摘要
提出了一种半监督线性近邻传递的相关反馈方法FSLNP(feedback semi-supervised linear neighborhood propagation).该算法不仅能够保持正、负例约束信息,而且能够保持图的局部以及全局相关性结构信息.采用相关反馈的有标签和未知标签图像点,找到比较好的表示图像相关性的一个图结构,来揭示图像点的语义间结构关系.实验结果表明:该算法可以提高检索的准确度,而且在经过长期学习后可以获得一个优化相关性的图结构.
A feedback semi-supervised linear neighborhood propagation method（FSLNP） is proposed.FSLNP method can not only preserve the positive and negative constraints but also preserve the local and global relevance structure information of the whole graph.With both labeled and unlabeled images in relevance feedbacks,a better structure for relevance representation among images is found to reveal the semantic structure.Experimental results show that FSLNP can effectively improve retrieval accuracy,and after long term learning,an optimal relevance graph space can be obtained.
出处
《信息与控制》
CSCD
北大核心
2011年第3期289-295,共7页
Information and Control
基金
国家自然科学基金资助项目(60873151
60973098
90820306)
关键词
相关反馈
半监督学习
图像检索
线性近邻传递
relevance feedback
semi-supervised learning
image retrieval
linear neighborhood propagation
