Presentation 2018-06-16
Anomaly Detection for Pointing out Mistaken Folding in Origami
Hiroshi Shimanuki, Toyohide Watanabe, Koichi Asakura, Hideki Sato,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We have developed a system that detects the location of origami paper from single camera images and supports foldings in real-time. This paper proposes an approach to appropriately point out the user's mistaken folding. First, a method of detecting the mistakes by using the progress of the folding and the distance between the user's origami shape and the correct shape is described. However, in this system, shadows and occlusion caused by user's hands frequently occur, so it is not possible to obtain the accurate shape of origami paper in the all time. Therefore, an anomaly detection problem among shape variation of origami paper observed as time series data is solved based on machine learning. The effectiveness of the proposed method is demonstrated by experiments using a one-class support vector machine (one-class SVM).
Keyword(in Japanese) (See Japanese page)
Keyword(in English) computer-aided origami / single camera image / anomaly detection / mistaken folding / one-class SVM
Paper # ET2018-13
Date of Issue 2018-06-09 (ET)

Conference Information
Committee ET
Conference Date 2018/6/16(1days)
Place (in Japanese) (See Japanese page)
Place (in English) Nanzan University
Topics (in Japanese) (See Japanese page)
Topics (in English) Adbanced Exercise Support, etc.
Chair Yozo Miyadera(Tokyo Gakugei Univ.)
Vice Chair Ryo Takaoka(Yamaguchi Univ.)
Secretary Ryo Takaoka(Open Univ. of Japan)
Assistant Megumi Kurayama(National Inst. of Tech., Hakodate College) / Masaru Okamoto(Hiroshima City Univ.)

Paper Information
Registration To Technical Committee on Educational Technology
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Anomaly Detection for Pointing out Mistaken Folding in Origami
Sub Title (in English)
Keyword(1) computer-aided origami
Keyword(2) single camera image
Keyword(3) anomaly detection
Keyword(4) mistaken folding
Keyword(5) one-class SVM
1st Author's Name Hiroshi Shimanuki
1st Author's Affiliation *(*)
2nd Author's Name Toyohide Watanabe
2nd Author's Affiliation Nagoya Industrial Science Research Institute(NISRI)
3rd Author's Name Koichi Asakura
3rd Author's Affiliation Daido University(Daido Univ.)
4th Author's Name Hideki Sato
4th Author's Affiliation Daido University(Daido Univ.)
Date 2018-06-16
Paper # ET2018-13
Volume (vol) vol.118
Number (no) ET-98
Page pp.pp.7-11(ET),
#Pages 5
Date of Issue 2018-06-09 (ET)