Spatial graphlet matching kernel for recognizing aerial image categories

This paper presents a method for recognizing aerial image categories based on matching graphlets(i.e., small connected subgraphs) extracted from aerial images. By constructing a Region Adjacency Graph (RAG) to encode the geometric property and the color distribution of each aerial image, we cast aerial image category recognition as RAG-to-RAG matching. Based on graph theory, RAG-to-RAG matching is conducted by matching all their respective graphlets. Towards an effective graphlet matching process, we develop a manifold embedding algorithm to transfer different-sized graphlets into equal length feature vectors and further integrate these feature vectors into a kernel. This kernel is used to train a SVM [8] classifier for aerial image categories recognition. Experimental results demonstrate our method outperforms several state-of-the-art object/scene recognition models.