Categorisation of random images into fog and blur based on the statistical analysis
by Monika Verma; Vandana Dixit Kaushik; Vinay Pathak
International Journal of Advanced Intelligence Paradigms (IJAIP), Vol. 25, No. 1/2, 2023

Abstract: Noisy images are a bottleneck to solve the image processing problems. The present paper aims to classify images as different types of foggy and blurry images. A feature based classifier called FB classifier has been proposed. Given an image the classifier is able to tell whether the image is clear or unclear, which type of distortion is there, either foggy or blurry and also the categories of different types of blur and fog. The quality of the images taken through any equipment depends on few factors: 1) medium in which the photograph is taken; 2) the movements of either the camera or the object or movement of both; 3) the quality of the equipment that is used for capturing. All the algorithms of classification or the removal of distortions are made to handle the above three scenarios. The three factors encompass all types of foggy or the blurry images. The images viewed are given different threshold values according to their properties and finally the cumulative threshold value decides which type of the image is it. The algorithm is simple to implement yet it is comparable to the state of art methods.

Online publication date: Thu, 11-May-2023

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 Advanced Intelligence Paradigms (IJAIP):
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 [email protected]