| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 494646 | Applied Soft Computing | 2016 | 13 Pages |
•The optimization of the antecedent parameters for a type 2 fuzzy system of edge detection is presented.•The goal of interval type-2 fuzzy logic in edge detection methods is to provide the ability to handle uncertainty.•Results show that the Cuckoo search provides better results in optimizing the type-2 fuzzy system.
This paper presents the optimization of a fuzzy edge detector based on the traditional Sobel technique combined with interval type-2 fuzzy logic. The goal of using interval type-2 fuzzy logic in edge detection methods is to provide them with the ability to handle uncertainty in processing real world images. However, the optimal design of fuzzy systems is a difficult task and for this reason the use of meta-heuristic optimization techniques is also considered in this paper. For the optimization of the fuzzy inference systems, the Cuckoo Search (CS) and Genetic Algorithms (GAs) are applied. Simulation results show that using an optimal interval type-2 fuzzy system in conjunction with the Sobel technique provides a powerful edge detection method that outperforms its type-1 counterparts and the pure original Sobel technique.
Graphical abstractFigure optionsDownload full-size imageDownload as PowerPoint slide
