Résumé | We presents a nouvel approach to addresses the well-known problem of
adding spatial information to the standard bag-of-visual-words (BoVW)
model.
To that end, a set of graphs descriptors are constructed for the
entire image or for local image regions via graph-cuts based methods.
These descriptors are then incorporated into a bag-of-visual-words
approach, leading to a method called bag-of-bag-of-visual-words (BBoVW).
In experimental results for Caltech101 benchmark, our proposed method
performs better than SPM(Spatial Pyramid Matching) for 19 objects
categories. |