Performance of Wavelet - Based Threshold Selection Schemes for Watermark Detection

Watermark detection can be considered as an estimation problem in which the watermark sequence has to be estimated from a possibly distorted image. In this paper, we use wavelet threshold estimation for extraction of watermark sequence. The correlation matching is then used for checking for the presence of the watermark. It is shown that the performance of this method is superior to that of correlation matching. The performance of two threshold selection methods are compared for this purpose. The watermark embedding is performed in wavelet domain.