基于自适应HMM的在线草图识别方法

On-Line Sketchy Graphic Recognition Based on Adaptive HMM

用户适应性是在线手绘草图识别的一个关键问题。本文以实现草图识别的自适应性为目标,对草图识别中的用户适应性问题进行了深入的研究和实验,提出了一种自适应草图识别解决方法,并针对在线草图识别的特点,提出了一种基于笔划曲率,速率以及整体几何特性的组合特征。本文重点研究并实现了基于自适应HMM的草图识别,在已有HMM的基础上,针对在线草图识别的特点,提出了状态数可变自适应HMM的学习方法。实验表明本文所提出的方法具有很好的效果。

User adaptation is a crux for on-line sketchy graphic recognition. The purpose of this paper is to make a comprehensive discuss about some critical issues of user adaptation in on-line sketch recognition supporting normal graphics design, we also hope to make some achievements in adaptive ouline sketch recognition. A method of on-line sketchy graphics recognition for user adaptation is proposed in this paper. We make a preparatory research on selec- tion mechanism of feature descriptor and propose a combined feature based on curvature, velocity and geometrical character of stroke. We make some improvement in traditional HMM and propose an adaptive HMM based on vari- able state number for the purpose of description of multi-stroke sketch. Experiments prove the proposed method both effective and efficient.