Spatial graphlet matching kernel for recognizing aerial image categories

• Published in: Proceedings of the 21st International Conference on Pattern Recognition (ICPR2012) pp. 2813 - 2816
• Main Authors: Luming Zhang, Mingli Song, Li Sun, Xiao Liu, Yinting Wang, Dacheng Tao, Jiajun Bu, Chun Chen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.11.2012
• Subjects: Image recognition; Image segmentation; Kernel; Manifolds; Support vector machines; Training; Vectors
• ISBN: 9781467322164; 1467322164
• ISSN: 1051-4651; 2831-7475

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.