Using Novel, Flexible Benchmarking Tool for Robustness Evaluation of Image Watermarking Techniques.
Ranjana Shende · 2013
The main idea of this paper is to propose an innovative ,benchmarking tool based on genetic algorithm to evaluate robustness of visible and invisible watermarking techniques. Image fidelity metrics such as mean square error(MSE), signal to noise ratio(SNR),peak signal to noise ratio(PSNR), weighted peak signal to noise ratio(WPSNR) are being used. However, when large quantities of data are to be assessed, subjective metrics such as mean opinion score(MOS),signal to noise ratio(SNR),peak signal to noise ratio(PSNR) are not pragmatic since it needs experts and inordinate amount of time.PSNR and WPSNR are independent of human visual system(HVS) parameters and hence they are inappropriate scales to measure potential research results. This brings out a new image fidelity metric called Enhanced Weighted peak signal to noise ratio(EWPSNR) which is experimentally proven to be better than PSNR and WPSNR.