基于智能像卡输入的手绘电气符号特征提取方法研究

Study of Feature Extraction Approach for Hand-Drawn Electronic Component Symbol Based on Input with Smart Image Card

提出了一种特定输入方式下脱机手绘电气符号的特征提取方法。采用一种新的书写载体和图像采样装置。在分析了以智能像卡输入的手绘电气符号的结构特点的基础上,给出了扩展网格构造方法,定义了扩展网格的比较特征,将其应用于手绘电气符号的特征提取。所提取的特征具备对不同书写笔画不规则变形的适应能力,有效地反映了手绘电气符号的局部和全局特征。识别实验表明,该特征提取方法是有效的。

A new feature extraction method for off-line hand-drawn electronic component symbols inputted in special way is presented. Both a new writing carder and a sampling equipment are used. Based on analyzing the structure characteristic of hand-drawn electronic component symbols, an expandable meshing construction method is given, and the comparative features based on expandable meshing are defined. This feature extraction method possesses adaptability of variations of strokes in different handwritings. Experiment of recognition shows that the proposed approach is both effective and efficient.