计算机应用研究2016，Vol.33Issue(12)：3836-3838,3846,4.DOI:10.3969/j.issn.1001-3695.2016.12.070
一种基于SVM和主动学习的图像检索方法
Image retrieval method based on SVM and active learning
摘要
Abstract
In order to improve the speed and accuracy of image retrieval,this paper proposed an image retrieval method based on SVM and active learning.It involved two stages.Fristly,it utilized K-means clustering algorithm to find representative sam-ples from the image database,which may effectively reduce the search range.Secondly,it used a comprehensive evaluation to the unlabeled samples by the distance of the samples with the classification of the border and its neighbor density,then selected the most valuable samples as training samples,which might the classifier achieve higher accuracy by a small number of feed-back times.Experimental results show that the algorithm can greatly improve the performance of the image retrieval.关键词
图像检索/SVM/主动学习/K-means/代表性样本/关键性样本Key words
image retrieval/SVM/active learning/K-means/representative samples/key samples分类
信息技术与安全科学引用本文复制引用
王新建,罗光春,秦科,陈爱国,赖云一..一种基于SVM和主动学习的图像检索方法[J].计算机应用研究,2016,33(12):3836-3838,3846,4.基金项目
四川省科技厅资助项目（2012GZ0088，2013JQ0005）；中央高校基本科研业务费资助项目 （）
