摘要
提出使用主成分分析(PCA)和支持向量机(SVM)对研磨后的陶瓷零件进行正废品检测。首先利用主成分分析法对研磨后的陶瓷零件进行特征提取,然后在支持向量机的算法上进行识别验证。通过实验分析,在阈值取0.93时,对研磨后的陶瓷零件正废品检测的识别率最高。
A new method of Ceramic Parts After Grinding recognition based on Principal component analysis(PCA)and support vector machine(SVM).Ceramic parts After Grinding images are translated into feature extraction by principal component analysis(PCA),which are applied to training support vector machine(SVM)method for recognition.Through the experimental analysis,when the threshold value is 0.93,the recognition accuracy is the highest.
作者
李颜瑞
Li Yanrui(Information Engineering Department,Shan Xi Institute of Mechanical an d Electrical Engineering,Changzhi,Shanxi 046011,China)
出处
《信息记录材料》
2021年第5期8-10,共3页
Information Recording Materials
基金
山西机电职业技术学院教科研项目(JKY-17025)。
关键词
陶瓷零件
主成分分析
特征提取
支持向量机
Ceramic parts
Principal component analysis
Feature extract
Support vector machine
