AdaBoost neural network based classification for optical remote sensing image

摘要：

Artificial neural network (ANN) model based classification approach has been widely used in remote sensing applications. An improvement to ANN is using ensemble scheme to reduce over-fitting. In this paper, a ensemble neural network - Adaboost NN classifier is used to classify six bands Landsat TM images. Comparison with standard NN classifier shows the AdaBoost NN performs better in both visualization inspection and quantitative evaluation.

关键词： neural network AdaBoost remote sensing classification

作者: ZHANG Denghui MAO Shengyi YU Le

作者单位: College of Information and Technology Zhejiang Shuren University Hangzhou,China Guangzhou Institute of Geochemistry Chinese Academy of Sciences Guangzhou,China Department of Earth Sciences Zhejiang University Hangzhou,China

会议类型: 国际会议

会议名称: 2010 International Conference on Circuit and Signal Processing(2010年电路与信号处理国际会议 ICCSP 2010)

会议地点: 上海

会议语种:英文

页码: 202-204

在线出版日期: 2010-12-25（万方平台首次上网日期，不代表论文的发表时间）