典型文献
Robust discriminative broad learning system for hy-perspectral image classification
文献摘要：
With the advantages of simple structure and fast training speed,broad learning system(BLS)has attracted attention in hyperspectral images(HSIs).However,BLS cannot make good use of the discriminative information contained in HSI,which limits the classification performance of BLS.In this paper,we propose a robust discriminative broad learning system(RDBLS).For the HSI classification,RDBLS introduces the total scatter matrix to construct a new loss function to participate in the training of BLS,and at the same time minimizes the feature distance within a class and maximizes the feature distance between classes,so as to improve the discriminative ability of BLS features.RDBLS inherits the advantages of the BLS,and to a certain extent,it solves the problem of insufficient learning in the limited HSI samples.The classification results of RDBLS are verified on three HSI datasets and are superior to other comparison methods.
文献关键词：
中图分类号：
作者姓名：
ZHAO Liauo;HAN Zhe;LUO Yona
作者机构：
School of Computer and Information Engineering,Luoyang Institute of Science and Technology,Luoyang 471023,China;Guizhou Cloud Big Data Industry Development Co.,Ltd.,Guiyang 550001,China
文献出处：
引用格式：
[1]ZHAO Liauo;HAN Zhe;LUO Yona-.Robust discriminative broad learning system for hy-perspectral image classification)[J].光电子快报（英文版）,2022(07):444-448
A类：
perspectral,HSIs,RDBLS
B类：
Robust,discriminative,broad,learning,system,classification,With,advantages,simple,structure,fast,training,speed,has,attracted,attention,hyperspectral,images,However,cannot,make,good,use,information,contained,which,limits,performance,In,this,paper,propose,robust,For,introduces,total,scatter,matrix,construct,new,loss,function,participate,same,minimizes,distance,within,maximizes,between,classes,improve,ability,features,inherits,certain,extent,solves,problem,insufficient,limited,samples,results,are,verified,three,datasets,superior,other,comparison,methods
AB值：
0.491381
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
