| 基于多层神经网络的交叉线自动识别 |
| |
| 引用本文： | 曹爱军,史杏荣,孙贞寿,梅建华.基于多层神经网络的交叉线自动识别[J].中国图象图形学报,2000,5(2):149-152. |
| |
| 作者姓名： | 曹爱军 史杏荣 孙贞寿 梅建华 |
| |
| 作者单位： | 中国科学技术大学信息处理中心!合肥230027 |
| |
| 摘 要： | 神经网络是一个非线性动力学系统，在许多方面都表现出强大的生命力，特别为信息科学所瞩目。将图形信息输入计算机是ＣＡＤ、ＧＩＳ等应用系统中不可避免而又十分繁重的工作，人们一直在追求一种自动化的方法来解决这一问题。该文在深入分析Ｈｏｐｆｉｅｌｄ模型及多层神经网络的理论基础、学习算法的基础上，尝试使用神经网络的方法进行交叉线的自动识别，提出了一种全新的思路，并且用ＢＰ学习算法实现了这一思想。在实验模拟中，
|
| 关 键 词： | 多层神经网络 交叉线识别 计算机图形识别 |
| 收稿时间： | 1999/1/11 0:00:00 |
| 修稿时间： | 7/9/1999 12:00:00 AM |
Intersecting Lines Recognition Based on Multilayer Network |
| |
| CAO Ai-jun,SHI Xing-rong,SUN Zhen-shou and Mei Jian-hua.Intersecting Lines Recognition Based on Multilayer Network[J].Journal of Image and Graphics,2000,5(2):149-152. |
| |
| Authors: | CAO Ai-jun SHI Xing-rong SUN Zhen-shou and Mei Jian-hua |
| |
| Affiliation: | Information Processing Center,University of Science and Technology of China,Hefei 230027;Information Processing Center,University of Science and Technology of China,Hefei 230027;Information Processing Center,University of Science and Technology of China,Hefei 230027;Information Processing Center,University of Science and Technology of China,Hefei 230027 |
| |
| Abstract: | Neural Network is a non linear dynamics kinetics system, which can do a lot of complex jobs, especially in information science. Inputting image information into computers is an inevitable and troublesome job in many practical systems such as CAD and GIS, etc. An automatic method is needed badly. After analysing fundamental theories of Hopfield model and multi layered network, a new method to solve the problem realized by a BP algorithm is proposed. During experimental simulations,this algorithm really showed fine performance. |
| |
| Keywords: | Map recognition Multilayer network Intersecting lines recognition BP Algorithm |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
| 点击此处可从《中国图象图形学报》浏览原始摘要信息 |
|
点击此处可从《中国图象图形学报》下载免费的PDF全文 |
