欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
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。
英文摘要：
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.
同期刊论文项目
同项目期刊论文
期刊信息
位置：