Background of shape contexts for point matching
文献类型：期刊论文
| 作者 | Qian, Deheng1 ; Chen, Tianshi2,3; Qiao, Hong3,4
|
| 刊名 | PATTERN RECOGNITION LETTERS
 |
| 出版日期 | 2016-12-01 |
| 卷号 | 84期号:无页码:114-119 |
| 关键词 | Point matching Shape context Local feature |
| 通讯作者 | Qiao, Hong |
| 英文摘要 | Point matching seeks the optimal correspondences between two sets of points. It is often tackled via assigning each point a set of features and minimizing the dissimilarities of corresponded features. In this process, a kind of widely applied features is the Shape Contexts (SC). Given a reference point, SC exploits the relative positions between this point and the remaining points. However, SC omits the relative positions among the remaining points, which limits its distinctiveness. In this paper, we propose a new kind of features, called the Background of Shape Contexts (BSC), which encodes not only these relative positions between the reference point and the remaining points, but also those among the remaining points. The BSC concisely presents the relative positions among feature points by edges among the points. The distribution of edges is then calculated in a Coordinate-Gradient Space (CGS). The CGS is a combination of a gradient space and a Euclidean space which can be 2D or 3D. Finally, the BSC exploits histograms to capture the distribution of edges in the CGS. We evaluate the BSC on multiple matching experiments over widely used datasets and demonstrate the effectiveness of the BSC. (C) 2016 Elsevier B. V. All rights reserved. |
| WOS标题词 | Science & Technology ; Technology |
| 类目[WOS] | Computer Science, Artificial Intelligence |
| 研究领域[WOS] | Computer Science |
| 关键词[WOS] | PATTERN-RECOGNITION ; EM ALGORITHM ; GRAPH ; DISTANCE ; COMPUTATION ; CONSTRAINTS ; HISTOGRAMS |
| 收录类别 | SCI |
| 语种 | 英语 |
| WOS记录号 | WOS:000390660900017 |
| 源URL | [http://ir.ia.ac.cn/handle/173211/12614]  |
| 专题 | 自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组 |
| 作者单位 | 1.Samsung Res Inst China Beijing SRC B, Beijing 100028, Peoples R China 2.Chinese Acad Sci, State Key Lab Comp Architecture, Inst Comp Technol, Beijing 100190, Peoples R China 3.Chinese Acad Sci, Ctr Excellence Brain Sci & Intelligence Technol, Shanghai 200031, Peoples R China 4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100190, Peoples R China |
| 推荐引用方式 GB/T 7714 | Qian, Deheng,Chen, Tianshi,Qiao, Hong. Background of shape contexts for point matching[J]. PATTERN RECOGNITION LETTERS,2016,84(无):114-119. |
| APA | Qian, Deheng,Chen, Tianshi,&Qiao, Hong.(2016).Background of shape contexts for point matching.PATTERN RECOGNITION LETTERS,84(无),114-119. |
| MLA | Qian, Deheng,et al."Background of shape contexts for point matching".PATTERN RECOGNITION LETTERS 84.无(2016):114-119. |
入库方式： OAI收割
来源：自动化研究所
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。