Presentation 2014-07-01
Registration between scenery images of the past and present by using Self-similarity descriptor
Naoya OKADA, Jun IMURA, Takuji NARUMI, Tomohiro TANIKAWA, Michitaka HIROSE,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) As for registration between two images, various methods have been proposed in accordance with the target images. However, if you target landscape images of the past and present, it is difficult to automatically correspond the images due to the large changes in the imaging conditions, and it takes operation costs for manual correspondence by visual inspection. Therefore, we propose a semi-automatic registration method and automatize the corresponding parts, applying Self-similarity feature descriptor in consideration of geometric structure and a matching method based on SIFT flow, to the regions a user selected in advance. As a result of comparison with the conventional method, our method can reduce 60% of the work time of registration and the effectiveness of our method was shown.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) digital museum / image matching / registration / Self-similarity descriptor / SSim flow
Paper # MVE2014-18
Date of Issue

Conference Information
Committee MVE
Conference Date 2014/6/24(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Registration between scenery images of the past and present by using Self-similarity descriptor
Sub Title (in English)
Keyword(1) digital museum
Keyword(2) image matching
Keyword(3) registration
Keyword(4) Self-similarity descriptor
Keyword(5) SSim flow
1st Author's Name Naoya OKADA
1st Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo()
2nd Author's Name Jun IMURA
2nd Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
3rd Author's Name Takuji NARUMI
3rd Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
4th Author's Name Tomohiro TANIKAWA
4th Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
5th Author's Name Michitaka HIROSE
5th Author's Affiliation Graduate School of Information Science and Technology, The University of Tokyo
Date 2014-07-01
Paper # MVE2014-18
Volume (vol) vol.114
Number (no) 114
Page pp.pp.-
#Pages 6
Date of Issue