基于MRF模型的金属工件红外热像表面缺陷检测  

An Infrared Thermo Image Processing Framework Based on MRF Model to Detect Surface Defect on a Metal Element

作　　者：谢静[1] 徐长航[1] 陈国明[1] 

机构地区：[1]中国石油大学(华东)机电工程学院,山东青岛266580

出　　处：《石油矿场机械》2012年第11期20-24,共5页Oil Field Equipment

基　　金：国家自然科学基金"面向老龄平台延寿工程的寿命预测与管理理论及方法研究"(50679083)

摘　　要：基于MRF模型图像分割方法,建立了红外热像处理流程,实现金属工件表面缺陷的自动检测。对红外热像进行预处理,得到了具有较强缺陷特征的图像;基于MRF模型对图像进行分割,将缺陷对应的像素分割为单独的一类;进行缺陷类识别及形态学后处理,最终得到完整的缺陷信息。实例分析结果表明:红外热像处理流程可以自动检测金属工件表面缺陷的位置及尺寸信息,适用于粗糙表面工件的缺陷检测。An infrared thermo image processing framework was proposed to complete the detection task using the MRF model-based image segmentation method.Firstly,the preprocessing including a few steps is implemented on the infrared thermo image to get the enhancement image.Secondly,MRF model-based image segmentation method is used to cluster the defect pixels.Lastly,the mean gray level in the original gray level image of clustered pixels is taken as a feature to find the defect cluster and the morphological area opening operator is lastly used get the accurate information of defect.Experimental result shows that the proposed framework has very promising performance and can obtain precise information of defects on a metal element even the element has some rough surface.

关 键 词：红外热像 缺陷检测 MARKOV随机场 面积开算子 

分 类 号：TE927.901[石油与天然气工程—石油机械设备]