Skip to main content

Firefly algorithm approach for rational bézier border reconstruction of skin lesions from macroscopic medical images.

Galvez, A., Iglesias, A., Ugail, H., You, L., Haron, H. and Habib, Z., 2019. Firefly algorithm approach for rational bézier border reconstruction of skin lesions from macroscopic medical images. In: 13th International Conference on Software, Knowledge, Information Management and Applications, 26-28 August 2019, Island of Ulkulhas, Maldives.

Full text available as:

[img]
Preview
PDF
SKIMA 2019 paper 1.pdf - Accepted Version
Available under License Creative Commons Attribution Non-commercial.

774kB

DOI: 10.1109/SKIMA47702.2019.8982465

Abstract

Image segmentation is a fundamental step for image processing of medical images. One of the most important tasks in this step is border reconstruction, which consists of constructing a border curve separating the organ or tissue of interest from the image background. This problem can be formulated as an optimization problem, where the border curve is computed through data fitting procedures from a collection of data points assumed to lie on the boundary of the object under analysis. However, standard mathematical optimization techniques do not provide satisfactory solutions to this problem. Some recent papers have applied evolutionary computation techniques to tackle this issue. Such works are only focused on the polynomial case, ignoring the more powerful (but also more difficult) case of rational curves. In this paper, we address this problem with rational Bézier curves by applying the firefly algorithm, a popular bio-inspired swarm intelligence technique for optimization. Experimental results on medical images of melanomas show that this method performs well and can be successfully applied to this problem.

Item Type:Conference or Workshop Item (Paper)
Group:Faculty of Media & Communication
ID Code:34670
Deposited By: Unnamed user with email symplectic@symplectic
Deposited On:07 Oct 2020 10:39
Last Modified:07 Oct 2020 10:39

Downloads

Downloads per month over past year

More statistics for this item...
Repository Staff Only -