Copyright protection using KELM-PSO based multi-spectral image watermarking in DCT domain with local texture information
- PDF / 3,456,218 Bytes
- 22 Pages / 439.37 x 666.142 pts Page_size
- 4 Downloads / 186 Views
Copyright protection using KELM-PSO based multi-spectral image watermarking in DCT domain with local texture information based selection Varsha Sisaudia 1
& Virendra P. Vishwakarma
1
Received: 12 January 2020 / Revised: 1 October 2020 / Accepted: 6 October 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Since many years, researchers have been developing techniques for copyright protection. This paper presents a novel approach for copyright protection of multi-spectral images using particle swarm optimization (PSO) and kernel extreme learning machine (KELM) based watermarking technique. It begins with the selection of nonoverlapping blocks of host image based on local texture information. Next, discrete cosine transform (DCT) is performed on these selected blocks, after which coefficients scanned in zig-zag manner are used to form the dataset for training and testing of KELM. KELM is applied as a regression model and predicts the output for given input vector. The watermark bits are then embedded into the output vector. PSO is a nature- inspired meta- heuristic technique used for optimization of scaling factors that control the strength of copyright logo bits being inserted into the original image. The promising results obtained by using this technique have been compared with other state-of-art approaches. Keywords Kernel extreme learning machine . Digital image watermarking . Entropy . Discrete cosine transform . Particle swarm optimization
1 Introduction Copyrights [32, 42, 46] are a means of attaining a legal right over any piece of information. The owner uses them to define the terms of usage and distribution by other parties. * Varsha Sisaudia [email protected] Virendra P. Vishwakarma [email protected]
1
University School of Information Communication & Technology, Sector 16C, Dwarka, 110078 New Delhi, India
Multimedia Tools and Applications
Anyone found to have unauthorized access to that information is liable to trial. Watermarks can usually be seen on images marking the ownership of the photographer. Though these watermarks act as copyrights, they also significantly degrade the quality of image. With powerful tools like Photoshop, these can also be removed. Therefore, to have a watermark embedded in the image such that it is not visible to the naked eyes, but also marks the ownership, is a clever option. What needs to be ensured is not only that the watermark can be efficiently hidden into the image, but also that it remains unaffected despite modifications in the images. The robustness of marking scheme is quantified by exposing an image to multiple attacks or modifications in terms of filters, noise addition, resizing, etc. Striking a healthy balance between robustness and imperceptibility is what makes a watermarking scheme a preferred choice. Thus, any watermarking scheme must ensure the robustness and imperceptibility of watermark, and find an optimal way to embed a copyright logo in any image. Watermarking has been a topic of interest for
Data Loading...
