| 基于神经网络的形状识别系统及优化 |
| |
| 引用本文： | 高隽. 基于神经网络的形状识别系统及优化[J]. 系统工程与电子技术, 1999, 0(3) |
| |
| 作者姓名： | 高隽 |
| |
| 作者单位： | 合肥工业大学计算机与信息系!230009(高隽，张维勇，蒋建国)，中国科学技术大学计算机科学与技术系!合肥230027(曹先彬，王煦法) |
| |
| 基金项目： | 国家自然科学基金!（编号：69805001） |
| |
| 摘 要： | Ｈｏｕｇｈ变换用于形状识别、神经网络用于分类都不是新课题，而我们将这两种方法结合起来，用神经网络实现 Ｈｏｕｇｈ变换并进行特征提取，所提取的特征矢量不受待识别体的大小和位置的影响，且所提特征为一维矢量。对于所构成的神经网络形状识别系统，采用ＢＰ算法进行初１练，优化系统参数。文中最后得出令人满意的实验结果。
|
| 关 键 词： | 网络 形状识别 优化 |
| 修稿时间： | 1998-03-29 |
The Shape Recognition System Based on Neural Networks and Its Optimization |
| |
| Gao Jun,Zhang Weiyong and Jiang Jianguo. The Shape Recognition System Based on Neural Networks and Its Optimization[J]. System Engineering and Electronics, 1999, 0(3) |
| |
| Authors: | Gao Jun Zhang Weiyong Jiang Jianguo |
| |
| Abstract: | It is not a new thing to use Hough transform in shape recognition or neural networks in classification. In this paper, combining the two methods together, we use the neural networks to realize the Hough transform and feature extraction. The feature extraction is an 1-D vector and is not affected by the sizes and positions of extracting objects. With the help of the shape recognition systems of constructed neural networks, a very good experiment re- sult is obtained by using the BP algorithm to carry out studying, training and optimizing system parameters. |
| |
| Keywords: | Hough transformation Neural networks Shape recognition BP. |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
