Support Vector Machine and hyperplanes in digital watermark detection

Correlation detector (CD) has been widely used to determine whether a legitimate watermark exists in a suspected watermarked object. The watermarked and unwatermarked images are perceived as positive and negative class respectively. Hence, support vector machine (SVM) is used as the classifier of water-marked and unwatermarked digital image due to its ability of separating both linearly and non-linearly separable data. Hyperplanes of various detectors are briefly elaborated to show how SVM´s hyperplane is suitable for Stirmark attacked watermarked image. Cox´s spread spectrum watermarking scheme is used to embed the watermark into digital images. Then, SVM is trained with both the watermarked and unwatermarked images. Receiver operating characteristics graphs are plotted to assess the false positive and false negative probability of both the CD and SVM classifier. Both watermarked and unwatermarked images are later attacked under Stirmark, and then tested on the CD and SVM classifier. The preprocessing and optimal parameters setting enable the trained SVM to achieve substantially better results than those resulting from the CD.