针对支持向量机在大规模数据集上的低效率,提出了基于约减支持向量机的相关反馈图像检索算法.首先采用约减支持向量机训练初始分类器,以该分类器作为检索模型,根据检索结果进行相关反馈,从而进行再检索.实验结果表明,随着反馈次数的增加,检索到的相关图像也会增加;另外相对传统的基于向量机的方法,数据集规模越大,基于约减支持向量机的算法在时间上的优势越明显.%Aiming at the inefficiency of support vector machine applied on large data sets, an image retrieval algorithm with relevance feedback based on reduced support vector machine (RSVM) is presented. Firstly, the RSVM is used to train primary classifier, and then such classifier is taken as the retrieval model to make relevance feedback according to the retrieved result followed by further re-retrieval. Experiments show that along with the increase of the feedback times, the relevant images will be increased too. More importantly, in contrast to traditional algorithm based on SVM, the larger the database size is, the more manifest the advantage in time-consuming aspect the algorithm based on RSVM has.
展开▼
