%0 Journal Article
%T Automatic image annotation based on salient regions<br>基于显著区域的图像自动标注*
%A YIN Wen-jie
%A HAN Jun-wei
%A GUOLei
%A HE Sheng
%A XU Ming
%A <br>尹文杰
%A 韩军伟
%A 郭雷
%A 贺胜
%A 许明
%J 计算机应用研究
%D 2011
%I 
%X In order to improve the performance of automatic image annotation,this paper presented a novel algorithm based on image saliency analysis.Firstly,computed image saliency and obtained the salient objects.Then,the SIFT features were extracted for every image,the visual words were derived through K-Means cluster algorithm,and thus the visual Bag-of-Words model weighted by the saliency information was built to characterize images.Finally,SVM was trained to classify and annotate images automatically.Compared wit...
%K automatic image annotation
%K saliency
%K SIFT feature
%K K-Means cluster
%K bag-of-words
%K SVM<br>图像自动标注
%K 显著区域
%K SIFT特征
%K K-均值聚类
%K 视觉词袋
%K 支持向量机
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=A9D9BE08CDC44144BE8B5685705D3AED&aid=1F8EB868F38CE0726FABEFCF50F0CF4B&yid=9377ED8094509821&vid=D3E34374A0D77D7F&iid=F3090AE9B60B7ED1&sid=FECA0F6D1E05D767&eid=26BD694567433246&journal_id=1001-3695&journal_name=计算机应用研究&referenced_num=0&reference_num=22