基于小波域双谱分析的磨粒图像多尺度形状特征提取  

EXTRACTING MULTISCALE SHAPE FEATURE OF WEAR PARTICLE IMAGE BASED ON WAVELET DOMAIN BISPECTRAL ANALYSIS

作　　者：郭恒光[1] 瞿军[2] 

机构地区：[1]海军航空工程学院研究生管理大队,山东烟台264000 [2]海军航空工程学院飞行器工程系,山东烟台264000

出　　处：《计算机应用与软件》2016年第9期224-226,278,共4页Computer Applications and Software

摘　　要：磨粒图像的形状特征是识别典型磨粒的主要参数,而这些典型的磨粒反映机械设备零部件的运行状态。根据双谱分析不能抑制非高斯噪声干扰的缺点,提出基于小波域双谱分析的磨粒图像多尺度形状特征提取方法。首先对磨粒图像进行小波包多尺度分解,再对低频部分进行重构,达到去噪和磨粒图像多尺度表征的目的。然后采用Radon变换将重构后的图像映射到一组一维投影,对一维信号进行双谱分析,得到双谱不变量特征,作为磨粒图像的多尺度形状特征参数。实验结果表明,该方法能够很好地结合小波包变换和双谱分析的优点,获得的多尺度形状特征参数能够有效地用于磨粒类型识别。Shape feature of wear particle image is the principal parameter for typical wear particle recognition, and these typical wear particles can reveal the operation condition of machine spare parts. For the shortcoming of bispectral analysis that it cannot suppress non-Gaussian noise interference,we propose the wavelet domain bispectral analysis-based muhiscale shape feature extraction method for wear particles im- age. First, the method makes wavelet packet muhiseale decomposition on wear particle image, and then reconstructs its low frequency compo- nent to reach the goals of denoising and multiscale eharacterisation of wear particle image. The next, the method uses Radon transform to map the reconstructed images onto a set of one-dimensional projections, and carries out bispectral analysis on one-dimension signal to get the feature of bispeetral invariants ,which are used as the multiscale shape feature parameter of wear particle image. Experimental resuh demonstrates that the method proposed in this paper can well combine the advantages of wavelet packet transform and bispeetral analysis, and the derived multi-scale shape feature parameter can be effectively used for wear particle type recognition.

关 键 词：磨粒图像 多尺度形状特征 小波包变换 双谱分析 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]