An improved integer transform combining with an irregular block partition

Abstract

After conducting deep research on all existing reversible data hiding (RDH) methods based on Alattar's integer transform, we discover that the frequently-used method in obtaining the difference value list of an image block may lead to high embedding distortion. To this end, we propose an improved Alattar's transform-based-RDH-method. Firstly, the irregular block partition method which makes full use of high correlation between two neighboring pixels is proposed to increase the embedding performance. Specifically, each image block is composed of a center pixel and several pixels surrounding this center pixel. Thus, the difference value list is created by using the center pixel to predict each pixel surrounding it. Since the center pixel is highly related to each pixel surrounding it, a sharp difference value histogram is generated. Secondly, the mean value of an image block in Alattar's integer transform has embedding invariance property, and therefore, it can be used for increasing the estimation performance of a block's local complexity. Finally, two-layer embedding is combined into our scheme in order to optimize the embedding performance. Experimental results show that our method is effective.