Reasoning and algorithm selection augmented symbolic segmentation

Michitaka Kameyama, Martin Lukac, Kamila Abdiyeva, Alexandra Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper an alternative method to symbolic segmentation is studied. Semantic segmentation being one of the most difficult tasks currently in the computer vision area, and large number of algorithms is being developed. Thus the proposed approach in this paper exploits this large amount of available computational tools by using the algorithm selection approach. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features F, a set of image attribute A and a selection mechanism S(F, A, A) that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2%.

Original languageEnglish
Title of host publication2017 Intelligent Systems Conference, IntelliSys 2017
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages259-266
Number of pages8
Volume2018-January
ISBN (Electronic)9781509064359
DOIs
Publication statusPublished - Mar 23 2018
Event2017 Intelligent Systems Conference, IntelliSys 2017 - London, United Kingdom
Duration: Sep 7 2017Sep 8 2017

Other

Other2017 Intelligent Systems Conference, IntelliSys 2017
CountryUnited Kingdom
CityLondon
Period9/7/179/8/17

Fingerprint

Segmentation
Reasoning
Semantics
Process Optimization
Computer Vision
Computer vision
Attribute
Alternatives
Experiment
Experiments

Keywords

  • Algorithm selection
  • high-level feedback
  • scene understanding
  • semantic segmentation

ASJC Scopus subject areas

  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence
  • Computer Vision and Pattern Recognition
  • Control and Optimization

Cite this

Kameyama, M., Lukac, M., Abdiyeva, K., & Kim, A. (2018). Reasoning and algorithm selection augmented symbolic segmentation. In 2017 Intelligent Systems Conference, IntelliSys 2017 (Vol. 2018-January, pp. 259-266). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IntelliSys.2017.8324302

Reasoning and algorithm selection augmented symbolic segmentation. / Kameyama, Michitaka; Lukac, Martin; Abdiyeva, Kamila; Kim, Alexandra.

2017 Intelligent Systems Conference, IntelliSys 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. p. 259-266.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kameyama, M, Lukac, M, Abdiyeva, K & Kim, A 2018, Reasoning and algorithm selection augmented symbolic segmentation. in 2017 Intelligent Systems Conference, IntelliSys 2017. vol. 2018-January, Institute of Electrical and Electronics Engineers Inc., pp. 259-266, 2017 Intelligent Systems Conference, IntelliSys 2017, London, United Kingdom, 9/7/17. https://doi.org/10.1109/IntelliSys.2017.8324302
Kameyama M, Lukac M, Abdiyeva K, Kim A. Reasoning and algorithm selection augmented symbolic segmentation. In 2017 Intelligent Systems Conference, IntelliSys 2017. Vol. 2018-January. Institute of Electrical and Electronics Engineers Inc. 2018. p. 259-266 https://doi.org/10.1109/IntelliSys.2017.8324302
Kameyama, Michitaka ; Lukac, Martin ; Abdiyeva, Kamila ; Kim, Alexandra. / Reasoning and algorithm selection augmented symbolic segmentation. 2017 Intelligent Systems Conference, IntelliSys 2017. Vol. 2018-January Institute of Electrical and Electronics Engineers Inc., 2018. pp. 259-266
@inproceedings{0b9aa9eaf9e04ca5ad9158d3e6dab292,
title = "Reasoning and algorithm selection augmented symbolic segmentation",
abstract = "In this paper an alternative method to symbolic segmentation is studied. Semantic segmentation being one of the most difficult tasks currently in the computer vision area, and large number of algorithms is being developed. Thus the proposed approach in this paper exploits this large amount of available computational tools by using the algorithm selection approach. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features F, a set of image attribute A and a selection mechanism S(F, A, A) that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2{\%}.",
keywords = "Algorithm selection, high-level feedback, scene understanding, semantic segmentation",
author = "Michitaka Kameyama and Martin Lukac and Kamila Abdiyeva and Alexandra Kim",
year = "2018",
month = "3",
day = "23",
doi = "10.1109/IntelliSys.2017.8324302",
language = "English",
volume = "2018-January",
pages = "259--266",
booktitle = "2017 Intelligent Systems Conference, IntelliSys 2017",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

TY - GEN

T1 - Reasoning and algorithm selection augmented symbolic segmentation

AU - Kameyama, Michitaka

AU - Lukac, Martin

AU - Abdiyeva, Kamila

AU - Kim, Alexandra

PY - 2018/3/23

Y1 - 2018/3/23

N2 - In this paper an alternative method to symbolic segmentation is studied. Semantic segmentation being one of the most difficult tasks currently in the computer vision area, and large number of algorithms is being developed. Thus the proposed approach in this paper exploits this large amount of available computational tools by using the algorithm selection approach. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features F, a set of image attribute A and a selection mechanism S(F, A, A) that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2%.

AB - In this paper an alternative method to symbolic segmentation is studied. Semantic segmentation being one of the most difficult tasks currently in the computer vision area, and large number of algorithms is being developed. Thus the proposed approach in this paper exploits this large amount of available computational tools by using the algorithm selection approach. That is, let there be a set A of available algorithms for symbolic segmentation, a set of input features F, a set of image attribute A and a selection mechanism S(F, A, A) that selects on a case by case basis the best algorithm. The semantic segmentation is then an optimization process that combines best component segments from multiple results into a single optimal result. The experiments compare three different algorithm selection mechanisms using three selected semantic segmentation algorithms. The results show that using the current state of art algorithms and relatively low accuracy of algorithm selection the accuracy of the semantic segmentation can be improved by 2%.

KW - Algorithm selection

KW - high-level feedback

KW - scene understanding

KW - semantic segmentation

UR - http://www.scopus.com/inward/record.url?scp=85050866496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85050866496&partnerID=8YFLogxK

U2 - 10.1109/IntelliSys.2017.8324302

DO - 10.1109/IntelliSys.2017.8324302

M3 - Conference contribution

AN - SCOPUS:85050866496

VL - 2018-January

SP - 259

EP - 266

BT - 2017 Intelligent Systems Conference, IntelliSys 2017

PB - Institute of Electrical and Electronics Engineers Inc.

ER -