文章基本信息

标题：Comparative Researches on Probabilistic Neural Networks and Multi-layer Perceptron Networks for Remote Sensing Image Segmentation
本地全文：下载
作者：Liu Gang
期刊名称：ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
印刷版ISSN：2194-9042
电子版ISSN：2194-9050
出版年度：2009
卷号：XXXVIII-7/C4
页码：25-29
出版社：Copernicus Publications
摘要：Image segmentation is one of the most important methods for extracting information of interest from remote sensing image data, but it still remains some problems, leading to low quality segmentation. The research focuses on image segmentation based on PNNs and MLPNs. It presents to construct a PNN model and tunes a satisfied PNN for hyper-spectral image segmentation. Furthermore, the paper gives a comparative study on segmentation methods based on PNNs and MLPNs. It is concluded that PNNs have quick speed of learning and training. The main advantage of a PNN is its ability to output probabilities in pattern recognition. Image segmentation based on PNNs is an effective and efficient method in image analysis, it obtains a bit higher segmentation overall accuracy than MLPNs
关键词：Remote sensing; Segmentation; Probabilistic Neural Networks (PNNs); Multi-Layer Perception Networks (MLPNs)