SVM regression based robust image watermarking technique in joint DWT-DCT domain

• Published in: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT) pp. 1426 - 1433
• Main Authors: Islam, M., Mallikharjunudu, G., Parmar, A. S., Kumar, A., Laskar, R. H.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2017
• Subjects: Discrete Cosine Transform (DCT); Discrete cosine transforms; Discrete Wavelet Transform (DWT); Discrete wavelet transforms; Distortion; image watermarking; Normalized cross-correlation (NC); Robustness; Support Vector Machine (SVM) Regression; Support vector machines; Watermarking
• DOI: 10.1109/ICICICT1.2017.8342779

In this paper, a robust image watermarking technique has been proposed based on the combination of discrete wavelet transform (DWT) and discrete cosine transform (DCT). SVM regression model has been incorporated for geometric distortion correction to achieve improved robustness against de-synchronization attacks such as rotation, translation etc. Low order Pseudo Zernike (PZ) moments have used as a feature vector in SVM regression model. The 3-level DWT transformed DCT coefficients are modified to embed a binary bit. The performance of algorithm has been observed against both intentional and non-intentional attacks. The scheme provides an average imperceptibility of around 42.45 dB. The effect of rotation and translation attack has been estimated using trained SVM regression model. The robustness against de-synchronization attack is performed after correcting the attacked watermarked images. The experimental results show that the algorithm provides adequate robustness against both the geometric and non-geometric attacks.