基于Contourlet-RVM航空构件断口图像识别方法研究  

RECOGNITION METHOD OF FRACTURE IMAGE OF AERIAL MATERIAL BASED ON CONTOURLET TRANSFORM AND RELEVANCE VECTOR MACHINE

作　　者：梁鹏[1,2] 李志农[1] 

机构地区：[1]南昌航空大学无损检测技术教育部重点实验室,南昌330063 [2]郑州大学机械工程学院,郑州450001

出　　处：《机械强度》2013年第4期395-399,共5页Journal of Mechanical Strength

基　　金：国家自然科学基金(51261024,51075372);无损检测技术教育部重点实验室开放基金(ZD200829003);江西省研究生教育创新基地资助~~

摘　　要：Contourlet变换的少量系数能有效捕捉图像中的边缘轮廓,关联向量机(relevance vector machine,RVM)具有很好的泛化能力,能对类别的归属给出一种概率度量。结合Contourlet变换和RVM的各自优点,提出一种基于Contourlet-RVM的航空构件断口形貌识别方法,即以Contourlet变换进行特征提取,以RVM为分类器,对金属断口形貌进行识别。同时,将提出的方法与Contourlet-SVM识别方法进行对比分析。实验结果表明,提出的方法是有效的,不论在正确识别率方面,还是在训练速度方面,Contourlet-RVM识别方法都优于Contourlet-SVM识别方法。A few of coefficients of Contourlet transform can effectively capture the image edges.Relevance vector machine（RVM） has good generalization ability,it can give a probability measure in the classification.Combined the respective advantage of Contourlet transform and RVM,a Recognition method of fracture image of aerial material based on Contourlet-RVM is proposed.In the proposed method,Contourlet transform is used as the feature extraction,RVM as a classifier.The proposed method has been successfully completed in the recogniton of metal fracture image.At the same time,the proposed method is compared with the Contourlet-SVM recognition method.The experiment result shows that the proposed method is very effective.Whether in the correct recognition rate,or in the training speed,the Contourlet-RVM recognition method is superior to the Contourlet-SVM recognition method.

关 键 词：Contourlet变换 关联向量机 金属断口 模式识别 特征提取 

分 类 号：TG113[金属学及工艺—物理冶金] TP391.4[金属学及工艺—金属学]