Histogram pyramid representations computed from a vocabulary tree of visual words have proven valuable for a range of image indexing and recogniton tasks; however, they have only used a single, fixed partition of feature space. We present a new efficient algorithm to incrementally compute set-of-trees (forest) vocabulary representatons, and show that they improve recognition and indexing performance in methods which use histogram pyramids. Our algorithm incrementally adapts a vocabulary forest with an inverted filesystem at the leaf nodes and automatically keeps existing histogram pyramid database entries up-to-date in a forward filesystem. It is possible not only to apply vocabulary tree indexing algorithms directly, but also to compute pyramid match kernel values efficiently. On dynamic recognition tasks where cateories or objects under consideration may change over time, we show that adaptive vocabularies offer significant performance advantages in comparison to a single, fixed vocabulary.
|Published - 2007
|2007 IEEE 11th International Conference on Computer Vision, ICCV - Rio de Janeiro, Brazil
Duration: 14 Oct 2007 → 21 Oct 2007
|2007 IEEE 11th International Conference on Computer Vision, ICCV
|Rio de Janeiro
|14/10/07 → 21/10/07