Knowledge Commons of Institute of Automation,CAS
A novel CBIR system with WLLTSA and ULRGA | |
Feng, Lin; Liu, Shenglan; Xiao, Yao; Hong, Qiao; Wu, Bin; Feng, L | |
发表期刊 | NEUROCOMPUTING |
2015 | |
卷号 | 147期号:0页码:509-522 |
摘要 | At present, relevance feedback (RF) has been widely applied in content-based image retrieval (CBIR) system. Local Regression and Global Alignment (LRGA) is a novel ranking algorithm used in CBIR system which utilizes RE technique. However, there are some problems in LRGA: (1) for handling the problem of out-of-sample, dimension reduction is used after RF, but it is time-consuming; (2) feature space of images is often assumed to be linear. While, classical manifold learning methods are sensitive to the Gaussian bandwidth parameter of Laplacian matrix and cannot be combined with RF either. To address problems above, this paper proposes a novel CBIR system. Firstly, we calculate the local curvature parameter of manifold utilizing the angle information in subspace to avoid local high curvature problem and then we propose a Warp Linear Local Tangent Space Alignment (WLLTSA) algorithm; furthermore, we propose a U-Local Regression and Global Alignment (ULRGA) ranking algorithm to rank low-dimensional image features. Curvature parameter is used in both WLLTSA and ULRGA to enhance robustness. A large amount of experimental results demonstrate the efficiency of our CBIR system. (C) 2014 Elsevier B.V. All rights reserved. |
关键词 | Dimensionality Reduction Local Curvature Tangent Space Cbir Rf |
学科领域 | Computer Science |
文献类型 | 期刊论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/12587 |
专题 | 多模态人工智能系统全国重点实验室_机器人理论与应用 |
通讯作者 | Feng, L |
推荐引用方式 GB/T 7714 | Feng, Lin,Liu, Shenglan,Xiao, Yao,et al. A novel CBIR system with WLLTSA and ULRGA[J]. NEUROCOMPUTING,2015,147(0):509-522. |
APA | Feng, Lin,Liu, Shenglan,Xiao, Yao,Hong, Qiao,Wu, Bin,&Feng, L.(2015).A novel CBIR system with WLLTSA and ULRGA.NEUROCOMPUTING,147(0),509-522. |
MLA | Feng, Lin,et al."A novel CBIR system with WLLTSA and ULRGA".NEUROCOMPUTING 147.0(2015):509-522. |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论