×

Neural network-based digital image watermarking algorithm. (Chinese. English summary) Zbl 1150.68367

Summary: A novel digital image watermarking algorithm based on the association memory ability of neural networks is proposed in this paper. The watermark is stored in a neural network first and then embedded into the significant and detail wavelet coefficients of original image. The inverse embedding process is first used to extract watermark, then the extracted watermark is processed using the association memory ability of neural networks. Experimental results show that the algorithm can improve the watermark image quality which is extracted from the watermarked image attacked by JPEG compression, noise adding, filtering, cropping etc.

MSC:

68P25 Data encryption (aspects in computer science)
68T05 Learning and adaptive systems in artificial intelligence
42C40 Nontrigonometric harmonic analysis involving wavelets and other special systems
68U10 Computing methodologies for image processing
PDFBibTeX XMLCite