Image steganalysis: real-time adaptive colour image segmentation for hidden message retrieval and Matthew's correlation coefficient calculation
by B. Yamini; R. Sabitha
International Journal of Information and Computer Security (IJICS), Vol. 17, No. 1/2, 2022

Abstract: Adaptive image steganography is the method of hiding secret information in colour adaptive regions of the image. Its counter method to reveal hidden secret information is called as adaptive image steganalysis. In the proposed method, the colour correlations between pixels are used to identify the adaptive region of the image by real time adaptive colour image segmentation. Bi-cubic interpolation method is applied on these colour adaptive regions to extract the features from the selected region. These features are considered for classification using support vector machine classifier, to distinguish between stego and cover images. Reversible two least significant bit (LSB) technique is used to identify and to retrieve the hidden content from the payload locations. The accuracy is measured using Matthew's correlation coefficient calculation. The results of real-time adaptive colour image segmentation outperform the methods, normalised cut segmentation, MX-quadtree segmentation and watershed segmentation.

Online publication date: Fri, 04-Mar-2022

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 Computer Security (IJICS):
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