Adaptive Image Watermarking Approach Based on Kernel Clustering and HVS

Abstract

In this paper, an adaptive image watermarking approach is introduced, which consists of kernel fuzzy c-means (KFCM) clustering algorithm and human visual system (HVS). Firstly, the host image is divided into image blocks and block-wise DCT transform is accomplished. Then, three local features of image blocks are extracted from its DCT coefficients, and these features are used to train KFCM in order to select the embedding position and determine the embedding strength of image blocks adaptively. The experimental results show the proposed algorithm is robust to common attacks such as JPEG, filtering, noise addition, scaling, sharpen, etc.