A majority-voting based watermarking scheme for color image tamper detection and recovery

This paper presents a novel color image watermarking scheme for both tamper detection and tampered image recovery. The proposed scheme embeds watermarks consisting of the authentication data and the recovery data into image blocks. In the tamper detection process, instead of independently examining each embedded authentication data, we take all the authentication data embedded in an image into account and utilize a majority-voting technique to determine the legitimacy of image blocks. Experimental results show that the proposed scheme can effectively thwart collage attack and vector quantization (VQ) attack, while sustaining superior accuracy of tamper localization. Furthermore, the results reveal that the tampered images can be successfully recovered with acceptable visual quality.