有较强的抗光线干扰能力和较高的准确度。     

A neural network based on the generalized Fischer-Burmeister function for nonlinear complementarity problems

In this paper, we consider a neural network model for solving the nonlinear complementarity problem (NCP). The neural network is derived from an equivalent unconstrained minimization reformulation of the NCP, which is based on the generalized Fischer-Burmeister function ?_p(a,b)=‖(a,b)‖_p-(a+b). We establish the existence and the convergence of the trajectory of the neural network, and study its Lyapunov stability, asymptotic stability as well as exponential stability. It was found that a larger p leads to a better convergence rate of the trajectory. Numerical simulations verify the obtained theoretical results.     

Generation of robust root loci for linear systems with parametric uncertainties in an ellipsoid

Given a parametric polynomial family p(s; Q) := {ⁿ _k=0 a_k (q)s^k : q ] Q}, Q R ^m , the robust root locus of p(s; Q) is defined as the two-dimensional zero set _p,Q := {s ] C:p(s; q) = 0 for some q ] Q}. In this paper we are concerned with the problem of generating robust root loci for the parametric polynomial family p(s; E) whose polynomial coefficients depend polynomially on elements of the parameter vector q ] E which lies in an m-dimensional ellipsoid E. More precisely, we present a computational technique for testing the zero inclusion/exclusion of the value set p(z; E) for a fixed point z in C, and then apply an integer-labelled pivoting procedure to generate the boundary of each subregion of the robust root locus _p,E . The proposed zero inclusion/exclusion test algorithm is based on using some simple sufficient conditions for the zero inclusion and exclusion of the value set p(z,E) and subdividing the domain E iteratively. Furthermore, an interval method is incorporated in the algorithm to speed up the process of zero inclusion/exclusion test by reducing the number of zero inclusion test operations. To illustrate the effectiveness of the proposed algorithm for the generation of robust root locus, an example is provided.     

Theoretical analysis of a remotely measurable soil evaporation transfer coefficient

Reducing soil evaporation (E) is an important way to increase water use efficiency for agriculture and sustainable water use. To achieve this goal, an accurate estimate of soil evaporation at the macro-scale level is necessary. By including the surface temperature of dry soil, the three temperatures model (3T model) was proposed as an estimate of E, and its temperature term was defined as the soil evaporation transfer coefficient (h_a). Although it has been primarily shown that h_a determines the boundaries of E, further studies of its properties are necessary because h_a has the application potential for remote sensing. The objectives of this study are to (1) investigate the relationships between h_a and those parameters that are important for E estimation but are not able to be remotely measured (aerodynamic resistance, soil surface resistance (r_s), and cumulative evaporation (E_c)); and (2) discuss the possibility for remote sensing application. Two experiments were carried out for these purposes: one in an open field and the other one in a closed growth chamber at constant temperature, humidity, and radiation. The following results were obtained: (1) Given the boundaries of 0 ≤ h_a ≤ 1, E was determined between its maximum value (potential evaporation rate) and minimum value (zero); (2) During the period when evaporation is controlled by r_s, a linear relation between h_a and log (r_s) is observed with a coefficient of determination r² = 0.76. Because h_a and r_s are independent variables with significant differences in properties and magnitudes, these results indicate that h_a and r_s are well related to each other; (3) During stage 1 of evaporation, cumulative evaporation (E_c) increased with time while h_a remained constant. Afterwards, h_a linearly increased with E_c. The relationships among h_a, E_c, r_a, and r_s would be useful for estimation of evapotranspiration by remote sensing.     

Coloring inductive graphs on-line

In this paper we consider the problem of on-line graph coloring. In an instance of on-line graph coloring, the nodes are presented one at a time. As each node is presented, its edges to previously presented nodes are also given. Each node must be assigned a color, different from the colors of its neighbors, before the next node is given. LetA(G) be the number of colors used by algorithmA on a graphG and letx(G) be the chromatic number ofG. The performance ratio of an on-line graph coloring algorithm for a class of graphsC is max_{G C(A(G)/(G))}. We consider the class ofd-inductive graphs. A graphG isd-inductive if the nodes ofG can be numbered so that each node has at mostd edges to higher-numbered nodes. In particular, planar graphs are 5-inductive, and chordal graphs arex(G)-inductive. First Fit is the algorithm that assigns each node the lowest-numbered color possible. We show that ifG isd-inductive, then First Fit usesO(d logn) colors onG. This yields an upper bound ofo(logn) on the performance ratio of First Fit on chordal and planar graphs. First Fit does as well as any on-line algorithm ford-inductive graphs: we show that, for anyd and any on-line graph coloring algorithmA, there is ad-inductive graph that forcesA to use (d logn) colors to colorG. We also examine on-line graph coloring with lookahead. An algorithm is on-line with lookaheadl, if it must color nodei after examining only the firstl+i nodes. We show that, forl/logn, the lower bound ofd logn colors still holds.This research was supported by an IBM Graduate Fellowship.     

Scalable 2D Convex Hull and Triangulation Algorithms for Coarse Grained Multicomputers

In this paper we describe scalable parallel algorithms for building the convex hull and a triangulation ofncoplanar points. These algorithms are designed for thecoarse grained multicomputermodel:pprocessors withO(n/p)⪢O(1) local memory each, connected to some arbitrary interconnection network. They scale over a large range of values ofnandp, assuming only thatn⩾p^1+ε(ε>0) and require timeO((T_sequential/p)+T_s(n, p)), whereT_s(n, p) refers to the time of a global sort ofndata on approcessor machine. Furthermore, they involve only a constant number of global communication rounds. Since computing either 2D convex hull or triangulation requires timeT_sequential=Θ(n log n) these algorithms either run in optimal time,Θ((n log n)/p), or in sort time,T_s(n, p), for the interconnection network in question. These results become optimal whenT_sequential/pdominatesT_s(n, p) or for interconnection networks like the mesh for which optimal sorting algorithms exist.     

Operations preserving regular languages

Given a strictly increasing sequence s   of non-negative integers, filtering a word _a0a1?_an$a_0{a}_1?a_n$ by s   consists in deleting the letters _ai$a_i$ such that i   is not in the set {_s0,_s1,…}$\{s_0,s_1,\dots \}$. By a natural generalization, denote by L[s]$L[s]$, where L is a language, the set of all words of L filtered by s. The filtering problem is to characterize the filters s such that, for every regular language L  , L[s]$L[s]$ is regular. In this paper, the filtering problem is solved, and a unified approach is provided to solve similar questions, including the removal problem considered by Seiferas and McNaughton. Our approach relies on a detailed study of various residual notions, notably residually ultimately periodic sequences and residually rational transductions.     

The region approach for computing relative neighbourhood graphs in the Lp metric

The following geometrical proximity concepts are discussed: relative closeness and geographic closeness. Consider a setV={v ₁,v ₂, ...,v _n } of distinct points in atwo-dimensional space. The pointv _j is said to be arelative neighbour ofv _i ifd _p (v _i ,v _j )≤max{d _p (v _j ,v _k ),d _p (v _j ,v _k )} for allv _k ∈V, whered _p denotes the distance in theL _p metric, 1≤p≤∞. After dividing the space around the pointv _i into eight sectors (regions) of equal size, a closest point tov _i in some region is called anoctant (region, orgeographic) neighbour ofv _i. For anyL _p metric, a relative neighbour ofv _i is always an octant neighbour in some region atv _i. This gives a direct method for computing all relative neighbours, i.e. for establishing therelative neighbourhood graph ofV. For every pointv _i ofV, first search for the octant neighbours ofv _i in each region, and then for each octant neighbourv _j found check whether the pointv _j is also a relative neighbour ofv _i. In theL _p metric, 1<p<∞, the total number of octant neighbours is shown to be θ(n) for any set ofn points; hence, even a straightforward implementation of the above method runs in θn ²) time. In theL ₁ andL _∞ metrics the method can be refined to a θ(n logn+m) algorithm, wherem is the number of relative neighbours in the output,n-1≤m≤n(n-1). TheL ₁ (L _∞) algorithm is optimal within a constant factor.     

Whole-body vibration exposure experienced by motorcycle riders – An evaluation according to ISO 2631-1 and ISO 2631-5 standards

Riders of twelve motorcycles, comprising 6 full-scale motorbikes and 6 motor-scooters, and 5 sedan vehicles, performed test runs on a 20.6 km paved road composed of 5 km, 5 km, and 10.6 km of rural, provincial and urban routes, respectively. Each test run of motorcycle was separately performed under speed limits of 55 km/h and 40 km/h. Tri-axial accelerations of whole-body vibration (WBV) were obtained by using a seat pad and a portable data logger, and the driver's view was videotaped with a portable media recorder. Root mean square (RMS) acceleration, 8-h estimated vibration dose value (VDV₍₈₎) and 8-h estimated daily dose of static compression dose (S_ed) were determined from the collected data in accordance with ISO 2631-1 and ISO 2631-5 standards. Experimental results indicate that the WBV values of the sedan vehicle drivers have low RMS, VDV₍₈₎ and S_ed values (RMS 0.27–0.32 m/s²; VDV₍₈₎ 6.3–8.3 m/s^1.75; S_ed 0.21–0.26 MPa). However, over 90% of the motorcycle riders had VDV₍₈₎ (mean 23.5 m/s^1.75) exceeding the upper boundary of health guidance caution zone (17 m/s^1.75) recommended by ISO 2631-1, or had S_ed (mean 1.17 MPa) exceeding the value associated with a high probability of adverse health effects (0.8 MPa) recommended by ISO 2631-5. Over 50% of the motorcycle riders reached these boundary values for VDV and S_e in less than 2 h. The WBV exposure levels of the full-scale motorbikes riders and motor-scooter riders were not significantly different. However, the RMS and VDV₍₈₎ values of motorcycle riders indicate significant roadway effect (p < 0.001), while their S_ed values indicate significant speed limit effect (p < 0.05). This study concludes that the WBV exposure levels of common motorcycle riders are distinctively higher than those of sedans, even on a regular paved road. The impact on health of WBV exposure in motorcycle riders should be carefully addressed with reference to ISO 2631-1 and ISO 2631-5.

Relevance to industry

This study compares the predicted health risks of motorcycle riders according to ISO 2631-1 and ISO 2631-5 standards. Experimental data suggest that the vibration dose value of ISO 2631-1 and daily dose of equivalent static compression stress of ISO 2631-5 have roughly equivalent boundaries for probable health effects.     

Fast evaluation of the hypergeometric function p F p−1(a; b; z) at the singular point z = 1 by means of the Hurwitz zeta function ζ(α, s)

A method for fast and highly accurate evaluation of the generalized hypergeometric function _p F _p?1(a ₁, ..., a _p ; b ₁, ..., b _p?1; 1) = Σ _{k = 0} ^∞ f _k by means of the Hurwitz zeta function ζ(α, s) is developed. Based on asymptotic analysis of the coefficients f _k , an expansion of _p F _p?1 is constructed as a combination of the functions ζ(α, s) with explicit coefficients expressed in terms of the generalized Bernoulli polynomials. An appropriate selection of the parameter α and the number of terms of the asymptotic expansion makes it possible to obtain the result with any desired degree of accuracy. The use of computer algebra methods, efficient numerical algorithms, and stochastic optimization methods considerably improve the efficiency of the suggested method.