基于随机共振的FHN神经元并联阵列图像复原

Image Restoration Based on Stochastic Resonance in Parallel Array of FitzHugh-Nagumo Neuron

针对在低峰值信噪比(PSNR)条件下传统灰度图像复原方法处理噪声图像效果差且会丢失一些图像的细节信息的问题,提出了一种Fitz Hugh-Nagumo(FHN)神经元并联阵列模型,可以在低PSNR条件下复原噪声灰度图像并且更好的保留图像细节。上述方法用行列扫描将二维灰度图像转换成一维信号,然后通过信号幅值调制将一维信号转换为一维二进制脉冲幅值调制(BPAM)信号,将BPAM信号输入到FHN并联阵列模型进行随机共振。最后,将FHN阵列输出信号通过解调,反扫描等操作恢复为二维灰度图像,并基于PSNR分析图像复原效果。结果表明:FHN并联阵列模型可以有效地共振低PSNR条件下的噪声,图像复原效果明显优于传统图像复原方法,可获得较大的PSNR。上述方法为低PSNR条件下的灰度图像复原提供了新思路。

Aiming at the problem that the traditional gray-scale image restoration method has poor effect in processing noisy images and will lose some image details under the condition of low peak signal-to-noise ratio(PSNR),a parallel array model of Fitz Hugh-Nagumo(FHN) neurons was proposed, which can restore noise grayscale images under low PSNR conditions and the image details are better preserved. The row-column scanning method was used to convert the 2D grayscale image into a 1D signal, and then the 1D signal was converted into a binary pulse amplitude modulation(BPAM) signal by signal modulation. The modulated signal was input to an FHN parallel array for stochastic resonance. Finally, the array output signal was restored to a 2D gray image, and the image restoration effect was analyzed based on the PSNR index. The results show that the FHN parallel array model can effectively resonate the noise under the condition of low PSNR, the image restoration effect is obviously better than the traditional image restoration method, and a larger PSNR can be obtained. It provides a new idea for grayscale image restoration in low PSNR environment.