Combined Private and Public Watermarking in Wavelet Transform Domain

Abstract

In this paper, a wavelet-based digital wa-termarking algorithm is proposed. Unlike other watermark casting algorithms, which embedded either a random number of a sequence of bits or a visually recognizable pattern as a watermark into the original source at a time, we present an algorithm to embed two watermarks for the copyright protection improvement. In the pro-posed approach, an original image is decom-posed into three levels using a discrete wavelet transform (DWT). The two watermarks, stand-ing for the owner’s signature and the cus-tomer’s unique serial number, are embedded into and extracted from different mid-dle-frequency subbands with private and public watermarking, respectively. The embedding and extraction procedures can be performed in parallel to reduce the processing time, espe-cially in large-scale use of watermarks for the purpose of owner identification and transaction tracking simultaneously. Simulation results show that the embedded watermarks are im-perceptible in the watermarked image and could be perfectly extracted under no attack. Moreover, the superior performance of the proposed technique is robust to various signal distortions.