| LBAM神经网络及其在图像识别中的应用 |
| |
| 引用本文： | 沈定刚,戚飞虎.LBAM神经网络及其在图像识别中的应用[J].上海交通大学学报,1994,28(3):58-63. |
| |
| 作者姓名： | 沈定刚 戚飞虎 |
| |
| 基金项目： | 国家攀登计划认知科学（神经网络）重大关键项目 |
| |
| 摘 要： | 本文提出了一种用于图像识别的神经网络。它由映射网络ＭＮ和ＬＢＡＭ网络组成。ＭＮ中使用了不变性换法，降低了图像样本的维数肯保持分类距离不变。在设计ＬＢＡＭ网络时，通过全局考虑，使得网络的吸引点和吸引区域满足实际全局最优之需要。ＬＢＡＭ具有网络结构简单和收敛速度快的优点，计算机模拟证实，此网络具有对缺损和噪声图像进行正确识别的能力。
|
| 关 键 词： | 图像识别 神经网络 不变性变换 |
Liked-Bam Neural Network for Image Recognition |
| |
| Shen Dinggang, Qi Feihu.Liked-Bam Neural Network for Image Recognition[J].Journal of Shanghai Jiaotong University,1994,28(3):58-63. |
| |
| Authors: | Shen Dinggang Qi Feihu |
| |
| Institution: | Shen Dinggang; Qi Feihu |
| |
| Abstract: | A neural network model and its application to image recognition are proposed in this paper. This model consists of Mapping Network (MN) and Liked Bidirectional Associative Memory (LBAM). Invariant mapping is used in MN in order to decrease the number of dimensions of image samples and not to change the distance between them. LBAM'S structure is simple and its convergence speed is fast. Several computer simulations given to prove that the model is capable of recognizing the corrupted targets and the incomplete targets. |
| |
| Keywords: | image recognition LBAM neural network invariant mapping |
| 本文献已被 CNKI 维普 等数据库收录！ |
