Author:
Mohammed Ahmed A,Jebur Bilal A,Younus Karam M
Abstract
Abstract
The quality of medical image is crucial due to the sensitivity of medical diagnoses. Nowadays medical images are commonly shared between various entities across the medical sector to improve the quality of diagnoses. Thus, watermarking process is usually applied on these images to embed patient’s private information. One of the key challenges is preserving image quality, keeping it clean of distortions after the watermarking process, and sustaining robustness. In this work, a hybrid Discrete Cosine Transform (DCT) and Singular value decomposition (SVD) based image watermarking scheme with chaotic encryption is proposed. The obtained results have demonstrated that the proposed scheme is secure and robust compared to the present schemes. In particular, the results show decent robustness and excellent imperceptibility of watermarked host medical images. Moreover, Peak signal to noise ratio (PSNR), and Normalized Correlation (NC) are used to evaluate the performance of the scheme. The scheme has shown a minimum PSNR of 59 dB and an NC value of 1 with no attacks applied, and not less than 0.5 with the presence of various attacks.
Reference19 articles.
1. Image quality assessment for medical images based on gradient information;Preedanan,2018
2. Improving Lung Lesion Detection in Low Dose Positron Emission Tomography Images Using Machine Learning;Nai,2018
3. A new robust binary image embedding algorithm in discrete wavelet domain;Mohammed,2014
4. Application of the 4-D XCAT phantoms in biomedical imaging and beyond;Segars;IEEE Transactions on Medical Imaging,2017
Cited by
11 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献