概率神经网络在超谱图像分类中的应用 |
| |
引用本文: | 董延华,;白文秀,;张钧萍.概率神经网络在超谱图像分类中的应用[J].长春邮电学院学报,2008(2):122-125. |
| |
作者姓名: | 董延华 ;白文秀 ;张钧萍 |
| |
作者单位: | [1]吉林师范大学计算机学院,吉林四平136000; [2]哈尔滨工业大学电子信息与通信工程系,黑龙江哈尔滨150001 |
| |
基金项目: | 基金项目:国家自然科学基金资助项臼(60302019) |
| |
摘 要: | 针对超谱图像高维光谱信息给传统分类带来的困难,结合径向基神经网络的原理,提出了一种概率神经网络分类方法。并将其成功应用到具体超谱图像数据中,验证了概率神经网络分类器的有效性。通过实验仿真,研究了特征向量维数对分类结果的影响,证明概率神经网络可应用于大于100个波段的超谱图像数据。
|
关 键 词: | 概率神经网络 超谱图像分类 特征矢晕维数 |
Research on Application of Probability Neural Network in Hyperspetral Image Classification |
| |
Affiliation: | DONG Yan-hua1,2, BAI Wen-xiu1, ZHANG Jun-ping2( 1. College of Computer, Jilin Normal University, Siping 136000, China; 2. Department of Electronics and Communieation Engineering, Harbin Industrial Technology University, Harbin 150001, China) |
| |
Abstract: | Aiming at based on the theory of method is illustrated, tion. research on the the difficulty of traditional classification brought by hyperspectral image's high dimension, radical basis function network, a kind of PNN (Probability Neural Network) classification and its affectivity is verified by its application in hyperspectral image. Through the emula-effect of feature image's dimensions to classification result, proves the PNN's applicability high dimension hyperspectral image. |
| |
Keywords: | probability neural network (PNN) hyperspetral image classification feature image's dimensions |
本文献已被 维普 等数据库收录! |
|