Vector Quantizing Feature Space with a Regular Lattice

9 years 7 months ago
Vector Quantizing Feature Space with a Regular Lattice
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent approach to construct such a visual vocabulary, where the feature space is discretized using a regular lattice. Using hashing techniques, only non-empty bins are stored, and fine-grained grids become possible in spite of the high dimensionality of typical feature spaces. Based on this representation, we can explore the structure of the feature space, and obtain state-of-the-art pixelwise classification results. In the case of image classification, we introduce a class-specific feature selection step, which takes the spatial structure of SIFT-like descriptors into account. Results are reported on the Graz02 dataset.
Tinne Tuytelaars, Cordelia Schmid
Added 14 Oct 2009
Updated 14 Oct 2009
Type Conference
Year 2007
Where ICCV
Authors Tinne Tuytelaars, Cordelia Schmid
Comments (0)