Journal of Jilin University Science Edition
Previous Articles Next Articles
WANG Hui, SONG Shuyun
Received:
Online:
Published:
Contact:
Abstract: In order to get better result of image classification a nd improve the efficiency of image classification, we proposed image classificat ion algorithm based on kernel principal component analysis and relevance vector machine (RVM). Firstly, a large number of images were collected to establish the image database, and features were extracted. Secondly, kernel principal compone nt analysis was used to select features and reduce dimension of image to reduce the number of image features and eliminate some small features. Finally, image c lassifier was constructed by training of releva nce vector machine, and 3 kinds of standard image databases were used to pe rform image classification experiments. The experimental results show that, for 3 kinds of standard image databases, the image classification accuracies of the proposed algorithm are more than 95%, which is much higher than that of oth er classification algorithms, and the image classification speed can meet practi cal requirements of the image.
Key words: relevance vector machine (RVM), kernel principal component analysis, image classification, feature extraction
CLC Number:
WANG Hui, SONG Shuyun. Image Classification Based on KCPA Feature Extraction and RVM[J].Journal of Jilin University Science Edition, 2017, 55(02): 357-362.
0 / / Recommend
Add to citation manager EndNote|Reference Manager|ProCite|BibTeX|RefWorks
URL: http://xuebao.jlu.edu.cn/lxb/EN/
http://xuebao.jlu.edu.cn/lxb/EN/Y2017/V55/I02/357
Cited