Exploring Local and Overall Ordinal Information for Robust Feature Description
文献类型:期刊论文
作者 | Zhenhua Wang1; Bin Fan1![]() ![]() |
刊名 | IEEE Transactions on Pattern Analysis and Machine Intelligence
![]() |
出版日期 | 2016 |
卷号 | 38期号:11页码:2198-2211 |
关键词 | Feature Description Intensity Order Illumination Invariance Image Matching |
英文摘要 | This paper aims to build robust feature descriptors by exploring intensity order information in a patch. To this end, the local intensity order pattern (LIOP) and the overall intensity order pattern (OIOP) are proposed to effectively encode intensity order information of each pixel in different aspects. Specifically, LIOP captures the local ordinal information by using the intensity relationships among all the neighbouring sampling points around a pixel, while OIOP exploits the coarsely quantized overall intensity order of these sampling points. These two kinds of patterns are then separately aggregated into different ordinal bins, leading to two kinds of feature descriptors. Furthermore, as these two kinds of descriptors could encode complementary ordinal information, they are combined together to obtain a discriminative and compact mixed intensity order pattern descriptor. All these descriptors are constructed on the basis of relative relationships of intensities in a rotationally invariant way, making them be inherently invariant to image rotation and any monotonic intensity changes. Experimental results on image matching and object recognition are encouraging, demonstrating the superiorities of our descriptors over the state of the art. |
源URL | [http://ir.ia.ac.cn/handle/173211/19696] ![]() |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Bin Fan |
作者单位 | 1.National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences 2.National University of Singapore |
推荐引用方式 GB/T 7714 | Zhenhua Wang,Bin Fan,Gang Wang,et al. Exploring Local and Overall Ordinal Information for Robust Feature Description[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2016,38(11):2198-2211. |
APA | Zhenhua Wang,Bin Fan,Gang Wang,&Fuchao Wu.(2016).Exploring Local and Overall Ordinal Information for Robust Feature Description.IEEE Transactions on Pattern Analysis and Machine Intelligence,38(11),2198-2211. |
MLA | Zhenhua Wang,et al."Exploring Local and Overall Ordinal Information for Robust Feature Description".IEEE Transactions on Pattern Analysis and Machine Intelligence 38.11(2016):2198-2211. |
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。