摘要
针对具有层次结构的图形符号的手绘输入在线识别提出了一种新方法 ,该方法使用模糊联想记忆 (FAM )方法来实现分类器 .提出了一种ID3方法的模糊规则提取以及优化算法 ,并用于训练FAM分类器 .实验结果表明 。
In this article, we present a novel approach for online hand-sketched graphics symbol recognition based on fuzzy associativc memory (FAM) classifier. An Interactive Dichotomizer 3 (ID3) method is adoped to produce fuzzy decision trees from training set. The optimization of decision trees is also discussed to obtain the computation efficiency. Experimental results show that the proposed method has a significantly high recognition rate and robustness.
出处
《兰州交通大学学报》
CAS
2001年第6期7-10,共4页
Journal of Lanzhou Jiaotong University
基金
国家自然科学基金"自适应手绘图形识别技术研究"(批准号 60 173 0 67)
关键词
人机并互
图形识别
模糊联想记忆
Human Machine Interaction
Graphics recognition
Fuzzy associative memory
