DSpace Repository

Evaluation of Component Algorithms in an Algorithm Selection Approach for Semantic Segmentation Based on High-level Information Feedback

Show simple item record

dc.contributor.author Lukac, Martin
dc.contributor.author Abdiyeva, K.
dc.contributor.author Kameyama, Michitaka
dc.date.accessioned 2020-06-26T11:03:44Z
dc.date.available 2020-06-26T11:03:44Z
dc.date.issued 2016
dc.identifier.citation Lukac, M., Abdiyeva, K., & Kameyama, M. (2015). EVALUATION OF COMPONENT ALGORITHMS IN AN ALGORITHM SELECTION APPROACH FOR SEMANTIC SEGMENTATION BASED ON HIGH-LEVEL INFORMATION FEEDBACK. Radio Electronics, Computer Science, Control, 0(1). https://doi.org/10.15588/1607-3274-2016-1-11 en_US
dc.identifier.issn 1607-3274
dc.identifier.uri https://doi.org/10.15588/1607-3274-2016-1-11
dc.identifier.uri http://ric.zntu.edu.ua/article/view/66670
dc.identifier.uri http://nur.nu.edu.kz/handle/123456789/4813
dc.description.abstract In this paper we discuss certain theoretical properties of the algorithm selection approach to the problem of semantic segmentation in computer vision. High quality algorithm selection is possible only if each algorithm’s suitability is well known because only then the algorithm selection result can improve the best possible result given by a single algorithm. We show that an algorithm’s evaluation score depends on final task; i.e. to properly evaluate an algorithm and to determine its suitability, only well formulated tasks must be used. When algorithm suitability is well known, the algorithm can be efficiently used for a task by applying it in the most favorable environmental conditions determined during the evaluation. The task dependent evaluation is demonstrated on segmentation and object recognition. Additionally, we also discuss the importance of high level symbolic knowledge in the selection process. The importance of this symbolic hypothesis is demonstrated on a set of learning experiments with a Bayesian Network, a SVM and with statistics obtained during algorithm selector training. We show that task dependent evaluation is required to allow efficient algorithm selection. We show that using symbolic preferences of algorithms, the accuracy of algorithm selection can be improved by 10 to 15% and the symbolic segmentation quality can be improved by up to 5% when compared with the best available algorithm. en_US
dc.language.iso en en_US
dc.publisher Zaporiz'kyi Natsional'nyi Tekhnichnyi Universytet (Zaporizhzhya National Technical University) en_US
dc.relation.ispartofseries Radio Electronics, Computer Science, Control;
dc.rights Attribution-NonCommercial-ShareAlike 3.0 United States *
dc.rights.uri http://creativecommons.org/licenses/by-nc-sa/3.0/us/ *
dc.subject algorithm selection en_US
dc.subject algorithm suitability en_US
dc.subject computer vision en_US
dc.subject Research Subject Categories::TECHNOLOGY en_US
dc.title Evaluation of Component Algorithms in an Algorithm Selection Approach for Semantic Segmentation Based on High-level Information Feedback en_US
dc.type Article en_US
workflow.import.source science

Files in this item

The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record

Attribution-NonCommercial-ShareAlike 3.0 United States Except where otherwise noted, this item's license is described as Attribution-NonCommercial-ShareAlike 3.0 United States

Video Guide

Submission guideSubmission guide

Submit your materials for publication to

NU Repository Drive


My Account