An opposition-based firefly algorithm for medical image contrast enhancement
by Amer Draa; Zeyneb Benayad; Fatima Zahra Djenna
International Journal of Information and Communication Technology (IJICT), Vol. 7, No. 4/5, 2015

Abstract: Image enhancement is a crucial pre-processing step in almost every medical imaging system. Different types of degradation can occur in medical images such as noise, blur and contrast imperfection. Filtering techniques have been successfully applied for denoising and deblurring images, while contrast enhancement has been achieved using histogram equalisation. This technique has the main drawbacks of losing details included in minor grey levels or over-enhancement. As a solution, the grey-level mapping technique has been adopted. Defining the new set of grey levels, to substitute those of the input image, using an exhaustive search is computationally complex; so metaheuristics are generally used. In this topic, this paper presents a new opposition-based firefly algorithm to search the best target set of grey levels for medical image contrast enhancement. The obtained results are compared against those obtained by histogram equalisation and classical variants of the firefly algorithm.

Online publication date: Thu, 02-Jul-2015

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

 
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Information and Communication Technology (IJICT):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?


Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email subs@inderscience.com