计算机工程

• 图形图像处理 • 上一篇    下一篇

基于编码稀疏表示的柔索机器人监测图像去噪算法

陈鹏旭,林茂松,梁艳阳,刘宏伟   

  1. (西南科技大学 信息工程学院,四川 绵阳 621000)
  • 收稿日期:2016-02-29 出版日期:2017-03-15 发布日期:2017-03-15
  • 作者简介:陈鹏旭(1989—),男,硕士研究生,主研方向为图像处理、柔索机器人;林茂松,教授、博士;梁艳阳,副教授、博士;刘宏伟,讲师。
  • 基金项目:
    四川省科技计划项目“面向稻田监测的柔索悬吊机器人运动控制关键技术研究”(2014NZ0118 )。

Wire Suspended Robot Monitoring Image Denoising Algorithm Based on Encoding with Sparse Representation

CHEN Pengxu,LIN Maosong,LIANG Yanyang,LIU Hongwei   

  1. (School of Information Engineering,Southwest University of Science and Technology,Mianyang,Sichuan 621000,China)
  • Received:2016-02-29 Online:2017-03-15 Published:2017-03-15

摘要: 在柔索机器人实际工作环境中,获取到的监测图像通常夹杂了混合噪声。为去除该混合噪声,给出一种混合噪声图像去噪算法,监测图像由加性高斯白噪声和脉冲噪声所组成。针对脉冲噪声,提出用2个阈值对噪声进行检测,在现有基于加权编码的算法上将图像稀疏表示以及非局部相似先验融入到去噪模型,最终得到去噪图像。实验结果表明,该算法在不同的噪声比率下有较好的去噪表现,且图像的纹理细节也得到了较好的保留,实用性较强。

关键词: 混合噪声, 噪声检测, 稀疏表示, 非局部相似, 图像去噪, 柔索机器人

Abstract: The actual wire suspended robot monitoring image is usually corrupted by the mixed noise in practical applications.This paper proposes a mixed noise image denoising algorithm for the mixed noise removal.The image consists of Additive White Gaussian Noise(AWGN) and Impluse Noise(IN).Aiming at pulse noise,two thresholds are proposed to detect noise.The image sparse representation and nonlocal similarity prior are integrated into the denoising model based on the existing weighted coding algorithm.Finally the denoising image is obtained.Experimental results show that the proposed algorithm under different noise ratio has good recovery performance,retains the texture details of the image,and has strong practicability.

Key words: mixed noise, noise detection, sparse representation, nonlocal similarity, image denoising, wire suspended robot

中图分类号: