Image processing applications in general consume more time. Same is true for image watermarking as well. For this purpose, it is crucial to keep in mind the image quality and the running time spans post processing. In this paper, a novel neuro fuzzy architecture for gray-scale image watermarking using fractal dimensions is proposed. The development also involves the tradeoff between the imperceptibility and robustness of the watermark embedding scheme. To this end, a very fast single layer feed forward neural network known as Extreme Learning Machine (ELM) is employed for image watermarking. The neural machine is combined with a Mamdani Fuzzy Inference System (FIS) to build a Neuro– Fuzzy architecture. The analysis is carried out in the initial stages using fractal analysis. The robustness of the scheme is evaluated by subjecting the signed images to StirMark attacks.
|Name||Proceedings of the International Joint Conference on Neural Networks|
|Conference||IEEE International Conference on Neural Networks|
|Period||1/01/11 → …|