基于自适应神经网络模糊系统的混沌音频水印盲检测

自适应神经网络模糊推理系统(AdaptiveNeuro FuzzyInferenceSystem, ANFIS)是将Sugeno一阶模糊系统以网络的形式来实现而得到的一种多输入单输出的神经网络。它能够很好的模拟出输入输出之间的关系,且收敛速度快,误差小,所需训练样本少,非常有利于水印信号的盲分离。利用ANFIS良好的自适应控制能力提出了一种具有较强鲁棒性的DCT域音频水印盲检测算法,实验证明,该水印检测算法准确性高,时间代价小,具有较强的抗攻击性,很有实用价值。

Blind detection of chaotic digital audio watermark in DCT domain based on ANFIS

Adaptive Neuro-Fuzzy Inference System(ANFIS) is a neural network system with one input and several outputs, which is got through achieving one step sugeno fuzzy system by the format of network. It can simulate the connection of the in-out very well, and its constringency is very soon, error is very little and the necessary swatch is little, which are very favourable for blind separation of watermark signals.Based on the upstanding adaptive control ability of ANFIS, a strongly robust audio watermarking algorithm in DCT domain was given in this paper. Experiments show that the performance in watermark detection is high, the time expense is litlle, the resisting to attacks is strong and the imperceptibility is good.