| 用于图像与模式识别的小波神经网络模型 |
| |
| 引用本文： | 王阿明,刘天放,王绪.用于图像与模式识别的小波神经网络模型[J].中国矿业大学学报,2002,31(5):382-384,389. |
| |
| 作者姓名： | 王阿明 刘天放 王绪 |
| |
| 作者单位： | 1. 中国矿业大学,资源与地球科学学院,江苏,徐州,221008
2. 徐州医学院附属医院放射科,江苏,徐州,221002 |
| |
| 摘 要： | 研究了一种用于图像与模式识别的小波神经网络模型，给出了相应的算法和计算公式，并进行了仿真模拟，该模型克服了传统BP网络隐层单元数目难以确定，收敛速率较慢以及易于收敛到局部极小点等缺点，仿真结果表明网络性能和收敛速度均明显优于传统BP网络，具有良好的应用前景。
|
| 关 键 词： | 图像 小波变换 神经网络 模式识别 数据处理 仿真模拟 |
| 文章编号： | 1000-1964(2002)05-0382-04 |
Image and Pattern Recognition Using Wavelet Neural Networks |
| |
| WANG A\|ming ,LIU Tian\|fang ,WANG Xu.Image and Pattern Recognition Using Wavelet Neural Networks[J].Journal of China University of Mining & Technology,2002,31(5):382-384,389. |
| |
| Authors: | WANG A\|ming LIU Tian\|fang WANG Xu |
| |
| Affiliation: | WANG A\|ming 1,LIU Tian\|fang 1,WANG Xu 2 |
| |
| Abstract: | A wavelet neural network used in image and pattern recognition was studied. The algorithm and formulas were presented, and the simulated experiments were carried out. The result shows that this model can overcome the shortcomings of BP networks, such as the uncertain unit number of the hidden layer, the slowly learning rate, and easy to converge to the local minima. All these remarkable features enable the new model to be of good prospects in application. |
| |
| Keywords: | wavelet transform neural networks model pattern recognition |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
