摘要
在研究带钢表面缺陷图像去噪算法的过程中,为了在去除图像中的一些例如噪声等不相关的信息的同时且要保留图像一些细节信息的不丢失,研究了一种基于BM3D的带钢表面图像去噪方法和对该算法的工作原理进行了叙述。通过做几组对比实验选择出了BM3D算法中最适合缺陷图像去噪的一些参数值,将设定好参数值的BM3D算法与传统的几种经典去噪算法相比较,实验结果表明,无论从主观判断标准还是从客观判断标准来看,BM3D算法在图像去噪方面都取得了不错的效果。
In the process of studying the image denoising algorithm of strip surface defect,in order to remove the image noise such as some of the information which is not related simultaneously and retain the image details which is not lost,a method of strip surface image denoising based on BM3D is studied and it describes the working principle of the algorithm.By doing the several groups of experiments to select the most suitable parameters of some defects of image denoising algorithm in BM3D value,comparing the BM3D algorithm with setting good parameters and the traditional denoising algorithm,the experimental results show that whether from the subjective judgment standard or from the objective judgment standard,the BM3D algorithm has obtained the good effect in the image denoising aspect.
作者
吕琳
汤勃
孔建益
王兴东
LV Lin;TANG Bo;KONG Jian-yi;WANG Xing-dong(Key Laboratory of Metallurgical Equipment and Control of Ministry of Education,Wuhan University of Science and Technology,Hubei Wuhan 430081,China;School of Mechanical and Automation Engineering,Wuhan University of Science andTechnology,Hubei Wuhan 430081,China)
出处
《机械设计与制造》
北大核心
2018年第7期104-106,110,共4页
Machinery Design & Manufacture
基金
冶金装备及其控制教育部重点实验室基金(2013B01)
