WEKO3
アイテム
A Feature Descriptor by Difference of Polynomials
https://ipsj.ixsq.nii.ac.jp/records/94703
https://ipsj.ixsq.nii.ac.jp/records/94703efc75d3d-66fa-49f6-824b-6bf52b6963e9
名前 / ファイル | ライセンス | アクション |
---|---|---|
![]() |
Copyright (c) 2013 by the Information Processing Society of Japan
|
|
オープンアクセス |
Item type | Trans(1) | |||||||
---|---|---|---|---|---|---|---|---|
公開日 | 2013-07-29 | |||||||
タイトル | ||||||||
タイトル | A Feature Descriptor by Difference of Polynomials | |||||||
タイトル | ||||||||
言語 | en | |||||||
タイトル | A Feature Descriptor by Difference of Polynomials | |||||||
言語 | ||||||||
言語 | eng | |||||||
キーワード | ||||||||
主題Scheme | Other | |||||||
主題 | [Regular Paper - Express Paper] image feature, feature descriptor, polynomial modeling | |||||||
資源タイプ | ||||||||
資源タイプ識別子 | http://purl.org/coar/resource_type/c_6501 | |||||||
資源タイプ | journal article | |||||||
著者所属 | ||||||||
IIS, U-Tokyo | ||||||||
著者所属 | ||||||||
BROTHER INDUSTRIES, LTD. | ||||||||
著者所属 | ||||||||
NAIST | ||||||||
著者所属 | ||||||||
IIS, U-Tokyo | ||||||||
著者所属(英) | ||||||||
en | ||||||||
IIS, U-Tokyo | ||||||||
著者所属(英) | ||||||||
en | ||||||||
BROTHER INDUSTRIES, LTD. | ||||||||
著者所属(英) | ||||||||
en | ||||||||
NAIST | ||||||||
著者所属(英) | ||||||||
en | ||||||||
IIS, U-Tokyo | ||||||||
著者名 |
Bo, Zheng
Yongqi, Sun
Jun, Takamatsu
Katsushi, Ikeuchi
× Bo, Zheng Yongqi, Sun Jun, Takamatsu Katsushi, Ikeuchi
|
|||||||
著者名(英) |
Bo, Zheng
Yongqi, Sun
Jun, Takamatsu
Katsushi, Ikeuchi
× Bo, Zheng Yongqi, Sun Jun, Takamatsu Katsushi, Ikeuchi
|
|||||||
論文抄録 | ||||||||
内容記述タイプ | Other | |||||||
内容記述 | In this paper, we propose a novel local image descriptor DoP which is termed as the difference of images represented by polynomials in different degrees. Once an interest point/region is extracted by a common image detector such as Harris corner, our DoP descriptor is able to characterize the interest point/region with high distinctiveness, compactness, and robustness to viewpoint change, image blur, and illumination variation. To efficiently build DoP descriptor, we propose to numerically reduce the computational cost by jumping over the repeatedly calculating polynomial representation. Our experimental results demonstrate a better performance compared to several state-of-art candidates. | |||||||
論文抄録(英) | ||||||||
内容記述タイプ | Other | |||||||
内容記述 | In this paper, we propose a novel local image descriptor DoP which is termed as the difference of images represented by polynomials in different degrees. Once an interest point/region is extracted by a common image detector such as Harris corner, our DoP descriptor is able to characterize the interest point/region with high distinctiveness, compactness, and robustness to viewpoint change, image blur, and illumination variation. To efficiently build DoP descriptor, we propose to numerically reduce the computational cost by jumping over the repeatedly calculating polynomial representation. Our experimental results demonstrate a better performance compared to several state-of-art candidates. | |||||||
書誌情報 |
IPSJ Transactions on Computer Vision and Applications (CVA) 巻 5, p. 80-84, 発行日 2013-07-29 |
|||||||
ISSN | ||||||||
収録物識別子タイプ | ISSN | |||||||
収録物識別子 | 1882-6695 | |||||||
出版者 | ||||||||
言語 | ja | |||||||
出版者 | 情報処理学会 |