Semi-supervised Hierarchical Clustering for Semantic SAR Image Annotation

In this paper, we propose a semi-automated hierarchical clustering and classification framework for synthetic aperture radar (SAR) image annotation. Our implementation of the framework allows the classification and annotation of image data ranging from scenes up to large satellite data archives. Our framework comprises three stages: 1) each image is cut into patches and each patch is transformed into a texture feature vector; 2) similar feature vectors are grouped into clusters, where the number of clusters is determined by repeated cluster splitting to optimize their Gaussianity; and 3) the most appropriate class (i.e., a semantic label) is assigned to each image patch. This is accomplished by semi-supervised learning. For the testing and validation of our implemented framework, a concept for a two-level hierarchical semantic image content annotation was designed and applied to a manually annotated reference dataset consisting of various TerraSAR-X image patches with meter-scale resolution. Here, the upper level contains general classes, while the lower level provides more detailed subclasses for each parent class. For a quantitative and visual evaluation of the proposed framework, we compared the relationships among the clustering results, the semi-supervised classification results, and the two-level annotations. It turned out that our proposed method is able to obtain reliable results for the upper-level (i.e., general class) semantic classes; however, due to the too many detailed subclasses versus the few instances of each subclass, the proposed method generates inferior results for the lower level. The most important contributions of this paper are the integration of modified Gaussian-means and modified cluster-then-label algorithms, for the purpose of large-scale SAR image annotation, as well as the measurement of the clustering and classification performances of various distance metrics.