Reversible data hiding in encrypted binary image with shared pixel prediction and halving compression

In this paper, a new reversible data hiding scheme in encrypted binary image is proposed by shared pixel prediction and halving compression. We first divide binary image into non-overlapping pure color blocks and non-pure color blocks, and then partition each non-pure color block as shared pixels and embeddable pixels by a cross-segmentation mechanism. Then, a location sequence which marked all blocks is further compressed by halving compression and is considered as auxiliary data. Subsequently, after performing image encryption, data hider embeds additional data into the pixels of pure color blocks and embeddable pixels of non-pure color blocks. Finally, separable operations of data extraction, direct image decryption, and image recovery are conducted by the receiver. With shared pixel prediction mechanism, perfect image recovery can be achieved. Extensive experiments demonstrate that compared with existing methods, our scheme can obtain a higher visual quality of decrypted images, while maintaining a larger embedding capacity.