Přístupnostní navigace
E-application
Search Search Close
Publication detail
MAŠEK, J. BURGET, R. UHER, V.
Original Title
IMMI: Interactive Segmentation Toolkit
Type
conference paper
Language
English
Original Abstract
General image segmentation is a non–trivial task, which requires significant computational power and huge amount of knowledge incorporated. Fortunately, it is not necessary in all the cases. In some specific cases, simpler non–supervised or supervised segmentation methods can be used giving even better results. In this paper, a novel trainable segmentation method based on RapidMiner data–mining platform is introduced, and its functionality is described. The method implementation was released under open–source license as a part of IMMI (IMage MIning) extension of the RapidMiner platform. When compared to other trainable segmentation algorithms, the platform provides flexibility connected with all the features of one of the most widely used data–mining platform today. The functionality has been verified on the satellite image use–case, accuracy achieving 78.3% pixel error.
Keywords
Classification, image segmentation, interactive tool, IMMI, RapidMiner
Authors
MAŠEK, J.; BURGET, R.; UHER, V.
RIV year
2013
Released
15. 9. 2013
Publisher
Springer Berlin Heidelberg
Location
Heidelberg
ISBN
978-3-642-41012-3
Book
Engineering Applications of Neural Networks
1865-0929
Periodical
Communications in Computer and Information Science
Year of study
383
Number
24
State
Federal Republic of Germany
Pages from
380
Pages to
387
Pages count
510
BibTex
@inproceedings{BUT101149, author="Jan {Mašek} and Radim {Burget} and Václav {Uher}", title="IMMI: Interactive Segmentation Toolkit", booktitle="Engineering Applications of Neural Networks", year="2013", journal="Communications in Computer and Information Science", volume="383", number="24", pages="380--387", publisher="Springer Berlin Heidelberg", address="Heidelberg", doi="10.1007/978-3-642-41013-0\{_}39", isbn="978-3-642-41012-3", issn="1865-0929" }