Unifying representation of Bézier curve and two kinds of generalized ball curves

This paper presents a new basis, the WSB basis, which unifies the Bemstein basis, Wang-Ball basis and Said-Ball basis, and therefore the Bézier curve, Wang-Ball curve and Said-Ball curve are the special cases of the WSB curve based on the WSB basis In addition, the relative degree elevation formula, recursive algorithm and conversion formula between the WSB basis and the Bern- stein basis are given.

A Novel Contour Tracing Algorithm for Object Shape Reconstruction Using Parametric Curves

Parametric curves such as Bézier and B-splines, originally developedfor the design of automobile bodies, are now also used in image processing andcomputer vision. For example, reconstructing an object shape in an image,including different translations, scales, and orientations, can be performedusing these parametric curves. For this, Bézier and B-spline curves can be generatedusing a point set that belongs to the outer boundary of the object. Theresulting object shape can be used in computer vision fields, such as searchingand segmentation methods and training machine learning algorithms. Theprerequisite for reconstructing the shape with parametric curves is to obtainsequentially the points in the point set. In this study, a novel algorithm hasbeen developed that sequentially obtains the pixel locations constituting theouter boundary of the object. The proposed algorithm, unlike the methods inthe literature, is implemented using a filter containing weights and an outercircle surrounding the object. In a binary format image, the starting point ofthe tracing is determined using the outer circle, and the next tracing movementand the pixel to be labeled as the boundary point is found by the filter weights.Then, control points that define the curve shape are selected by reducing thenumber of sequential points. Thus, the Bézier and B-spline curve equationsdescribing the shape are obtained using these points. In addition, differenttranslations, scales, and rotations of the object shape are easily provided bychanging the positions of the control points. It has also been shown that themissing part of the object can be completed thanks to the parametric curves.

B-Spline-ORB特征点提取算法

针对传统ORB算法尺度不变性较差的问题,提出了基于图像金子塔的ORB算法。首先研究了高斯图像金字塔和B-spline图像金字塔,通过实验对两种图像金字塔进行了探讨。实验表明,3阶B-spline图像金字塔的图像所包含的图像信息要高于相同层上高斯图像金子塔的图像所包含的信息。其次,在图像尺度发生变化的前提下,通过实验对传统ORB算法、基于高斯图像金字塔的ORB算法和基于B-spline图像金字塔的ORB算法进行了探讨。实验表明,基于3阶B-spline图像金字塔的ORB算法相比较传统ORB算法所提取的特征点配准率提高了40%。同时,相较基于高斯图像金字塔的ORB算法,本文提出的改进算法在匹配准确率和运行速度上也有所提升。

B/S模式下嵌入式说话人身份认证系统

目的研究设计基于B/S模式的与文本相关嵌入式说话人语音身份认证系统。方法针对网络数据传输的噪声环境、语音识别算法的复杂度和大量用户远程实时认证的需求等问题,首次利用了MPC850微控制器和EP2C35 FPGA芯片,采用2代小波降噪,语音增强,声谱中主要参数分布估计,加权MFCC语音特征提取,与指定文本相关的混合HMM辨识等技术完成设计要求。结果给出了系统SOC实现方法,讨论了语音特征提取算法的原理及改进措施。结论该系统能有效地完成基于B/S模式远程说话人身份认证,具有较高的实践应用价值。

B样条小波在铁路接触网故障诊断中的应用

提出了构造具有零点中心对称的二次B样条母函数的方法,利用该小波母函数把基于小波变换模极大值的信号奇异性检测理论应用于铁路接触网故障信号特征提取中,并利用Mallat算法对接触网故障后的瞬态行波信号实施多分辨率分析,实验结果表明,该方法能准确定位故障点,有效识别接触网故障类型。

T-Splines Based Isogeometric Topology Optimization with Arbitrarily Shaped Design Domains

In this paper,a new isogeometric topology optimization(ITO)method is proposed by using T-splines based isogeometric analysis(IGA).The arbitrarily shaped design domains,directly obtained from CAD,are represented by a single T-spline surface which overcomes the topological limitations of Non-Uniform Rational B-Spline(NURBS).The coefficients correlated with control points are directly used as design variables.Therefore,the T-spline basis functions applied for geometry description and calculation of structural response are simultaneously introduced to represent the density distribution.Several numerical examples show that the proposed approach leads to a coherent workflow to handle design problems of complicated structures.The optimized results are free of checkerboard patterns without additional stabilization and filtering techniques due to the properties of T-splines,which also simplified the post-processing.In addition,through performing local refinement,we can easily achieve multiresolution optimization and infill optimization within the T-splines based framework.In general,the proposed method provides a possibility to design,analyze,and optimize engineering structures in a uniform model,which has the potential to improve design efficiency and reduce the cost of product development.

航天器视觉导航多尺度B-Harris特征提取算法

在航天器视觉相对导航中,为了能够跟踪目标航天器,并对其的位姿信息进行实时、精确地观测和估计,首先需要针对相关图像建立稳定而快速的特征点提取与匹配算法,而特征点提取和匹配算法的准确性与实时性直接影响了航天器相对位姿的估计精度。针对SIFT算法计算量大,匹配时间长,不能满足航天任务高实时性的问题,提出了B-Harris(Binary Harris)算法,该方法结合SIFT算法的结构思想,通过采用多尺度Harris算子提取具有尺度不变的特征点;同时采用128位二进制描述子建立特征向量,组成B-Harris算法,使得特征点匹配时间大大降低。最后通过与SIFT算法的实验对比,证明了B-Harris算法能够适应航天器发生的旋转、尺度、视角等变化,并且在实时性方面明显优于SIFT特征点算法,能够满足航天任务的实时性要求。

The Automatic Generation of Chinese Outline Font Based on Stroke Extraction

A new method to obtain spline outline description of Chinese font based onstroke extraction is presented. It has two primary advanages: (1) the qualityof Chinese output is greatly improved; (2) the memory requirement is reduced.The method for stroke extraction is discussed in detail and experimental resultsare presented.

基于PHP技术的在线考试系统设计与实现

根据现代教育的发展需要,考试系统已成为计算机辅助教学的一个重要组成部分。为此,本文构建并设计了一个在线考试系统。系统被划分为用户注册/登录模块、考试模块和管理模块等三大部分,阐述了各模块及其子模块的功能,并对系统建立了流程图。着重讨论了实现过程中的相关技术和方法。在线考试系统的体系结构为B/S架构,以Linux作为服务器操作系统,MySQL为数据库平台,采用PHP技术开发。

基于循环神经网络的语音识别研究

语音识别作为人工智能研究中不可或缺的一部分已经逐渐渗透到人们的日常生活中。针对传统语音识别方法不能很好地实现并识别复杂多变、非特定人语音的问题,文中提出利用在时间序列上关联性较强的循环神经网络(RNN)建立语音识别模型。考虑到语音信号丰富的时频信息表达,在特征提取环节进行改进,利用具有较好时频分辨率的小波变换(WT)取代快速傅里叶变换(FFT)作为该模型的输入;然后,采用随时间展开的反向传播算法(BPTT)进行特征学习与训练。在实验测试中,首先,对比分析了基于小波变换的特征提取对识别效果的影响;其次,通过与传统的HMM模型及BP神经网络的识别率做对比,验证RNN神经网络可提高语音识别准确率和稳定性。

利用曲线面变形提取产品形态体特征的方法研究

在变形设计理论的基础上,提出了将产品主体形态分解为子形态。研究了基于超椭圆方程和三次带参均匀B样条曲线构造技术提取影响产品艺术风格子形态横截面造型特征的方法,并结合曲面构造变形技术实现产品形态体特征的提取。以电动手工具为例研究了产品形态体特征提取与形态优化设计效果,得出超椭圆方程提取算法参数少,可较好地提取对称图形、非倒角图形的造型特征;基于三次带参均匀B样条曲线构造技术的算法参数较多,可较好地提取多种图形。

遗传算法优化的模糊神经网络在刀具磨损诊断中的应用

针对刀具磨损监测时,采集的振动信号含有强烈的背景噪声,难以提取故障频率的问题,提出采用形态滤波消噪后进行经验模态分解来提取故障频率;同时,为了准确监测刀具的磨损状态,将提取的故障特征输入到遗传算法优化的模糊神经网络对刀具的磨损进行识别,模糊神经网络的基函数采用B样条基函数。传统的网络学习算法采用梯度下降法,这在学习过程中容易陷入局部最小,论文采用遗传算法寻求全局的最优解。实验表明,该方法能有效地应用于强噪声背景下的刀具磨损识别。

一种基于细菌觅食优化算法的舌体分割算法

针对医学舌体数字图像的准确分割,提出了一种基于细菌觅食优化算法(BFOA)和Snake活动轮廓模型相组合的舌体分割算法。首先,以信息熵与Kapur算法相结合作为自适应函数来改进BFOA算法,通过改进的BFOA算法计算舌体图像的最佳图像二值化阈值,并将舌体图像二值化;然后,利用舌体图像的对称性提取舌体的关键边缘点,并基于B-样条插值算法由关键点集合插值得到闭合的B-样条曲线,作为Snake模型的初始轮廓;最后,通过Snake模型计算求解,即可准确提取舌体的轮廓曲线。实验结果表明,改进算法能够高精度地分割出舌体图像,并能消除基本Snake模型在初始轮廓曲线选取中存在的人机交互难题,实现了舌体图像的自动分割。

Geometric Properties of Ribs and Fans of a Bézier Curve

Ribs and fans are interesting geometric entities that are derived from a given Bézier curve or surface based on the recent theory of rib and fan decomposition. In this paper, we present some of new geometric properties of ribs and fans for a Bézier curve including composite fans, rib-invariant deformation, and fan-continuity in subdivision. We also give some examples for the presented properties.

2m次贝塞尔曲线降一次逼近及误差分析

在计算机图形学、计算机辅助几何设计、计算机辅助制造和计算机辅助设计领域中 ,贝塞尔曲线降次逼近是一个基本而重要的课题 ,它在减少系统数据存储量、增加系统稳定性和提高计算效率等方面有着重要应用。通过对 2 m次平面参数贝塞尔曲线降一次逼近问题的分析研究 ,给出了用 2 m- 1次贝塞尔曲线逼近 2 m次贝塞尔曲线的“封闭”的计算公式 ,推广了文献 [1]中给出的降一次逼近时的误差估计公式 ,并得到了“封闭”的形式。为 CAD系统的用户和计算机图形学、计算机辅助几何设计、计算机辅助制造和计算机辅助设计领域的研究人员使用计算逼近曲线控制顶点和逼近误差的封闭形式提供了方便。而且对于事先给定的容许误差 ,利用文中的方法 ,借助于贝塞尔曲线离散分割算法可以很容易求出满足要求的逼近曲线。

基于矢量的纹织图像缩放算法

在对纹织图像进行缩放处理时,图像放大过程中会出现边缘马赛克效应,严重地增加了工作人员的负担。为了解决此问题,本文提出了基于矢量的纹织图像缩放算法。首先采用填充法提取图像的轮廓边缘,然后以直线拟合和曲线拟合相结合的方法得到控制点,并根据缩放的要求改变控制点的坐标。最后依据新的控制点通过拟合得到缩放后的图像。

Optimized Design of H-Type Vertical Axis Wind Airfoil at Multiple Angles of Attack

Numerical simulations are conducted to improve the energy acquisition efficiency of H-type vertical axis wind turbines through the optimization of the related blade airfoil aerodynamic performance.The Bézier curve is initi-ally used tofit the curve profile of a NACA2412 airfoil,and the moving asymptote algorithm is then exploited to optimize the design of the considered H-type vertical-axis wind-turbine blade airfoil for a certain attack angle.The results show that the maximum lift coefficient of the optimized airfoil is 8.33%higher than that of the original airfoil.The maximum lift-to-drag ratio of the optimized airfoil exceeds the maximum lift-to-drag ratio of the ori-ginal airfoil by 11.22%.Moreover,the power coefficient is increased by 12.19%and the torque coefficient of the wind turbine is significantly improved.

Path planning for agricultural robots in wild livestock farm environments

Path planning for field agricultural robots must satisfy several criteria:establishing feeding routes,maintaining gentle slopes,approaching multiple livestock observation points,ensuring timely environmental monitoring,and achieving high efficiency.The complex terrain of outdoor farming areas poses a challenge.Traditional A*algorithms,which generate only the shortest path,fail to meet these requirements and often produce paths that lack smoothness.Therefore,identifying the most suitable path,rather than merely the shortest one,is essential.This study introduced a path-planning algorithm tailored to field-based livestock farming environments,building upon the traditional A*algorithm.It constructed a digital elevation model,integrated an artificial potential field for evaluating multiple target points,calculated terrain slope,optimized the search neighborhood based on robot traversability,and employed Bézier curve segmentation for path optimization.This method segmented the path into multiple curves by evaluating the slopes of the lines connecting adjacent nodes,ensuring a smoother and more efficient route.The experimental results demonstrate its superiority to traditional A^(*),ensuring paths near multiple target points,significantly reducing the search space,and resulting in over 69.4%faster search speeds.Bézier curve segmentation delivers smoother paths conforming to robot trajectories.

Nonlinear Weighted Average and Blossoming

In this paper,we introduce a new averaging rule,the nonlinear weighted averaging rule.As an application,this averaging rule is used to replace the midpoint averaging in the de Casteljau evaluation algorithm and with this scheme we can also generate transcendental functions which cannot be generated by the classical de Casteljau algorithm.We also investigate the properties of the curves of the functions generated by blossoming,where the results show that these curves and the classical Bézier curves have some similar properties,including variation diminishing property and endpoint interpolation.However,the curves obtained by blossoming using nonlinear weighted averaging rules induced by certain functions violate some properties like convex hull property.

图像无级平滑缩放算法研究

在大幅面激光加工中,需要对原始图像进行缩放处理,但当图像放大时会出现马赛克的边缘效应。为解决这个问题,根据矢量在缩放过程中保持特征不变性的特点,以二值图像为例,提出一种行之有效的图像平滑无级缩放算法。该算法过程为:对原始图像进行边界提取;利用Hough变换提取边界的拐点;判别拐点间线的类型并计算控制点;对边界控制点进行缩放运算并拟合边界线;利用活性边表填充算法填充区域。利用该算法能很好地解决图像缩放所带来的边缘效应,方法简单有效,并在大幅面激光加工中取得了良好的应用。