Izvorni znanstveni članak

https://doi.org/10.24138/jcomss.v16i2.830

An Improved Image Segmentation System: A Cooperative Multi-agent Strategy for 2D/3D Medical Images

Hanane Allioui orcid.org/0000-0001-6208-3102 ; Cadi Ayyad University, Marrakesh, Morocco
Mohamed Sadgal ; Cadi Ayyad University, Marrakesh, Morocco
Aziz El Fazziki ; Cadi Ayyad University, Marrakesh, Morocco

Sažetak

In this paper, we present a solution-based cooperation approach for strengthening the image segmentation.This paper proposes a cooperative method relying on Multi-Agent System. The main contribution of this work is to highlight the importance of cooperation between the contour and region growing based on Multi-Agent System (MAS). Consequently, agents’ interactions form the main part of the whole process for image segmentation. Similar works were proposed to evaluate the effectiveness of the proposed solution. The main difference is that our Multi-Agent System can perform the segmentation process ensuring efficiency. Our results show that the performance indices in the system were higher. Furthermore, the integration of thecooperation paradigm allows to speed up the segmentation process. Besides, the tests reveal the robustness of our method by proving competitive results. Our proposal achieved an accuracy of 93,51%± 0,8, a sensitivity of 93,53%± 5,08 and a specificity rate of 92,64%± 4,01.

Ključne riječi

Artificial intelligence; Intelligent systems; Computer applications; Expert systems; Image processing; Image segmentation.

Hrčak ID:

240382

URI

https://hrcak.srce.hr/240382

Datum izdavanja:

15.6.2020.

Posjeta: 795 *