基于图像处理的磨粒特征定量分析系统

Quantitative Analysis System of Wear Particle Characteristics Based on Image Processing

为了提高铁谱图像的分析效率并提取磨粒的特征参数,提出了一种基于图像处理的磨粒特征定量分析方法,并在LabVIEW平台上进行了设计与实现。首先,对铁谱图像联合背景纠正法进行局部阈值分割以降低不均匀光照的影响;其次,通过形态学运算断开磨粒间的黏连,填充内部孔洞;最后,在LabVIEW平台上开发了磨粒特征定量分析系统,实现了磨粒几何参数的测量并与相关文献及软件的结果进行了对比分析。实验结果表明,该系统能够在不均匀光照的条件下实现磨粒图像的阈值分割,定量输出磨粒覆盖率及每个磨粒的面积、最大直径、圆度等特征参数并可保存至数据库文件中,达到了设计要求。

In order to improve the analysis efficiency of ferrographic Image and extract the characteristic parameters of wear particles, a quantitative analysis method of wear particle characteristics based on image processing is proposed and designed on the platform of LabVIEW.Firstly, local threshold segmentation is performed on ferrogram image combined with background correction method to reduce the effect of uneven illumination;Secondly, the adhesion between the abrasive particles is broken and the internal holes are filled by morphological operation;Finally, a quantitative analysis system of abrasive characteristics is developed on LabVIEW platform, which realized the measurement of geometric parameters of abrasive particles and is compared with the results of related literature and software.The experimental results show that the system can achieve the threshold segmentation of the wear debris image under the condition of uneven illumination, quantitatively output the wear debris coverage rate and the characteristic parameters of each particle, such as the area, maximum diameter and roundness, all of the above can be saved to the database file, which has achieved the design requirements.