A novel audio watermarking scheme using ensemble-based watermark detector and discrete wavelet transform
- PDF / 976,717 Bytes
- 21 Pages / 595.276 x 790.866 pts Page_size
- 8 Downloads / 198 Views
(0123456789().,-volV)(0123456789(). ,- volV)
ORIGINAL ARTICLE
A novel audio watermarking scheme using ensemble-based watermark detector and discrete wavelet transform Seyed Mostafa Pourhashemi1 • Mohammad Mosleh1
•
Yousof Erfani2
Received: 28 August 2019 / Accepted: 24 September 2020 Springer-Verlag London Ltd., part of Springer Nature 2020
Abstract Most existing extraction techniques in audio watermarking use conventional techniques in which some sets of special rules based on reverse embedding rules are used for watermark extraction and have many weaknesses, like very low robustness to destructive attacks. To overcome this problem, the use of machine learning-based methods has increased in recent years in this field. The disadvantage of these methods is the high reliance on a unique classifier and lack of proper efficiency when achieving high capacity, which is a major challenge in audio watermarking. The main purpose of this paper is to present a method that covers the weak points of conventional methods and simple intelligent methods and improves system performance using a synergistic combination of discrete wavelet transform (DWT) and ensemble-intelligent extraction approach by proposed combination of trained machine learning classifiers. For the embedding operation in the proposed method, the DWT and the difference in energy levels obtained through DWT coefficients are used. In the extraction section, three methods are used in parallel: (a) the trained support vector machine (SVM) classifier with RBF kernel, (b) trained SVM classifier with quadratic kernel and (c) the trained K-nearest neighbor classifier; finally, the majority function is used to vote and make a final decision to create an intelligent-based watermark detector. A training set is required to train the classifiers, whose bit sequence is generated by a proposed 5-bit linear-feedback shift register. The results of various experiments indicate that this ensemble method has achieved the appropriate imperceptibility and high capacity, along with higher robustness compared to conventional techniques and individual learning classifiers. Keywords Audio watermarking Discrete wavelet transform Support vector machine K-nearest neighbor Machine learning
1 Introduction Digital technologies are accessible to every user today and are easy to publish. Digital watermarking is a technique for manipulating a work or data stream to deliberately embed an extra message that can hardly or impossibly be perceived by a human. The work or data stream to be modified is called the ‘host signal’ or simply the ‘cover’ and might be any multimedia signal such as a speech, audio, image, or video signal [1]. The main purpose of digital audio & Mohammad Mosleh [email protected] 1
Department of Computer Engineering, Dezful Branch, Islamic Azad University, Dezful, Iran
2
Department of Electrical and Computer Engineering, AEL Group, McMaster University, Hamilton, ON, Canada
watermarking is to embed a series of hidden data in host audio files (as one of the most
Data Loading...
