PT Unknown
AU Jose Carlos Rubio
   Joan Serrat
   Antonio Lopez
   N. Paragios
TI Image Contextual Representation and Matching through Hierarchies and Higher Order Graphs
BT 21st International Conference on Pattern Recognition
PY 2012
BP 2664
EP 2667
AB We present a region matching algorithm which establishes correspondences between regions from two segmented images. An abstract graph-based representation conceals the image in a hierarchical graph, exploiting the scene properties at two levels. First, the similarity and spatial consistency of the image semantic objects is encoded in a graph of commute times. Second, the cluttered regions of the semantic objects are represented with a shape descriptor. Many-to-many matching of regions is specially challenging due to the instability of the segmentation under slight image changes, and we explicitly handle it through high order potentials. We demonstrate the matching approach applied to images of world famous buildings, captured under different conditions, showing the robustness of our method to large variations in illumination and viewpoint.
ER