NVF-Guided Adaptive DCT Watermarking for Binary Images via Hopfield Neural Associative Recall
NVF-Guided Adaptive DCT Watermarking for Binary Images via Hopfield Neural Associative Recall
Simin Mansouri Boroujeni1 Ayoub Taheri2
1) Department of Statistics University of Payame Noor P.O. Box 19395-4697 Tehran, Iran s_
2) Department of Computer Engineering Faculty of IT University of Payame Noor P.O. Box 19395-4697 Tehran, Iran
IOI Code
:
ACCA-ACAZHZ
Publication :
4th International Congress on Science, engineering & New Technologies(secongress.com)
Abstract :
This paper presents a novel hybrid blind watermarking framework that bridges frequency-domain adaptive embedding with neural associative memory for Binary images. By applying Gaussian low-pass filtering pre-processing to Binary host media, local spatial NVF masking is computed to dynamically scale the DC coefficient modulation factor across 8 × 8 DCT block clusters. Furthermore, a Discrete Hopfield Neural Network is integrated to store watermark spatial distribution topologies and key states. Experimental evaluations demonstrate that the proposed system mitigates the catastrophic noise failure typical of classic Binary DCT schemes, providing robust blind retrieval and visual quality across varied Binary media types.
Keywords : binary image noise visibility function (nvf) bit error rates (ber) hopfield neural network (hnn)