A Novel Reversible Data Hiding Based on the Prediction Error Image

Reversible data hiding has drawn a lot of interest recently. Being reversible, the original image can be completely restored without distortion. In this paper, a novel reversible data hiding scheme is proposed, which is based on histogram shifting of prediction errors. The JPEG-LS prediction method is employed. We apply the peak point of a histogram in a prediction error ( PE) image to generate an inverse transformation to create free space for hiding in the proposed scheme. The experimental results for many standard test images show that a higher hiding capacity is obtained while a good quality stego-image is preserved. Compared to Ni et al.'s scheme, the quality of the stego-image is improved about 10 dB when the same amounts of secret messages are embedded.