基于感觉亮度的脉冲耦合神经网络模型

A Pulse Coupled Neural Network Model Based on Sensory Luminance

在脉冲耦合神经网络模型中,为了寻找最优衰减时间常数,基于韦伯-费赫涅尔定律,考虑到人眼的感觉亮度与实际亮度对数之间的线性关系,提出将人眼的感觉亮度作为动态阈值的衰减时间常数,使神经元动态阈值的衰减速度更符合人眼的亮度感觉。对含有弱边界、对比度低的图像目标进行仿真对比实验。实验结果表明,提出的算法性能优于传统脉冲耦合神经网络模型。

In order to find the optimal decay time constant in the pulse coupled neural network model, based on Weber-Fechne law,considering the linear relationship between the sensory luminance of human eye and the actual logarithm of Luminance, this paper proposes that the sensory luminance of human eye is taken as the decay time constant of the dynamic threshold, the attenuating speed of the dynamic threshold value of neurons is more in line with the luminance perception of human eyes. Simulation experiments are carried out on the image target with weak boundary and low contrast. The experimental results show that the proposed algorithm is better than the traditional pulse coupled neural network model.