EVALUATION OF COMPONENT ALGORITHMS IN AN ALGORITHM SELECTION APPROACH FOR SEMANTIC SEGMENTATION BASED ON HIGH-LEVEL INFORMATION FEEDBACK

Authors

  • M. Lukac Nazarbayev University, Astana, Kazakhstan, Kazakhstan
  • K. Abdiyeva Nanyang Technological University, Singapore, Singapore
  • M. Kameyama Tohoku University, Sendai, Japan, Japan

DOI:

https://doi.org/10.15588/1607-3274-2016-1-11

Keywords:

algorithm selection, algorithm suitability, computer vision.

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.

References

Rice J. The algorithm selection problem / J. Rice // Advances in Computers. – 1976. – Vol. 15. – P. 65–118. 2. Lukac M. Machine learning based adaptive contour detection using algorithm selection and image splitting / M. Lukac, R. Tanizawa, M. Kameyama // Interdisciplinary Information Sciences. – 2012. – Vol. 18, № 2. – P. 123–134. 3. Lukac M. Natural image understanding using algorithm selection and high level feedback / M. Lukac, M. Kameyama, K. Hiura // SPIE Intelligent Robots and Computer Vision XXX: algorithms and Techniques. – 2013. DOI: 10.1117/12.2008593 4. Zhang Y. Optimal selection of segmentation algorithms based on performance evaluation / Y. Zhang and H. Luo // Optical Engineering. – 2000. – Vol. 39, № 6. – P. 1450–1456. 5. Yong X. Optimal selection of image segmentation algorithms based on performance prediction / X. Yong, D. Feng, Z. Rongchun // Proceedings of the Pan-Sydney Area Workshop on Visual Information Processing (VIP2003). – 2003. – P. 105–108. 6. Yu L. Feature selection for high-dimensional data: A fast correlationbased filter solution / L. Yu, H. Liu // Proceedings of the 20th International Conference on Machine Learning. – 2004. – P. 856–863. 7. Takemoto S. Algorithm selection for intracellular image segmentation based on region similarity / S. Takemoto, H. Yokota // Ninth International Conference on Intelligent Systems Design and Applications. –2009. – P. 1413–1418. DOI: 10.1109/ISDA.2009.205 8. Lukac M. Bayesian-network-based algorithm selection with high level representation feedback for real-world intelligent systems / M. Lukac, and M. Kameyama // Information Technology in Industry. – 2015. – Vol. 3, № 1. – P. 10–15. 9. Peng B. Parameter selection for graph cut based image segmentation / B. Peng, V. Veksler // In Proceedings of the British Conference on Computer Vision. – 2008. – P. 16.1–16.10. DOI: 10.5244/C.22.16 10. Hoiem D. Closing the loop on scene interpretation / D. Hoiem, A. A. Efros, M. Hebert // Proc. Computer Vision and Pattern Recognition (CVPR). – 2008. – P. 1–8. DOI: 10.1109/ CVPR.2008.4587587

Downloads

Published

2015-10-06

How to Cite

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, (1). https://doi.org/10.15588/1607-3274-2016-1-11

Issue

No. 1 (2016): Radio Electronics, Computer Science, Control

Section

Progressive information technologies

License

Copyright (c) 2016 M. Lukac, K. Abdiyeva, M. Kameyama

Creative Commons License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Creative Commons Licensing Notifications in the Copyright Notices

The journal allows the authors to hold the copyright without restrictions and to retain publishing rights without restrictions.

The journal allows readers to read, download, copy, distribute, print, search, or link to the full texts of its articles.

The journal allows to reuse and remixing of its content, in accordance with a Creative Commons license СС BY -SA.

Authors who publish with this journal agree to the following terms:

  • Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License CC BY-SA that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.

  • Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.

  • Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.