中文摘要：

针对现有基于速度特征的笔画分割方法对匀速绘制笔画过度分割的问题,提出一种创新性的基于速度特征的笔画分割方法。首先对笔画进行折线化预处理,从而将笔画的采样点进行数据压缩得到能反映笔画的折点序列;为了提高用户的绘制自由度,按照输入笔速的不同将笔画分为常速笔画和准匀速笔画,并按其特征的不同,给出相应的速度特征提取算法。对于前者给出了基于三线阈值的速度特征提取算法,后者则先采用基于＂滤波-锐化处理＂的方法将准匀速笔画转化为常速笔画,再通过常速笔画的速度特征提取算法得到其速度特征点,并针对笔画特征的模糊性提出以点段形式表示准匀速笔画的速度特征。最后通过自主开发的FSR_SS系统对上述算法加以验证,并给出其他算法与本文算法结果的比较分析。实验结果表明,基于速度特征的笔画分割方法能实时进行在线手绘笔画分割,为后期手绘图的识别研究奠定了基础。

英文摘要：

We describe a new method for segmenting non-single stroke to 2D geometric primitives using velocity features; these primitives are further interpreted as 2D line drawings. This method can support rapid segmenting and fitting of non-single stroke using velocity features extracted during stroke-inputting stage. A stroke processing method using polygonal approximation is used for online stroke compression. In order to reduce the user＇s drawing limitation,we divide the stroke into common speed stroke and uncommon one according to such information as speed,sampling points and length of stroke. For common speed stroke,an extraction algorithm of velocity feature is presented using three threshold values ： velocity and its upper deviation and lower one. For uncommon speed stroke,firstly it is transformed into the common one with the proposed filter-sharpness processing; then velocity features are extracted based on the feature extraction method of common stroke; finally,according to the fuzziness of velocity feature,dot segments represent the speed features of uncommon speed stroke. Finally,a combination method of primitives is introduced to eliminate over-segmentation. The proposed method has been tested with our FSR_SS online freehand sketch recognition system; FSR_SS is robust and easier to use by removing some limitations embedded with most existing sketching systems which only accept single stroke drawing. The test results show that the proposed method can support freehand sketching based conceptual design without limitations on drawing sequence and directions while still achieving a satisfactory segmentation rate.