%0 Journal Article
%T Image annotation based on AFSVM-MIL arithmetic<br>基于AFSVM-MIL算法的图像标注*
%A DENG Jian-xun
%A XIONG Zhong-yang
%A ZENG Dai-minb
%A <br>邓剑勋
%A 熊忠阳
%A 曾代敏b
%J 计算机应用研究
%D 2011
%I 
%X In most existing training data set,keywords are usually associated with images instead of regions.And not only supervised learning methods but also multi instance learning(MIL) methods need to associate Key words with regions.So this paper brought forward an improved MIL arithmetic(AFSVM-MIL),which based on active learning fuzzy support vector machine.Then image annotation problem became a supervised learning one in MIL framework.This method used AFSVM-MIL to classify the training datasets.And do generalize...
%K image annotation
%K multi-instance learning(MIL)
%K active learning fuzzy support vector machine(AFSVM)
%K generalized set operation<br>图像标注
%K 多示例学习
%K 自适应模糊支持向量机
%K 广义集合运算
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=1F8EB868F38CE072E872E185AC167A3E&yid=9377ED8094509821&vid=D3E34374A0D77D7F&iid=F3090AE9B60B7ED1&sid=94FAF819D4327D7D&eid=DE6D96EFF57B8D35&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=16