基于区域语义子概念分布的场景分类

Scene Classification Method Based on the Feature Fusion of Regional Semantic Sub-concept Occurrence

大量的需求使得图像检索成为当前研究的热点。提出了对图像进行均匀分割、识别区域子概念并在此基础上对概念分布向量进行融合的场景分类方法。实验结果表明,这种方法提高了分类结果的P/R值,获得了很好的分类结果。

A large quantity of practical demand has made image retrieval a research focus.We proposed a scene classification method based on the fusion of concept occurrence vectors,which are gained by segmenting images uniformly and recognizing corresponding regional sub concepts.Experiments show that our method increases the P/R values of scene classification,bringing a better result.