High-level verification of multi-object segmentation

Martin Lukac; Almas Zhurtanov; Aizhan Ospanova

doi:10.1109/DT.2016.7557169

High-level verification of multi-object segmentation

Martin Lukac, Almas Zhurtanov, Aizhan Ospanova

Department of Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

In this paper we present a relational analysis and verification of multi-labeled images as a result fo semantic segmentation. In semantic segmentation the result is a set of labeled regions but rarely this result is subject to verification that would allow to determine induce the reliability of this segmentation. We show that using shape measure, co-occurrence statistics and specially crafted weighted function we can estimate the correctness of a semantic segmentation up to 92%.

Original language	English
Title of host publication	IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	173-179
Number of pages	7
ISBN (Electronic)	9781467388603
DOIs	https://doi.org/10.1109/DT.2016.7557169
Publication status	Published - Aug 31 2016
Event	2016 International Conference on Information and Digital Technologies, IDT 2016 - Rzeszow, Poland Duration: Jul 5 2016 → Jul 7 2016

Other

Other	2016 International Conference on Information and Digital Technologies, IDT 2016
Country	Poland
City	Rzeszow
Period	7/5/16 → 7/7/16

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications
Signal Processing

Access to Document

10.1109/DT.2016.7557169

Fingerprint Dive into the research topics of 'High-level verification of multi-object segmentation'. Together they form a unique fingerprint.

Cite this

High-level verification of multi-object segmentation. / Lukac, Martin; Zhurtanov, Almas; Ospanova, Aizhan.

IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 173-179 7557169.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Lukac, M, Zhurtanov, A & Ospanova, A 2016, High-level verification of multi-object segmentation. in IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016., 7557169, Institute of Electrical and Electronics Engineers Inc., pp. 173-179, 2016 International Conference on Information and Digital Technologies, IDT 2016, Rzeszow, Poland, 7/5/16. https://doi.org/10.1109/DT.2016.7557169

@inproceedings{5edb139dcacd455892e26e60b51fac2b,

title = "High-level verification of multi-object segmentation",

abstract = "In this paper we present a relational analysis and verification of multi-labeled images as a result fo semantic segmentation. In semantic segmentation the result is a set of labeled regions but rarely this result is subject to verification that would allow to determine induce the reliability of this segmentation. We show that using shape measure, co-occurrence statistics and specially crafted weighted function we can estimate the correctness of a semantic segmentation up to 92%.",

author = "Martin Lukac and Almas Zhurtanov and Aizhan Ospanova",

year = "2016",

month = aug,

day = "31",

doi = "10.1109/DT.2016.7557169",

language = "English",

pages = "173--179",

booktitle = "IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

address = "United States",

note = "2016 International Conference on Information and Digital Technologies, IDT 2016 ; Conference date: 05-07-2016 Through 07-07-2016",

}

TY - GEN

T1 - High-level verification of multi-object segmentation

AU - Lukac, Martin

AU - Zhurtanov, Almas

AU - Ospanova, Aizhan

PY - 2016/8/31

Y1 - 2016/8/31

N2 - In this paper we present a relational analysis and verification of multi-labeled images as a result fo semantic segmentation. In semantic segmentation the result is a set of labeled regions but rarely this result is subject to verification that would allow to determine induce the reliability of this segmentation. We show that using shape measure, co-occurrence statistics and specially crafted weighted function we can estimate the correctness of a semantic segmentation up to 92%.

AB - In this paper we present a relational analysis and verification of multi-labeled images as a result fo semantic segmentation. In semantic segmentation the result is a set of labeled regions but rarely this result is subject to verification that would allow to determine induce the reliability of this segmentation. We show that using shape measure, co-occurrence statistics and specially crafted weighted function we can estimate the correctness of a semantic segmentation up to 92%.

UR - http://www.scopus.com/inward/record.url?scp=84988882851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84988882851&partnerID=8YFLogxK

U2 - 10.1109/DT.2016.7557169

DO - 10.1109/DT.2016.7557169

M3 - Conference contribution

AN - SCOPUS:84988882851

SP - 173

EP - 179

BT - IDT 2016 - Proceedings of the International Conference on Information and Digital Technologies 2016

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 2016 International Conference on Information and Digital Technologies, IDT 2016

Y2 - 5 July 2016 through 7 July 2016

ER -