基于时空关系的在线多笔划手绘直线段识别

综合考虑笔划的时空关系对在线多笔划手绘直线段进行识别。基于时间关系进行多笔划预处理;详细讨论基于空间关系的多笔划绘制直线段的识别方法。提出利用两条笔划拟合直线段间的位置关系进行多笔划判定的方法;提出依据其原有拟合特征的多笔划直线段拟合方法及相应的首尾点确定方法;并给出带线型直线段的完整定义。通过算例对提出的算法加以验证和应用。     

基于时空关系的在线多笔画手绘二次曲线识别

综合考虑笔画时空关系对在线多笔画手绘二次曲线进行识别。先对笔画识别结果进行基于时间间断的多笔画预处理将其识别为虚线或实线,然后详细讨论基于空间关系的多笔画手绘二次曲线的识别问题。将基于空间关系的二次曲线多笔画识别分为封闭二次曲线和非封闭二次曲线的多笔画识别,对前者给出采用最小中值二乘的多笔画拟合二次曲线方法。针对非封闭二次曲线提出广义笔画及其对应的旋转角和首尾点的概念,并从多笔画判定、草图生成、旋转角和首尾点的确定这3方面给出其多笔画识别方法。最后通过自主开发的FSR系统对文中算法加以验证。     

基于笔画容差带的手绘草图间断多笔画判定与拟合方法

在手绘草图的过程中经常会出现单一线元间断绘制的问题,为了将间断的笔画修整为单一线元以获得规范的设计图,提出了一种基于笔画容差带的手绘草图间断多笔画判定与拟合方法。该方法对输入的笔画进行折线化处理,得到笔画逼近折线段的折点序列,并判断笔画类型;根据笔画走势,绘制假想笔画以及扩展的笔画容差带,判定两笔画是否属于间断多笔画;聚类间断绘制多笔画,将笔画序列转换成子草图序列,并对子草图逐一进行拟合,从而得到规范的几何线元,这为实现由草图到规范设计图的识别提供了基础。     

在线多笔画重复绘制草图的判定与聚类

多笔画重复绘制是设计师传递设计意图的常用方式,为在手绘图识别系统中支持多笔画重复绘制,提出一种将在线多笔画重复绘制草图解释为二维线图的判定与聚类算法.首先通过笔画逼近折线段的折点序列,构造一个带圆弧过渡的等距边线围成的多边形区域作为笔画容差带;然后利用2条笔画之中最小包络矩形面积较小的笔画的采样点落入另一条笔画的容差带的个数,进行多笔画重复绘制的快速判定;最后提出将草图分成若干个子草图的聚类算法,根据子草图中笔画的单笔画识别结果将子草图分为同类型子草图和混合类型子草图,并给出相应的子草图拟合方法.通过自主开发的FSR_DJ原型系统对文中算法加以验证的结果表明,该算法能有效地解决多笔画重复绘制草图的识别问题,为后期手绘图的识别研究奠定了基础.     

基于几何特征的在线手绘草图分割

针对现有基于几何特征的笔画分割方法的不足,提出一种将笔画分为可识别基本几何线元的组合的笔画分割方法.首先将笔画的采样点进行基于折线化逼近的数据压缩,得到反映笔画特征的折点序列.其次依据折点的方向将笔画分为凸笔画和凹笔画,对于凸笔画给出了其分割点提取原则——将笔画分割成跨度最大的几条子笔画的组合,并给出了相应的提取算法;而凹笔画的几何特征提取方法是先将其进行凸化处理,将凹笔画分割成几个凸笔画的组合,然后通过凸笔画的分割点提取算法得到凹笔画的分割点;在进行凹笔画的凸化处理时提出了单位长度内所跨折点数最大的分割原则及算法.最后采用单一线元合并方法对误分割点进行修正处理.通过自主开发的FSR_JS原型系统对上述算法进行验证,并给出了笔画分割点修正前,后的比较分析,结果表明,本文方法能有效地解决在线手绘笔画的分割问题,通过分割点的修正可有效地提高分割正确率,为后期手绘图的识别研究及三维重构奠定了基础.     

基于贝叶斯网络的在线草图识别算法

针对手绘草图识别算法大多采用限制用户绘制习惯来实现笔画分组的问题,提出一种基于贝叶斯网络的手绘草图识别算法。该算法将手绘草图识别中的笔画分组和符号识别统一为一个过程,用贝叶斯网络拓扑结构来表达草图结构信息。基于该网络,根据最大后验概率对连续输入的笔画进行动态最优分组,同时在线预测每组笔画的符号类别。实验结果表明,该方法是一种有效的在线递进式笔画分组和识别算法,在电路符号手绘识别中达到71.3%的过程识别率和85%的最终识别率。     

手绘运动学机构示意图识别及运动过程模拟

目的 为了解决手绘运动学示意图对辅助学习的局限性,以及现有物理辅助教学软件只能模拟系统设定机构的局限性,提出了一种对手绘运动学机构示意图进行识别,并实现其运动过程模拟的方法。方法 首先提取笔画的几何特征进行笔画识别,得到笔画类型,然后根据构件笔画组成列表及笔画间相对关系,进行构件的匹配识别,再根据用户意图,识别构件间位置约束关系,自动矫正机构示意图中构件的相对位置,最后通过2维物理引擎,实现机构的运动过程模拟。结果 实现了对运动学教学中常见的16种构件的识别,和构件中常用的7种图元的识别,识别准确率分别为93.25%、94%。结论 实验结果表明,该方法可在对手写运动学构件符号以及构件间的约束关系进行正确的识别和矫正的基础上,实现对整个运动机构的识别,以及对机构运动过程的模拟。     

基于深度卷积-递归神经网络的手绘草图识别方法

针对现有基于深度学习的手绘草图识别方法直接从整体上提取手绘草图的图像特征,而忽略了草图中笔画的顺序信息的问题,利用手绘草图的笔画顺序信息,将深度卷积神经网络与递归神经网络相结合,提出一种基于深度卷积-递归神经网络的手绘草图识别方法.首先按照绘画草图时的笔画顺序提取笔画,生成多幅子笔画草图,并形成一个笔画数依次递增的子笔画草图序列;然后采用深度卷积神经网络依次提取该序列中每一幅子笔画草图的图像特征,并将提取的图像特征按照原先子笔画草图排列的顺序进行排序,作为递归神经网络的输入;最后利用递归神经网络来构建不同图像特征间的时序关系,以提高手绘草图的识别准确率.在现有最大的手绘草图数据集TU-Berlin Sketch数据集上的实验结果表明,文中方法能有效地提升手绘草图的识别准确率.     

基于手绘的三维建模系统的研究和实现*

研究基于手绘(sketch)的三维建模方法并实现相应的建模系统。通过对输入的手绘笔画(strokes)进行去噪、分段、识别等操作,将手绘笔画识别为直线、椭圆等基本图元,再根据图元之间的相应关系构建出三维模型,实现对用户输入意图的自动三维解释。实验结果表明,该方法能够对输入的strokes进行精确的分析处理,实现对输入手绘笔画的三维建模。     

基于几何特征的在线手绘流程图识别

为减少绘图设计软件繁琐的操作步骤,提出基于图元几何特征的在线手绘流程图识别方法.该方法首先识别用户笔画线元,对识别出的线元进行拟合并记录其属性信息,然后以流程图基本图形为单位,利用构成图元的笔画几何特征及笔画间的几何关系识别具体图形.整个识别过程简单、快捷、准确性较高,对用户绘图笔画顺序无要求,适用于不同用户的绘图习惯.     

New grouping and fitting methods for interactive overtraced sketches

This paper describes a new method for recognizing overtraced strokes to 2D geometric primitives, which are further interpreted as 2D line drawings. This method can support rapid grouping and fitting of overtraced polylines or conic curves based on the classified characteristics of each stroke during its preprocessing stage. The orientation and its endpoints of a classified stroke are used in the stroke grouping process. The grouped strokes are then fitted with 2D geometry. This method can deal with overtraced sketch strokes in both solid and dash linestyles, fit grouped polylines as a whole polyline and simply fit conic strokes without computing the direction of a stroke. It avoids losing joint information due to segmentation of a polyline into line-segments. The proposed method has been tested with our freehand sketch recognition system (FSR), which is robust and easier to use by removing some limitations embedded with most existing sketching systems which only accept non-overtraced stroke drawing. The test results showed that the proposed method can support freehand sketching based conceptual design with no limitations on drawing sequence, directions and overtraced cases while achieving a satisfactory interpretation rate.     

计算机辅助草绘设计技术研究

计算机辅助草绘技术结合了计算机与纸笔草绘的优点，比较适合于概念设计，便于帮助设计师快速记录下头脑中产生的瞬时灵感，近年来一直成为许多专家学者争相研究的热点课题之一。该文从产品设计的领域出发简要介绍了计算机辅助草绘设计的研究现状。并从支持草绘的用户界面设计、低层草图处理、高层草图语义理解、三维草绘建模4个方面分析比较了计算机辅助草绘一些关键技术的研究方法，指出了下一步的研究重点。     

计算机支持的智能草图技术研究及实现

首先论述了作为CAD技术当前研究前沿的计算机支持的智能草图技术研究现状。构建出智能草图的技术体系,包括基于单笔划的自然手势界面,徒手草图输入,草图识别与基于草图的几何建模。最后给出基于著名几何造型核心ACIS开发的智能草图工具原型系统ISID,它具有一个支持笔输入的用户界面,并能和典型的CAD系统实现集成。初步应用证明该系统具有很强的实用性和可扩展性。     

基于PUI界面的草图编辑软件

针对CAD系统在应用到概念设计时,由于传统的人机界面无法提供一个自然和高效的人机交互环境,导致CAD不能在概念设计领域中广泛被使用,对此提出了基于感知界面（PUI）思想,以手势命令取代传统人机界面的解决方法,并设计出基于．net平台的草图编辑系统。系统使用神经网络中的BP算法,完成计算机对用户输入的手势命令的识别,从而提高了草图编辑系统人机界面的人性化,并通过实例演示了部分系统功能,表明系统具有一定的实用价值。     

一种草图动画工具的设计与实现*

针对当前计算机在中小学课堂应用中采用静态幻灯片模式对学生缺乏吸引力、教学效率不高等不足,以及现有的动画制作工具对于大部分教师难以使用的问题,探讨了基于运动轨迹的动画制作方法、草图动画中的动作协调,以及形变算法在草图动画中的应用等问题,实现了一个草图动画制作工具。该草图动画制作工具支持平移、旋转、放缩等草图动画中常用的动作方式。基于运动轨迹的动画制作方法和简洁的用户界面使得设置动作像绘制物体一样简单。使用形变动画作为轨迹动画的补充方式,可制作出更加生动的动画。老师使用该工具可以快捷方便地制作出自己的动画。     

Tele-Graffiti: A Camera-Projector Based Remote Sketching System with Hand-Based User Interface and Automatic Session Summarization

One way to build a remote sketching system is to use a video camera to image what each user draws at their site, transmit the video to the other sites, and display it there using an LCD projector. Such camera-projector based remote sketching systems date back to Paul Wellner's (largely unimplemented) Xerox Double DigitalDesk. To make such a system usable, however, the users have to be able to move the paper on which they are drawing, they have to be able to interact with the system using a convenient interface, and sketching sessions must be stored in a compact format so that they can be replayed later. We have recently developed Tele-Graffiti, a remote sketching system with the following three features: (1) real-time paper tracking to allow the users to move their paper during system operation, (2) a hand based user interface, and (3) automatic session summarization and playback. In this paper, we describe the design, implementation, and performance of Tele-Graffiti.Supplementary material to this paper is available in electronic form at http://dx.doi.org/10.1023/A:1023084706295     

Sketch-based design for green geometry and image deformation

User interfaces have traditionally followed the WIMP (window, icon, menu, pointer) paradigm. Though functional and powerful, they are usually cumbersome for a novice user to design a complex model, requiring considerable expertise and effort. This paper presents a system for designing geometric models and image deformation with sketching curves, with the use of Green coordinates. In 3D modeling, the user first creates a 3D model by using a sketching interface, where a given 2D curve is interpreted as the projection of the 3D curve. The user can add, remove, and deform these control curves easily, as if working with a 2D line drawing. For a given set of curves, the system automatically identifies the topology and face embedding by applying graph rotation system. Green coordinates are then used to deform the generated models with detail-preserving property. Also, we have developed a sketch-based image-editing interface to deform image regions using Green coordinates. Hardware-assisted schemes are provided for both control shape deformation and the subsequent surface optimization, the experimental results demonstrate that 3D/2D deformations can be achieved in realtime.     

Polyline approach for approximating Hausdorff distance between planar free-form curves

This paper presents a practical polyline approach for approximating the Hausdorff distance between planar free-form curves. After the input curves are approximated with polylines using the recursively splitting method, the precise Hausdorff distance between polylines is computed as the approximation of the Hausdorff distance between free-form curves, and the error of the approximation is controllable. The computation of the Hausdorff distance between polylines is based on an incremental algorithm that computes the directed Hausdorff distance from a line segment to a polyline. Furthermore, not every segment on polylines contributes to the final Hausdorff distance. Based on the bound properties of the Hausdorff distance and the continuity of polylines, two pruning strategies are applied in order to prune useless segments. The R-Tree structure is employed as well to accelerate the pruning process. We experimented on Bezier curves, B-Spline curves and NURBS curves respectively with our algorithm, and there are 95% segments pruned on approximating polylines in average. Two comparisons are also presented: One is with an algorithm computing the directed Hausdorff distance on polylines by building Voronoi diagram of segments. The other comparison is with equation solving and pruning methods for computing the Hausdorff distance between free-form curves.