A novel graph-based invariant region descriptor for image matching

Identification of invariant image descriptors is an integral task for many computer vision applications such as image registration, object recognition, and object tracking. The detected features should be invariant to geometric transformations such as rotation and translation, as well photometric variations due to differing lighting conditions. In this work, we propose a unique and effective region descriptor that couples invariant features and texture information. The descriptor relies on spatial relationships of invariant SURF features to create a graph-based descriptor for image matching. Additionally, a novel method is proposed for matching region descriptors through the definition of an efficient similarity measure that couples invariant features and their spatial relationships. Several examples are presented to illustrate the effectiveness of the proposed region descriptor while the results of the proposed approach outperform SURF feature point matching.