Graph of Concepts for Semantic Annotation of Remotely Sensed Images based on Direct Neighbors in RAG

Image annotation is a challenging task and is widely studied in several fields such as image interpretation and retrieval. With the overwhelming volume of image data, manual annotation is no longer practical. Therefore, automatic image annotation (AIA) techniques have become a necessity where various approaches have been proposed mainly to resolve the semantic gap problem. Nevertheless, further efforts are still required in order to obtain more faithful semantic image annotations. In this paper, we propose a method to semantically annotate remote sensing (RS) images based on region adjacency graphs (RAG). Specifically, we simultaneously consider contextual, spatial and spectral information of image regions for AIA. Spectral libraries are used as a source of knowledge where several radiometric indices are computed to identify objects in the images. As a result, a graph of concepts representing objects is produced in scenes that exploit spatial and spectral attributes. Our approach is validated based on popular RS image datasets such as the Indian Pines and Jasper Ridge datasets. Promising results are reported based on the measurements of precision, recall, F1 and N + scores.