Multiple Watermarking for Healthcare Applications

Abstract

In this paper, an algorithm for multiple digital watermarking based on discrete wavelet transform (DWT), discrete cosine transform (DCT), and singular value decomposition (SVD) was proposed for healthcare applications such as tele-ophthalmology, tele-medicine, tele-diagnosis, and tele-consultancy services. Multiple watermarks were used in this algorithm to reduce the consequences of medical identity thefts. In the embedding process, the cover medical image was decomposed into third-level DWT. Low-frequency bands (LH2 and LL3) were transformed by DCT, and then SVD was applied to DCT coefficients. Two watermarks in the form of images were also transformed by DCT and then SVD. The singular values of the watermark information were embedded in the singular value of the cover medical image. Watermarks were extracted using an extraction algorithm. In order to enhance the robustness performance of the image watermarks, back-propagation neural network was applied to the extracted watermarks to reduce the effects of different noise applied on the watermarked image. Results were obtained by varying the gain factor and the different cover image modalities. Experimental results were provided to illustrate that the proposed method is able to withstand a variety of signal processing attacks, and has been found to give excellent performance in terms of robustness and imperceptibility. The performance of the method was also compared with other reported techniques. Further, the visual quality of the proposed method was also evaluated by a subjective method.