| 用RCR特征和NN识别实时手绘工程草图 |
| |
| 引用本文： | 刘伟,查建中,徐晓慧,鄂明成.用RCR特征和NN识别实时手绘工程草图[J].计算机辅助设计与图形学学报,2003,15(6):692-696. |
| |
| 作者姓名： | 刘伟 查建中 徐晓慧 鄂明成 |
| |
| 作者单位： | 1. 北方交通大学机械与电子控制学院,北京,100044
2. 清华大学精密仪器与机械学系,北京,100084 |
| |
| 摘 要： | 针对实时手绘工程草图(简称手绘草图)的识别，引入草图重心、重径距和正规化重径(RCR)等图形特征概念，提出手绘草图的神经网识别方法．该方法以图素具有统计意义的正规化重径作为特征、以图素交叉方式组织正规化重径的值作为学习样本，应用弹力传播的Rprop算法训练BP神经网，一次训练即可得到能够识别任意倾角和位置手绘草图图素的识别器．从而达到了理想的识别效果．
|
| 关 键 词： | RCR特征 NN识别 实时手绘工程草图 BP神经网 图素识别 |
| 修稿时间： | 2002年3月12日 |
Identifying Real-Time Hand-Sketched Engineering Drawing by Using RCR and NN |
| |
| Liu Wei,Cha Jianzhong,Xu Xiaohui,E Mingcheng.Identifying Real-Time Hand-Sketched Engineering Drawing by Using RCR and NN[J].Journal of Computer-Aided Design & Computer Graphics,2003,15(6):692-696. |
| |
| Authors: | Liu Wei Cha Jianzhong Xu Xiaohui E Mingcheng |
| |
| Affiliation: | Liu Wei 1) Cha Jianzhong 1) Xu Xiaohui 2) E Mingcheng 1) 1) |
| |
| Abstract: | This paper introduced several new concepts such as sketch's centroid,centroid radii and regularized centroid radii (RCR), and proposed a hand sketch neural network recognizer to distinguish 4 types of strokes, namely line segment, circle, half circle, and quarter circle The approach constructed a hand sketch classifier through extracting the sketch primitives' RCR as features,crossing the four primitives' RCR values as the learning samples of BP neural network, then using the resilient propagation (Rprop) training algorithm trained the BP Experiments demonstrate that not only the classifier can recognize the hand sketched primitives of arbitrary directions and positions, but also its abilities of anti noising and identifying are robust,and the identifying rate is high Furthermore,the classifier needn't be trained again in application |
| |
| Keywords: | regularized centroid radii (RCR) real time free hand engineering sketch primitive recognition hand sketch classifier BP neural network feature extraction conceptual design |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
