基于神经网络的边缘强度互相关匹配可信度分析

桑 农; 张天序; 曹治国

doi:10.11834/jig.20000708

学术论文与技术报告 | 浏览量 : 0 下载量: 150 CSCD: 0

PDF
导出
分享
收藏
专辑

基于神经网络的边缘强度互相关匹配可信度分析
Matching Confidence Analysis Based on Neural Network forEdge Magnitude Cross Correlation
2000年5卷第7期页码：580
纸质出版：2000
DOI： 10.11834/jig.20000708
稿件说明：

移动端阅览

桑农, 张天序, 曹治国. 基于神经网络的边缘强度互相关匹配可信度分析[J]. 中国图象图形学报, 2000,5(7):580. DOI： 10.11834/jig.20000708.

Matching Confidence Analysis Based on Neural Network forEdge Magnitude Cross Correlation[J]. Journal of Image and Graphics, 2000, 5(7): 580. DOI： 10.11834/jig.20000708.

摘要

匹配可信度是分析图象匹配质量的主要指标.针对归一化边缘强度互相关匹配算法

研究了基于神经网络的匹配可信度判别方法

即以参考图与若干实时图的匹配实验结果作为训练用样本数据

然后利用BP网络进行训练

再将训练后的网络用于匹配可信度的判别.通过实际卫片与航片图象对的匹配实验

证实了该方法的有效性.

Abstract

Matching confidence is an important measure to analyses the quality of image matching. For normalized edge magnitude cross correlation matching algorithm

the measure of matching confidence based on neural network is studied. The training samples used to train a BP network are the matching results with the reference image and several sensed images. The trained network can be adopted to measure matching confidence. Experimetal results with real satellite images and aerial images prove the effectiveness of the method.