A NOVEL REVERSIBLE WATERMARKING METHOD USING PRE-SELECTION STRATEGY

The histogram shifting based reversible watermarking method manipulates the prediction error of the pixels either to avoid overlapping or to embed the watermark. The embedding distortion of this kind of methods is mainly introduced by the pixels with large prediction error. In this paper, we employ the gradient-adjusted predictor (GAP) to improve the prediction efficiency and present a pre-selection algorithm to decrease the number of large prediction errors in the embedding process. Consequently, the embedding distortion is greatly reduced in the encoder. In addition, in order to obtain the optimal embedding thresholds, we design, an earning-cost ratio (ECR) based selection algorithm whose computation complexity is much lower than that of the traditional iterative method. Experimental results verify the superiority of the proposed method by comparing with some existing schemes.