SAR image retrieval based on Gaussian Mixture Model classification
Biao Hou, Xu Tang, Licheng Jiao, Shuang Wang · 2009
SAR image retrieval, lacking of well performance recently due to the particularity of SAR image, has drawn more and more attention with the increasing volume of SAR data and the dramatically enlarging application range of SAR image. This paper considers both the characteristic of content-based image retrieval (CBIR) and SAR image, proposing a novel SAR image retrieval method. The proposed method can be divided into two parts: image classification and matching. Firstly we use Gaussian Mixture Model (GMM) to gain a precise result of classification, and then we get the retrieval results through the integrated region matching (IRM) algorithm. Experimental results show that the proposed method can retrieve SAR images which contain all kinds of surface features effectively.