二维小波变换在磨粒图像处理中的应用  

Application of 2D Wavelet Transform on Wear Particle Image Processing

作　　者：江良洲[1] 龙凤[1] 杨庆[1] 陈桂明[1] 

机构地区：[1]第二炮兵工程学院装备管理工程系,陕西西安710025

出　　处：《润滑与密封》2010年第7期91-94,共4页Lubrication Engineering

基　　金：国家自然科学基金面上项目(60672108).

摘　　要：将小波理论用于磨粒图像处理,基于磨粒及磨粒图像处理的特点与要求,提出以二维小波分解重构和小波系数矩阵变换为核心的磨粒图像除噪、压缩和增强实现步骤与算法。结果表明,二维小波变换能有效去除噪声,突出图像细节,改善图像质量,提高磨粒特征提取的可靠性;压缩后的图像能保持磨粒特征,且恢复质量好。Wavelet theory was useful for wear particle image processing. Ferrography technique and wear particle image processing was introduced. Based on 2D wavelet decomposition and reconstruction, using wavelet coefficient matrix opera- tor, practical steps and algorism of image denoise, compression and enhancement were presented. Experimental results show that wear particle images from different sources can be denoised effectively using 2D wavelet transform, its object details can be improved, object features in compressed wear particle image and the quality of reconstructed image can be retained.

关 键 词：小波变换 小波系数 铁谱技术 图像处理 

分 类 号：TH117[机械工程—机械设计及理论] TP391[自动化与计算机技术—计算机应用技术]