一种改进的增维型双边滤波的快速算法
A fast implementation of improved bilateral filter based on ascending dimension
李俊峰 1杨丰 1黄靖1
作者信息
- 1. 南方医科大学生物医学工程学院,广东广州510515
- 折叠
摘要
双边滤波算法是一种在去噪的同时能很好地保留图像边缘等细节信息的非线性滤波技术.针对双边滤波器计算耗时、难于用于实时系统,本文提出一种改进的增维双边滤波的快速算法.该算法通过对双边滤波器的线性化和图像矩阵的映射,由FFT完成线性卷积；然后将计算结果逆映射还原为图像矩阵；最后依据图像的原始坐标和灰度值的差异进行像素补值,达到双边滤波快速实现的目的.五幅测试图像在不同噪声水平下的实验表明:本方法避免了插值过程,提高了计算效率,改进的双边滤波器在滤波精度与传统双边滤波器相仿的同时,运算时间仅为传统双边滤波器的3.6％左右.
Abstract
The bilateral filter is a nonlinear filter which smoothes an image signal for denoising while preserving edges and details.This paper presents a fast approximate algorithm of an improved growth-dimensional bilateral filtering,to overcome problems of large computational complexity and difficult for real-time systems.The algorithm starts with linearization for system of bilateral filter and the image matrix mapping,so that the filter can form linear convolutions through FFT.In a next step,the above calculation will be restored to the image matrix by inverse mapping.Finally,all pixels fill values in accordance with the difference of the coordinates and grayscale of the original image,to achieve the purpose of achieving important acceleration of the bilateral filter.Experimental which five images are tested at different noise levels proved that the method improves the computational efficiency due to interpolation can be avoided.The running time of improved bilateral filter is 3.6％ of traditional bilateral filter,while the filtering accuracy is close to the traditional bilateral filter.
关键词
双边滤波/去噪/增维/线性卷积/补值Key words
bilateral filter/denoising/ascending dimension/linear convolution/value-filled引用本文复制引用
基金项目
国家自然科学基金(61271155)
国家自然科学基金青年基金(81000642)
出版年
2013
NETL
NSTL
维普
万方数据