基于变换折衷阈值的多分辨图像双边滤波仿真

Simulation of Multi-resolution Image Bilateral Filtering Based on Transform Compromise Threshold

为了有效解决多分辨图像内存在噪声的问题,提出一种基于视觉灵敏度的多分辨图像双边滤波算法。通过粗糙集理论初步判断多分辨图像内的噪声,利用视觉灵敏度对判断结果展开修正。通过双边滤波器将噪声图像分解为高低频两个部分,高频部分使用Curvelet变换折衷阈值,根据设定的阈值保留多分辨图像中更多的边缘纹理细节。将低频图像和处理后的高频图像重构,获取经过滤波处理后的多分辨图像。实验结果表明,所提算法可以精准检测出多分辨图像内存在的噪声,同时能够获取满意的多分辨图像滤波结果。

In order to effectively solve the problem of noise in multi-resolution images,this article put forward a bilateral filter algorithm for multi-resolution images based on visual acuity.Firstly,rough set theory was adopted to preliminarily determine the noise in multi-resolution images.Then,visual sensitivity was used to correct the judgment result.Meanwhile,the noisy image was divided into high and low-frequency parts by a Bilateral filter.In the highfrequency part,the compromise threshold of the Curvelet transform was used to retain more edge texture details in the multi-resolution image.Moreover,low-frequency images and high-frequency images were reconstructed to obtain the filtered multi-resolution images.Experimental results show that the proposed algorithm can accurately detect the noise in multi-resolution images and obtain satisfactory filtering results.