Modified silhouette based segmentation outperforming in the presence of intensity inhomogeneity in the hyperspectral images
by Kriti; Urvashi Garg
International Journal of Intelligent Engineering Informatics (IJIEI), Vol. 9, No. 3, 2021

Abstract: In the real world the intensity inhomogeneity occurs presenting considerable challenges in the field of segmentation of images. In the arena of computer vision and processing of images, the method of level resolute takes an important place. For the conventional level resolute formulations, the indiscretions are established by the function of the level resolute during its progression causing the mathematical error and ultimately destroying the evolution constancy. Hence, a statistical remedy known as reestablishment was applied usually to substitute the besmirched function of level resolute. In the prototypical, the concentration of the confined image is labelled by Gaussian disseminations. It yields a novel type of evolution with level resolute in which the effect of distance regularisation disregards the necessity for reestablishment avoiding its tempted numerical errors. Hence, in the paper a subsequent multiplicative model is presented that considers the inhomogeneity in intensity likewise considering the astronomy of imaging in a diversity of modalities.

Online publication date: Mon, 18-Oct-2021

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 Intelligent Engineering Informatics (IJIEI):
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