Similarity learning for object recognition based on derived kernel
文献类型：期刊论文
| 作者 | Li, Hong4; Wei, Yantao3; Li, Luoqing2; Yuan, Yuan1
|
| 刊名 | neurocomputing
 |
| 出版日期 | 2012-04-15 |
| 卷号 | 83页码:110-120 |
| 关键词 | Derived kernel Hierarchical learning Image similarity Neural response Object recognition Template selection |
| ISSN号 | 0925-2312 |
| 产权排序 | 4 |
| 合作状况 | 国内 |
| 中文摘要 | recently, derived kernel method which is a hierarchical learning method and leads to an effective similarity measure has been proposed by smale. it can be used in a variety of application domains such as object recognition, text categorization and classification of genomic data. the templates involved in the construction of the derived kernel play an important role. to learn more effective similarity measure, a new template selection method is proposed in this paper. in this method, the redundancy is reduced and the label information of the training images is used. in this way, the proposed method can obtain compact template sets with better discrimination ability. experiments on four standard databases show that the derived kernel based on the proposed method achieves high accuracy with low computational complexity. |
| 英文摘要 | recently, derived kernel method which is a hierarchical learning method and leads to an effective similarity measure has been proposed by smale. it can be used in a variety of application domains such as object recognition, text categorization and classification of genomic data. the templates involved in the construction of the derived kernel play an important role. to learn more effective similarity measure, a new template selection method is proposed in this paper. in this method, the redundancy is reduced and the label information of the training images is used. in this way, the proposed method can obtain compact template sets with better discrimination ability. experiments on four standard databases show that the derived kernel based on the proposed method achieves high accuracy with low computational complexity. (c) 2012 elsevier b.v. all rights reserved. |
| WOS标题词 | science & technology ; technology |
| 学科主题 | computer science ; artificial intelligence |
| 类目[WOS] | computer science, artificial intelligence |
| 研究领域[WOS] | computer science |
| 关键词[WOS] | face recognition ; image similarity ; cortex ; decomposition ; distance ; features |
| 收录类别 | SCI ; EI |
| 语种 | 英语 |
| WOS记录号 | WOS:000301613800013 |
| 公开日期 | 2012-09-03 |
| 源URL | [http://ir.opt.ac.cn/handle/181661/20253]  |
| 专题 | 西安光学精密机械研究所_光学影像学习与分析中心 |
| 作者单位 | 1.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr OPT IMagery Anal & Learning OPTIMAL, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China 2.Hubei Univ, Fac Math & Comp Sci, Wuhan 430062, Peoples R China 3.Huazhong Univ Sci & Technol, Inst Pattern Recognit & Artificial Intelligence, Wuhan 430074, Peoples R China 4.Huazhong Univ Sci & Technol, Sch Math & Stat, Wuhan 430074, Peoples R China |
| 推荐引用方式 GB/T 7714 | Li, Hong,Wei, Yantao,Li, Luoqing,et al. Similarity learning for object recognition based on derived kernel[J]. neurocomputing,2012,83:110-120. |
| APA | Li, Hong,Wei, Yantao,Li, Luoqing,&Yuan, Yuan.(2012).Similarity learning for object recognition based on derived kernel.neurocomputing,83,110-120. |
| MLA | Li, Hong,et al."Similarity learning for object recognition based on derived kernel".neurocomputing 83(2012):110-120. |
入库方式： OAI收割
来源：西安光学精密机械研究所
浏览0
下载0
收藏0
其他版本
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。