Feature vector field and feature matching
Wu, F. C.; Wang, Z. H.; Wang, X. G.
发表期刊PATTERN RECOGNITION
2010-10-01
卷号43期号:10页码:3273-3281
文章类型Article
摘要In this paper, we propose a feature vector field for images, which is built by the inner products and exterior products of image gradients. The feature vector field effectively represents image edges and feature points including corners and edge points with big curvature. Using the feature vector field, some novel descriptors are constructed for point matching and curve matching. The descriptors are all invariant to image Euclidean transformations and linear intensity changes. The experiments show that the descriptors also have a good adaptability to small image affine transformation, JPEG compression and nonlinear changes of intensity. (C) 2010 Elsevier Ltd. All rights reserved.
关键词Inner Product Exterior Product Feature Matching Feature Descriptor
WOS标题词Science & Technology ; Technology
关键词[WOS]OBJECT RECOGNITION ; INVARIANT ; DETECTORS ; IMAGES ; SCALE
收录类别SCI
语种英语
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
WOS记录号WOS:000280006700008
引用统计
被引频次:10[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/2956
专题多模态人工智能系统全国重点实验室_机器人视觉
作者单位Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
第一作者单位模式识别国家重点实验室
推荐引用方式
GB/T 7714
Wu, F. C.,Wang, Z. H.,Wang, X. G.. Feature vector field and feature matching[J]. PATTERN RECOGNITION,2010,43(10):3273-3281.
APA Wu, F. C.,Wang, Z. H.,&Wang, X. G..(2010).Feature vector field and feature matching.PATTERN RECOGNITION,43(10),3273-3281.
MLA Wu, F. C.,et al."Feature vector field and feature matching".PATTERN RECOGNITION 43.10(2010):3273-3281.
条目包含的文件
条目无相关文件。
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Wu, F. C.]的文章
[Wang, Z. H.]的文章
[Wang, X. G.]的文章
百度学术
百度学术中相似的文章
[Wu, F. C.]的文章
[Wang, Z. H.]的文章
[Wang, X. G.]的文章
必应学术
必应学术中相似的文章
[Wu, F. C.]的文章
[Wang, Z. H.]的文章
[Wang, X. G.]的文章
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

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。