Part of the book series:Communications in Computer and Information Science ((CCIS,volume 1405))
Included in the following conference series:
639Accesses
Abstract
In April 2016, a severe earthquake occurred in Kumamoto, Japan. That damaged ISHIGAKI of Kumamoto castle and caused a large amount of stone to fall. We have developed support systems that use ICT and we have also investigated a method of extracting stone contour information. In our previous research, we have been improving GrabCut to try to automate stone contour extraction. However, in some cases, over-segmentation or under-segmentation occurred. In the paper, we dealed with this problem. From the observation results, it is considered that the stone shape has a convex polygonal shape to some extent. We set restrict regions for background-likely characteristics using a convex hull of a pre-extraction result by GrabCut close to the original iteratively. Convex hull fitness is a criterion to evaluate whether it is a convex polygon. In addition, the error with GT is calculated. From the results, the following can be considered. That with a small convex hull fitness value tended to have a small error with GT.
The A-STEP from Japan Science and Technology Agency, JST.
This is a preview of subscription content,log in via an institution to check access.
Access this chapter
Subscribe and save
- Get 10 units per month
- Download Article/Chapter or eBook
- 1 Unit = 1 Article or 1 Chapter
- Cancel anytime
Buy Now
- Chapter
- JPY 3498
- Price includes VAT (Japan)
- eBook
- JPY 5719
- Price includes VAT (Japan)
- Softcover Book
- JPY 7149
- Price includes VAT (Japan)
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Miyazawa, A., Koutaki, G.: Retrieval system for stones of Kumamoto Castle using ISHIGAKI marker. In: The 62nd Annual Conference of the Institute of Systems Proceedings (2018)
Toda, M., Inoue, K., Koutaki, G., Kishigami, T.: Extraction method of stone contour for support of ISHIGAKI retrieval on Kumamoto Castle. IEEJ Trans. Electron. Inf. Syst. (2018)
Yamasaki, Y., Masahiro, M., Koutaki, G., Toda, M., Kishigami, T.: A research on Kumamoto Castle ISHIGAKI region extraction using stone features and shape evaluation. In: PRMU2020 (2020)
Rother, C., Kolmogorv, V., Blake, A.: GrabCut: Interactive foreground extraction using iterated graph cuts. ACM Trans. Graph.23(3), 309–314 (2004)
Author information
Authors and Affiliations
Kumamoto University, 2-39-1 Kurokami, Chuo-ku, Kumamoto, Japan
Yuuki Yamasaki, Masahiro Migita, Go Koutaki & Masashi Toda
Toppan Printing CO., LTD., 1, KandaIzumi-cho, Chiyoda-ku, Tokyo, Japan
Tsuyoshi Kishigami
- Yuuki Yamasaki
You can also search for this author inPubMed Google Scholar
- Masahiro Migita
You can also search for this author inPubMed Google Scholar
- Go Koutaki
You can also search for this author inPubMed Google Scholar
- Masashi Toda
You can also search for this author inPubMed Google Scholar
- Tsuyoshi Kishigami
You can also search for this author inPubMed Google Scholar
Corresponding authors
Correspondence toYuuki Yamasaki,Masahiro Migita,Go Koutaki,Masashi Toda orTsuyoshi Kishigami.
Editor information
Editors and Affiliations
Chonnam National University, Gwangju, Korea (Republic of)
Hieyong Jeong
Aoyama Gakuin University, Kanagawa, Japan
Kazuhiko Sumi
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Yamasaki, Y., Migita, M., Koutaki, G., Toda, M., Kishigami, T. (2021). ISHIGAKI Region Extraction Using Grabcut Algorithm for Support of Kumamoto Castle Reconstruction. In: Jeong, H., Sumi, K. (eds) Frontiers of Computer Vision. IW-FCV 2021. Communications in Computer and Information Science, vol 1405. Springer, Cham. https://doi.org/10.1007/978-3-030-81638-4_9
Download citation
Published:
Publisher Name:Springer, Cham
Print ISBN:978-3-030-81637-7
Online ISBN:978-3-030-81638-4
eBook Packages:Computer ScienceComputer Science (R0)
Share this paper
Anyone you share the following link with will be able to read this content:
Sorry, a shareable link is not currently available for this article.
Provided by the Springer Nature SharedIt content-sharing initiative