铁谱图像典型磨粒自动提取方法研究  

Research on automatic extraction of wear particles for ferrographic images

作　　者：张云强[1] 张培林[1] 王国德[1] 

机构地区：[1]军械工程学院,石家庄050003

出　　处：《计算机工程与应用》2013年第16期175-178,共4页Computer Engineering and Applications

基　　金：国家自然科学基金项目(No.50705097);清华大学摩擦学国家重点实验室开放基金资助项目(No.SKLTKF09B06)

摘　　要：为了提高铁谱分析自动化程度,结合脉冲耦合神经网络(PCNN)和数学形态学,提出了一种铁谱图像典型磨粒自动提取方法。利用综合色距函数将彩色铁谱图像三通道问题转化为单通道问题,使分割问题简化;利用简化PCNN间接实现铁谱图像分割,并采用数学形态学对获得的二值图像进行处理;运用数学形态学中连通域提取算法自动提取图像中的典型磨粒。实验结果表明:与其他方法相比,该方法能快速有效地分割铁谱磨粒图像,并实现铁谱图像中典型磨粒的自动提取。To improve the automation of ferrography, mathematical morphology is combined with Pulse Coupled Neural Network （PCNN）, then an automatic extraction method of wear particles for ferrographic images is proposed. This method employs synthe- sis color distance function to transform three-channel issue of color ferrographic images into single-channel issue. Thus, image segmentation is simplified. Then ferrographic images are indirectly segmented by simplified PCNN, and achieved binary images are processed utilizing mathematical morphology. With connected domain extraction algorithm of mathematical morphology, typical wear particles are extracted automatically. Experiments results show that compared with other methods, the proposed method can segment color ferrographic images effectively and realize automatic extraction of typical wear particles.

关 键 词：铁谱技术 脉冲耦合神经网络 数学形态学 典型磨粒 图像分割 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]