小型微型计算机系统
小型微型計算機繫統
소형미형계산궤계통
MINI-MICRO SYSTEMS
2010年
2期
363-368
,共6页
图像检索%相关反馈%半监督学习%支持向量机%流形正则化
圖像檢索%相關反饋%半鑑督學習%支持嚮量機%流形正則化
도상검색%상관반궤%반감독학습%지지향량궤%류형정칙화
image retrieval%relevance feedback%semi-supervised learning%support vector machine%manifold regularization
在基于反馈的图像检索中,由于被用户标记为相关和不相关的图像数较少,使得检索问题变成了一个典型的小样本问题.流形可表达数据在低维空间中的内在几何结构,流形正则化的目的是利用这种几何结构来约束解空间,以使最优解能反映数据本身的几何分布.为了解决反馈检索中的小样本问题,本文在流形正则化框架下提出一个新的半监督图像检索算法.在新算法中,流形正则化项只依赖于文中定义的查询子流形,而不依赖于数据集的全局结构.在两个图像集上的实验结果对比表明,本文提出的新算法在检索效果上优于现有的4种state-of-the-art算法.
在基于反饋的圖像檢索中,由于被用戶標記為相關和不相關的圖像數較少,使得檢索問題變成瞭一箇典型的小樣本問題.流形可錶達數據在低維空間中的內在幾何結構,流形正則化的目的是利用這種幾何結構來約束解空間,以使最優解能反映數據本身的幾何分佈.為瞭解決反饋檢索中的小樣本問題,本文在流形正則化框架下提齣一箇新的半鑑督圖像檢索算法.在新算法中,流形正則化項隻依賴于文中定義的查詢子流形,而不依賴于數據集的全跼結構.在兩箇圖像集上的實驗結果對比錶明,本文提齣的新算法在檢索效果上優于現有的4種state-of-the-art算法.
재기우반궤적도상검색중,유우피용호표기위상관화불상관적도상수교소,사득검색문제변성료일개전형적소양본문제.류형가표체수거재저유공간중적내재궤하결구,류형정칙화적목적시이용저충궤하결구래약속해공간,이사최우해능반영수거본신적궤하분포.위료해결반궤검색중적소양본문제,본문재류형정칙화광가하제출일개신적반감독도상검색산법.재신산법중,류형정칙화항지의뢰우문중정의적사순자류형,이불의뢰우수거집적전국결구.재량개도상집상적실험결과대비표명,본문제출적신산법재검색효과상우우현유적4충state-of-the-art산법.
Under the circumstance of the relevance-feedback-based image retrieval,the quantity of relevant and irrelevant images la-beled by user is very few leading to a canonical small-size sample problem.The intrinsic structure of such image data usually appears in the manifold form in lower-dimension space,thus the goal of the manifold-regularization is to utilize the structure to make the opti-mal solution able to reflect the distribution geometry of the data.With the aim to solving such small-size sample problem,a new semi-supervised image retrieval algorithm is proposed in this paper,which based on the manifoid-regularization framework.In the proposed algorithm,the term of manifold-regularization only depends on the query submanifold rather than the global structure of the whole data set.The experimental results on two image databases indicate that such new retrieval algorithm is more effective than four current state-of-the-art algorithms.
