Exploring Local and Overall Ordinal Information for Robust Feature Description
Zhenhua Wang1; Bin Fan1; Gang Wang2; Fuchao Wu1
2016
发表期刊IEEE Transactions on Pattern Analysis and Machine Intelligence
卷号38期号:11页码:2198-2211
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.
关键词Feature Description Intensity Order Illumination Invariance Image Matching
收录类别SCI
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/19696
专题模式识别国家重点实验室_先进数据分析与学习
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.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
PAMI-2016-2-intensit(1911KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
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
[Zhenhua Wang]的文章
[Bin Fan]的文章
[Gang Wang]的文章
百度学术
百度学术中相似的文章
[Zhenhua Wang]的文章
[Bin Fan]的文章
[Gang Wang]的文章
必应学术
必应学术中相似的文章
[Zhenhua Wang]的文章
[Bin Fan]的文章
[Gang Wang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: PAMI-2016-2-intensity_order_pami_paper.pdf
格式: Adobe PDF
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。