一种针对椒盐噪声的高速自适应中值滤波算法
2021-10-24马炼李林
马炼 李林



摘要: 大数据量高清视频流在拍摄、传输等过程中可能受到干扰而产生椒盐噪声。由于其具有数据传输速度快的特点,为了确保它的实时性,进一步提高滤波算法的时间效率和计算效率,对现有的自适应中值滤波进行了改进,提出了一种高速自适应中值滤波算法。滤波过程主要分为噪声点检测和噪声去除两个阶段。其中,在噪声点检测阶段,根据椒盐噪声的极值特性,将图像的像素点分为噪声点和信号点;在噪声去除阶段,信号点保持原值,噪声点根据自适应中值进行赋值。实验结果表明,该算法相较于多种中值滤波方法具有很好的滤波作用,以及很大的速度提升。
关键词: 图像去噪; 中值滤波; 自适应; 椒盐噪声; 高速
中图分类号:TP391 文献标识码:A 文章编号:1006-8228(2021)10-68-04
A high speed adaptive median filtering algorithm for salt and pepper noise removing
Ma Lian, Li Lin
(School of Electrical and Electronic Engineering, Wuhan Polytechnic University, Wuhan, Hubei 430000, China)
Abstract: The high-definition video stream with large amount of data may be interfered in the process of shooting and transmission, resulting in salt and pepper noise. Because of its fast data transmission speed, in order to ensure its real-time performance, further improving the time efficiency and calculation efficiency of the filtering algorithm, the existing adaptive median filter is improved, and a high-speed adaptive median filter algorithm is proposed. The filtering process is divided into two stages: noise point detection and noise removing. In the noise point detection stage, according to the extreme value characteristics of salt and pepper noise, the image pixels are divided into noise points and signal points; in the noise removing stage, the signal points keep the original value, but the value of the noise points are assigned according to the adaptive median. The experiment results show that the algorithm has a good filtering effect compared with a variety of median filtering methods, and greatly improves the speed.
Key words: image denoising; median filtering; self-adaptive; salt and pepper noise; high speed
0 引言
随着社会智能化不断推进,图像的处理需求越来越大。无论是零件制造还是红外成像技术、监控视频技术,每一类都对图像处理有数以亿计的需求。而在图像采集、傳输和接收的过程中,由于环境、温度等不稳定因素,常常会使得图像受到脉冲噪声的影响。噪声的加入会使得图像处理的过程变得复杂,更可能影响到图像分析与处理的最终结果。因此如何有效快速的去除噪声具有十分现实及重要的意义。
一般随机噪声分为脉冲噪声、窄带噪声和起伏噪声。本文研究的主要是脉冲噪声,而固定值脉冲噪声也称为椒盐噪声,其灰度以等概率取最小灰度值和最大灰度值,属于突发性的,对数字通信影响大。……
