C. Jin
Fuzzy clustering, neural network, digital watermark, robustness, imperceptibility
Digital watermark has been proposed as an effective method to protect the copyright of multimedia data. An adaptive watermark system of still image in discrete cosine transform (DCT) domain is proposed. By exploiting the luminance and texture characteristics of human visual system (HVS) and considering properties of DCT block coefficient, a soft computing framework is designed. It adopts the feature vectors composed the luminance and texture information of each DCT block, the fuzzy clustering (FC) for more reliable classifying to DCT blocks, and neural network (NN) for determining adaptively the best watermark embedding strength of each DCT block are used. The experimental results show that the proposed system are robust against attacks most commonly used image processing algorithms and provides very good results in term of image imperceptibility.
Important Links:
Go Back
