Title: Robust zero-watermarking algorithm for medical images based on K-means and DCT

Authors: Wenxing Zhang; Jingbing Li; Uzair Aslam Bhatti; Mengxing Huang; Jixin Ma; Cheng Zeng

Addresses: School of Information and Communication Engineering, Hainan University, Haikou, Hainan, China ' School of Information and Communication Engineering, Hainan University, Haikou, Hainan, China ' School of Information and Communication Engineering, Hainan University, Haikou, Hainan, China ' State Key Laboratory of Marine Resource Utilisation in the South China Sea, Hainan University, Haikou, Hainan, China ' School of Computing and Mathematical Sciences, University of Greenwich, London, England, UK ' School of Information and Communication Engineering, Hainan University, Haikou, Hainan, China

Abstract: To better protect patient information in medical images and improve the security of medical image transmission, this paper studies a robust watermarking algorithm for medical images based on K-means and Discrete Cosine Transform (DCT). Firstly, the watermark is pre-processed by chaotic encryption to make it more secure. Then, the K-means clustering algorithm is used to classify the grey values of the pixels in the medical image to obtain the feature image after the cluster segmentation; then the DCT is used to extract the feature coefficient matrix and transform it into the feature hash sequence of the image. Finally, the zero-watermark technology is used to combine the feature hash sequence with the encrypted watermark to realise the embedding and extraction of the watermark. Experiments show that the algorithm not only can resist conventional attacks, but also has good robustness against geometric attacks.

Keywords: medical image; K-means clustering; feature vector; DCT; zero watermark.

DOI: 10.1504/IJWMC.2022.126368

International Journal of Wireless and Mobile Computing, 2022 Vol.23 No.2, pp.163 - 172

Received: 08 Oct 2021
Accepted: 02 Apr 2022
Published online: 24 Oct 2022 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article