Using Spatial Pyramids with Compacted VLAT for Image Categorization

Romain Negrel (1) , David Picard (1) , Philippe-Henri Gosselin (2)

1 ETIS - UMR 8051 - Equipes Traitement de l'Information et Systèmes
2 MIDI - Multimedia Indexation and Data Integration

In this paper, we propose a compact image signa- ture based on VLAT. Our method integrates spatial in- formation while significantly reducing the size of orig- inal VLAT by using two pojection steps. we carry out experiments showing our approach is competitive with state of the art signatures.

Domains: Machine Learning [stat.ML]; Multimedia [cs.MM]

Romain Negrel, David Picard, Philippe-Henri Gosselin. Using Spatial Pyramids with Compacted VLAT for Image Categorization. International Conference on Pattern Recognition, Nov 2012, Tsukuba, Japan. ⟨hal-00753158⟩