Contourlet域自适应萎缩阈值去噪方法

受到传输距离、电子干扰等多方面因素的影响,在测量船远程故障视频诊断系统中,地面接收到的设备状态图像不可避免地混合有随机噪声,因此图像去噪是设备状态图像预处理阶段重要的任务之一。Contourlet变换是一种优异的图像去噪工具,但固定的萎缩阈值不能自适应于Contourlet系数的邻域信息。构造了一种利用Contourlet系数邻域信息的自适应萎缩阈值,用该阈值结合Contourlet循环平移方法实现图像去噪,实验结果表明,该方法可以提高去噪后图像的峰值信噪比。

Adaptive shrinkage denoising method in contourlet domain

Suffered by transmission distance,electrical disturbance,etc.,random noise is inevitably interfused equipment state images in system of remote fault diagnosis on the metrical vessel.Hence,image denoising is one of the important tasks for pretreatment of the equipment state image.The contourlet transform is an outstanding tool for image denoising.But the fixed shrinkage threshold is not adaptive to neighbor information of contourlet coefficients.A new adaptive shrinkage threshold in contourlet domain,which makes good use of the neighborhood characteristic of the coefficients,is proposed in this paper.The proposed threshold is used for noise attenuation when combined with the contourlet cycle spinning denoising process.The experiments on test images show that the proposed method outperforms the classical contourlet-based denoising method in terms of PSNR values.