Hierarchical Clustering Based Medical Video Watermarking Using DWT and SVD

Abstract

A video watermarking technique is proposed in for securing medical videos by adapting new clustering algorithm. As per law the information need to keep secure in order to protect the privacy of the patient. Cybercriminals may sell the medical video with the patient’s fake identities which leads to data insecurity and various criminal activities. And so the technique is mainly for maintenance and confidentiality purpose of medical video. This is designed in a way to cluster the medical video frames which incorporates a Euclidean distance of frames. The Hierarchical representation is constructed for every cluster to choose key frame with the entropy and Probability Density Function (PDF) value of the frames. Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) improve the performance of the watermark embedding process, where the watermark image is chosen to embed into the selected key frames for every cluster. The experimental results show that the proposed scheme has higher robustness and imperceptibility against various image and video processing attacks.