A comparative study between PVO-based framework and multi-predictor mechanism in reversible data hiding

•Proposing the general multi-predictor (GMP) framework.•Explaining two typical methods are special cases of the GMP framework.•Using the eight neighboring pixels of to-be-embedded pixel of IPVO to propose new predictors.•Using different number of predictors to predict pixels of different complexities. Sorting-based reversible data hiding (RDH) methods like pixel-value-ordering (PVO) can predict pixel values accurately and achieve an extremely low distortion on the embedded image. However, the excellent performance of these methods was not well explained in previous works, and there are unexploited common points among them. In this paper, we propose a general multi-predictor (GMP) framework to summarize PVO-based RDH methods and explain their high prediction accuracy. Moreover, by utilizing the proposed GMP framework, a more efficient sorting-based RDH method is given as an example to show the generality and applicability of our framework. Comparing with other PVO-based methods, the proposed example method can achieve significant improvement in embedding performance. It is hopeful that more efficient sorting-based RDH algorithms can be designed according to our proposed framework by designing better predictors and their combination methods.