Improved CNN Prediction Based Reversible Data Hiding

TL;DR

This paper introduces an improved CNN predictor for reversible data hiding in images, enhancing embedding performance by predicting pixel complexities and sorting prediction errors for low-distortion data embedding.

Contribution

The paper presents an enhanced CNN predictor that incorporates complexity prediction, leading to more efficient and lower-distortion reversible data hiding compared to previous CNN-based methods.

Findings

Achieves better embedding performance than previous CNN predictor-based methods.

Uses pixel complexity prediction to improve sorting and selection of prediction errors.

Demonstrates superior results with the same histogram shifting strategy.

Abstract

This letter proposes an improved CNN predictor (ICNNP) for reversible data hiding (RDH) in images, which consists of a feature extraction module, a pixel prediction module, and a complexity prediction module. Due to predicting the complexity of each pixel with the ICNNP during the embedding process, the proposed method can achieve superior performance than the CNN predictor-based method. Specifically, an input image does be first split into two different sub-images, i.e., the "Dot" image and the "Cross" image. Meanwhile, each sub-image is applied to predict another one. Then, the prediction errors of pixels are sorted with the predicted pixel complexities. In light of this, some sorted prediction errors with less complexity are selected to be efficiently used for low-distortion data embedding with a traditional histogram shift scheme. Experimental results demonstrate that the proposed method can achieve better embedding performance than that of the CNN predictor with the same histogram shifting strategy.