| 基于粒子群优化神经网络的移动机器人门牌识别方法研究 |
| |
| 引用本文： | 郭健,莫国梁,陈庆伟. 基于粒子群优化神经网络的移动机器人门牌识别方法研究[J]. 计算机与数字工程, 2009, 37(4): 7-9 |
| |
| 作者姓名： | 郭健 莫国梁 陈庆伟 |
| |
| 作者单位： | 南京理工大学自动化学院,南京,210094 |
| |
| 摘 要： | 针对移动机器人门牌识别问题，提出了一种基于粗分类与细分类相结合的门牌识别方法。首先利用门牌号码字符的特殊节点进行粗分类，进而计算图像的不变矩；在此基础上，利用粒子群神经网络进行细分类，完成门牌识别。最后通过办公室环境中的门牌号码识别实验验证了该方法的快速性与有效性。
|
| 关 键 词： | 移动机器人 门牌识别 粒子群 神经网络 不变矩 |
Research on Door Number Recognition Techniques Based on PSO-NN for Mobile Robot |
| |
| Guo Jian,Mo Guoliang,Chen Qingwei. Research on Door Number Recognition Techniques Based on PSO-NN for Mobile Robot[J]. Computer and Digital Engineering, 2009, 37(4): 7-9 |
| |
| Authors: | Guo Jian Mo Guoliang Chen Qingwei |
| |
| Affiliation: | Automation School;Nanjing University of Science and Technology;Nanjing 210094 |
| |
| Abstract: | A method which combines rough classification with precise classification for door number recognition is present to solve the mobile robot door recognition problem.Characters' special node is used to realize the rough classification.And the moment invariants of the image is calculated.Then neural network based on particle swarm optimization is designed to realize precise classification.Experiments in office environment show that the method is efficient. |
| |
| Keywords: | mobile robot door number recognition PSO （particle swarm optimization） NN（neural networks） moment invariants |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
