A Feature-Based Hybrid Medical Image Watermarking Algorithm Based on SURF-DCT

Researching digital watermarking algorithms with better transparency and robustness is essential for protecting the copyright of medical images. Security issues in medical images are increasing day to day with the increase of health data all around the globe. This paper proposed a new algorithm image-based zero-watermarking using SURF-DCT perceptual hashing (Speeded Up Robust Features and Discrete Cosine Transform). Firstly, by using the SURF features of the medical image are taken to perform watermark embedding and extraction. Then by using perceptual hashing and quantization to generate hashing sequences to capture semi-global geometric characteristics. Next, used chaotic maps to encrypt the watermarking and embed it in the medical image after extracting the final features which are used as a hash value. Finally, the correlation coefficient is used to measure the performance of the proposed algorithm with other algorithms against the embedded and extracted watermarking sequences. The experimental results show that the proposed algorithm is robust to many attacks such as clipping, JPEG compression, and filtering. It also has good resistance to attacks such as rotation and noise.