Presentation 2016-11-30
Keypoint Detection based on Learning to Rank for Robust Image Matching under Resolution Variation
Satoshi Yoshikawa, Keisuke Kameyama,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) The image matching by keypoint selection from images is used in various situations in computer vision. Among them, Scale-Invariant Feature Transform (SIFT), has been widely used for the feature extraction. However, when the resolutions of the matchedimages differ, solving keypoint correspondences becomedifficult. In this work, we propose a method to detectkeypoints that are robust to scale changes. Based onRankSIFT by Li et al., Gaussian Scale Space (GSS) andscale features of each feature point are used to estimatetheir robustness against scaling. In addition, we proposed the method that predict the stability of keypoints by regression, and compared with the previous method based on RankSIFT. The proposed method proved to be effective in finding a small set of points that persist through scaling.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Keypoint Detection / Image Matching / SIFT
Paper # CPM2016-85,ICD2016-46,IE2016-80
Date of Issue 2016-11-22 (CPM, ICD, IE)

Conference Information
Committee VLD / DC / CPSY / RECONF / CPM / ICD / IE
Conference Date 2016/11/28(3days)
Place (in Japanese) (See Japanese page)
Place (in English) Ritsumeikan University, Osaka Ibaraki Campus
Topics (in Japanese) (See Japanese page)
Topics (in English) Design Gaia 2016 -New Field of VLSI Design-
Chair Takashi Takenana(NEC) / Michiko Inoue(NAIST) / Yasuhiko Nakashima(NAIST) / Minoru Watanabe(Shizuoka Univ.) / Satoru Noge(Numazu National College of Tech.) / Minoru Fujishima(Hiroshima Univ.) / Seishi Takamura(NTT)
Vice Chair Hiroyuki Ochi(Ritsumeikan Univ.) / Satoshi Fukumoto(Tokyo Metropolitan Univ.) / Koji Nakano(Hiroshima Univ.) / Hidetsugu Irie(Univ. of Tokyo) / Masato Motomura(Hokkaido Univ.) / Yuichiro Shibata(Nagasaki Univ.) / Fumihiko Hirose(Yamagata Univ.) / Hideto Hidaka(Renesas) / Takayuki Hamamoto(Tokyo Univ. of Science) / Atsuro Ichigaya(NHK)
Secretary Hiroyuki Ochi(Fujitsu Labs.) / Satoshi Fukumoto(Hiroshima City Univ.) / Koji Nakano(Kyoto Sangyo Univ.) / Hidetsugu Irie(Tokyo Inst. of Tech.) / Masato Motomura(Fujitsu Labs.) / Yuichiro Shibata(NII) / Fumihiko Hirose(Univ. of Tsukuba) / Hideto Hidaka(Hiroshima City Univ.) / Takayuki Hamamoto(NTT) / Atsuro Ichigaya(Nihon Univ.)
Assistant Parizy Matthieu(Fujitsu Labs.) / / Takeshi Ohkawa(Utsunomiya Univ.) / Shinya Takameda(NAIST) / Takefumi Miyoshi(e-trees.Japan) / Yuuki Kobayashi(NEC) / Takashi Sakamoto(NTT) / Yuichi Nakamura(Toyohashi Univ. of Tech.) / Takashi Hashimoto(Panasonic) / Masanori Natsui(Tohoku Univ.) / Hiroyuki Ito(Tokyo Inst. of Tech.) / Pham Konkuha(Univ. of Electro-Comm.) / Kei Kawamura(KDDI R&D Labs.) / Keita Takahashi(Nagoya Univ.)

Paper Information
Registration To Technical Committee on VLSI Design Technologies / Technical Committee on Dependable Computing / Technical Committee on Computer Systems / Technical Committee on Reconfigurable Systems / Technical Committee on Component Parts and Materials / Technical Committee on Integrated Circuits and Devices / Technical Committee on Image Engineering
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Keypoint Detection based on Learning to Rank for Robust Image Matching under Resolution Variation
Sub Title (in English)
Keyword(1) Keypoint Detection
Keyword(2) Image Matching
Keyword(3) SIFT
1st Author's Name Satoshi Yoshikawa
1st Author's Affiliation University of Tsukuba(Univ. of Tsukuba)
2nd Author's Name Keisuke Kameyama
2nd Author's Affiliation University of Tsukuba(Univ. of Tsukuba)
Date 2016-11-30
Paper # CPM2016-85,ICD2016-46,IE2016-80
Volume (vol) vol.116
Number (no) CPM-333,ICD-334,IE-335
Page pp.pp.45-50(CPM), pp.45-50(ICD), pp.45-50(IE),
#Pages 6
Date of Issue 2016-11-22 (CPM, ICD, IE)