一种新的基于PCNN的自适应强去噪方法

Novel adaptive denoising method for extreme noise based on PCNN

为了实现椒盐噪声的有效去除和图像细节及纹理的有效保留,提出了一种新的基于PCNN(Pulse Coupled Neural Network)的自适应滤波方法ADEN(Adapative Denosingmethod for Extreme Noise)-PCNN.该方法引入了像素受污染状态的甄别机制,只对被污染的像素进行降噪处理,保证了去噪的同时不损坏图像信息,实现了图像的细节和纹理的有效保留;为了确保图像质量,在面向图像降噪的PCNN神经网络阵列结构中引入了自组织机制,可以自动地估计噪声的强度信息并进行PCNN网络中神经元连接方式的自组织转换,此外引入了自适应机制,根据噪声强度的估计信息,自动进行滤波次数的优选,增强自适应能力.实验结果表明所提方法较常规方法和其他同类方法在去噪效果、保留图像细节方面展现出明显的优势.

To implement the removal of salt and pepper noise effectively and the conservation of image details and textures, a novel adaptive denoising method for extreme noise based-on pulse coupled neural network （ADEN-PCNN） was proposed. A kind of detection mechanism was applied to discriminate whether a given pixel was corrupted or not, and only the corrupted pixels must be denoised so that the original image information could not be damaged and the details as well as the textures of the images elould be conserved effective- ly. To improve the image quality, the self-organization mechanism was introduced into PCNN array framework, thus the neighboring connection modes of neurons in the PCNN could switch automatically. Furthermore, an adaptive mechanism was used to automatically select the optimal filtering times based on the estimated noise intensity to enhance adaptability of algortihm. Experiment results indicate that this method presented is more preponderant than the conventional methods and other congeneric methods in removing noise and conserving image details.