摘要
针对语义鸿沟问题,将基于语义特征挖掘模型与支持向量机相关反馈方法相结合,建立了基于支持向量机相关反馈的人机交互遥感影像语义检索系统。实验结果表明,该方法利用高层语义特征及人机交互反馈信息缩小了语义鸿沟,提高了影像检索的精度。
The semantic gap between high-level human perception and low-level image fea- tures becomes the bottleneck in content-based remotely sensed image retrieval technology. To solve this problem, in this research, a human machine interaction （HMI） remotely sensed image retrieval system is built that combines semantic mining model and SVM-based relevance feedback method. The experiments indicate that this method can well narrow se- mantic gap and improve retrieval precision and recall.
出处
《武汉大学学报（信息科学版）》
EI
CSCD
北大核心
2012年第4期415-418,共4页
Geomatics and Information Science of Wuhan University
基金
国家海洋局极地专项“测绘遥感技术在极地环境考察与评估中的应用”资助项目(JDZX20110008)
武汉大学青年教师资助项目(3101004)
关键词
影像检索
语义挖掘模型
相关反馈
SVM
image retrieval
semantic mining model~ relevance feedback
SVM
