期刊名称：International Journal of Image Processing (IJIP)
电子版ISSN：1985-2304
出版年度：2012
卷号：6
期号：6
页码：478-487
出版社：Computer Science Journals
摘要：Teleradiology using internet can offer patients in remote locations the benefit of diagnosis and advice by a super specialist present in a metropolis. However, exchange of vital information such as the clinical images and textual facts in the public network poses challenges of transmission of large volume of data as well as prevention of the distortion of the images. In this paper, a novel application system to jointly compress and watermark the medical images in a near-lossless, image-adaptive adaptive fashion is proposed to address these challenges. The system design uses genetic algorithm for adaptive wavelet coding to generate compressed data and integration of dual watermarks to realize the security and authentication of the compressed data. The GA-based image adaptive compression provides feasible way to obtain optimal compression ratio without compromising the image fidelity upon subsequent watermarking. A multi-gene approach, with one gene coding for the embedding strength of the robust watermark and the other for the number of bits for embedding the semi-fragile watermark is used for optimal image-adaptive watermarking. A multi-parameter fitness function is designed to address the conflicting requirements of image compression, authenticity and integrity associated with teleradiology. Experimental results show the ability of the system to detect tampering and to limit the peak error between the original and the watermarked images. Moreover, as the watermarking is performed on the compressed image, the overhead for watermarking gets reduced.
