%0 Journal Article
%T Kernel optimization approach based on maximumsubclass margin criterion<br>最大子分类间隔准则的核函数优化
%A Zhang Jing
%A Yang Zhiyong
%A Yu Hongyun
%A Sun Xiaoyan
%A <br>张静
%A 杨智勇
%A 于红芸
%A 孙晓燕
%J 中国图象图形学报
%D 2012
%I 
%X In order to deal with the kernel optimization, a new kernel data-dependent optimizaition kernel approach based on maximum subclass margin criterion is proposed. In this scheme, a maximum subclass margin function is created firstly. Then, the in-between-subclass and inter-subclass scatter matrix in the empirical feature space are defined. Finally, the optimal coefficients vector is solved by the selected optimization criterion. Experimental results based on UCI data show that it is effective and feasible.
%K kernel function
%K kernel optimization
%K maximum subclass margin criterion
%K target recognition<br>核函数
%K 核优化
%K 最大子分类间隔准则
%K 目标识别
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=D06194629680C940ACE75262F54B9D85&aid=DC0994A58AFB6AE9FB120441A03BD548&yid=99E9153A83D4CB11&vid=BCA2697F357F2001&iid=59906B3B2830C2C5&sid=AEA8CA70A6C58E24&eid=6F185A924223F19E&journal_id=1006-8961&journal_name=中国图象图形学报&referenced_num=0&reference_num=17