Publication detail

IMMI: Interactive Segmentation Toolkit

MAŠEK, J. BURGET, R. UHER, V.

Original Title

IMMI: Interactive Segmentation Toolkit

English Title

IMMI: Interactive Segmentation Toolkit

Type

conference paper

Language

en

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.

English 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

RIV year

2013

Released

15.09.2013

Publisher

Springer Berlin Heidelberg

Location

Heidelberg

ISBN

978-3-642-41012-3

Book

Engineering Applications of Neural Networks

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",
  annote="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.",
  address="Springer Berlin Heidelberg",
  booktitle="Engineering Applications of Neural Networks",
  chapter="101149",
  doi="10.1007/978-3-642-41013-0_39",
  howpublished="online",
  institution="Springer Berlin Heidelberg",
  number="24",
  year="2013",
  month="september",
  pages="380--387",
  publisher="Springer Berlin Heidelberg",
  type="conference paper"
}