Authentication of medical images through a hybrid watermarking method based on Hermite-Jigsaw-SVD

Abstract

This work presents a watermarking algorithm applied to medical images by using the Steered Hermite Transform (SHT), the Singular Value Decomposition (SVD), and the Jigsaw transform (JS). The principal objective is to protect the patient's information using imperceptible watermarking and preserve its diagnosis. Thus, the watermark imperceptibility is achieved using the high-order Steered Hermite coefficients, whereas the SVD decomposition and the JS ensure the watermark against attacks. We use the medicine symbol Caduceus as a watermark. The metrics employed to evaluate the algorithm's performance are the Peak Signal-to-Noise Ratio (PSNR), the Mean Structural Similarity Index (MSSIM), and the Normalized Cross-Correlation (NCC). The evaluation metrics over the watermarked image show that it does not suffer quantitative and qualitative changes, and the extracted watermark was recovered successfully with high PSNR values. In addition, several watermark extraction tests were performed against geometric and common processing attacks. These tests show that the proposed algorithm is robust under critical conditions of attacks, for example, against nonlinear smoothing (median filter), high noise addition (Gaussian and Salt & Pepper noise), high compression rates (JPEG compression), rotation between 0 to 180 degree, and translations up to 100 pixels.

Bio-Inspired Watermarking Method for Authentication of Fundus Images in Computer-Aided Diagnosis of Retinopathy

“…The present article is an extension of a previous work published in [55]. In that work, we proposed a hybrid watermark method based on the SHT, SVD, and JST.…”

“…In this paper, we propose to use a variation of the algorithm presented in [55], applied to RGB fundus images, and evaluate whether the watermark insertion process modifies the DR diagnosis.…”

“…Thus, the main differences with the previous work are listed as follows: (i) The proposed watermarking method was adapted and tested on RGB fundus images instead of gray-scale images, as was reported in [55]. (ii) The fundus images were first transformed into the Y'CbCr color model, then the luma channel was selected to insert the watermark, and the SHT for 2D images (Equations ( 1) and ( 4)) was applied.…”

“…(ii) The fundus images were first transformed into the Y'CbCr color model, then the luma channel was selected to insert the watermark, and the SHT for 2D images (Equations ( 1) and ( 4)) was applied. (iii) The watermark was embedded into the blood vessel patterns extracted by the SHT in the luma channel, obtaining in consequence a natural and automatic ROI-based watermarking method, and differing from [55] where the watermark is embedded in the whole image. (iv) The encryption security of the watermark was increased by using blocks of 1 × 1 of the JST.…”