Welcome to the InfoSci Platform
Reference Hub2
Improvement of 2-Partition Entropy Approach Using Type-2 Fuzzy Sets for Image Thresholding

Improvement of 2-Partition Entropy Approach Using Type-2 Fuzzy Sets for Image Thresholding

Ouarda Assas
Copyright: © 2015 |Volume: 6 |Issue: 3 |Pages: 16
ISSN: 1942-3594|EISSN: 1942-3608|EISBN13: 9781466677517|DOI: 10.4018/IJAEC.2015070103
Cite Article Cite Article

MLA

Assas, Ouarda. "Improvement of 2-Partition Entropy Approach Using Type-2 Fuzzy Sets for Image Thresholding." IJAEC vol.6, no.3 2015: pp.33-48. http://doi.org/10.4018/IJAEC.2015070103

APA

Assas, O. (2015). Improvement of 2-Partition Entropy Approach Using Type-2 Fuzzy Sets for Image Thresholding. International Journal of Applied Evolutionary Computation (IJAEC), 6(3), 33-48. http://doi.org/10.4018/IJAEC.2015070103

Chicago

Assas, Ouarda. "Improvement of 2-Partition Entropy Approach Using Type-2 Fuzzy Sets for Image Thresholding," International Journal of Applied Evolutionary Computation (IJAEC) 6, no.3: 33-48. http://doi.org/10.4018/IJAEC.2015070103

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

Thresholding is a fundamental task and a challenge for many image analysis and pre-processing process. However, the automatic selection of an optimum threshold has remained a challenge in image segmentation. The fuzzy 2-partition entropy approach for threshold selection is one of the best image thresholding techniques. In this work, an improvement of the later method using type-2 fuzzy sets is proposed to represent the imprecision or lack of knowledge of the expert in the choice of the membership function associated with the image. Two databases are used to evaluate its effectiveness: dataset of standard grayscale test images and MR Brain images. Experiment results show that the type-2 Fuzzy 2-partition entropy algorithm performs equally well in terms of the quality of image segmentation and leads to a good visual result.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.