Short Local Descriptors from 2D Connected Pattern Spectra

Petra Bosilj (1, 2) , Ewa Kijak (2) , Michael H.F. Wilkinson (3) , Sébastien Lefèvre (1)

1 OBELIX - Environment observation with complex imagery
2 LinkMedia - Creating and exploiting explicit links between multimedia fragments
3 Bernoulli Institute for Mathematics and Computer Science and Artificial Intelligence

We propose a local region descriptor based on connected pattern spectra, and combined with normalized central moments. The descriptors are calculated for MSER regions of the image, and their performance compared against SIFT. The MSER regions were chosen because they can be efficiently selected by constructing a max-tree, a structure used to calculate both descriptors and region moments. Experiments on the UCID database show an improvement over SIFT in two out of five experimental setups, and comparable performance in two other experiments. The new descriptors are only half the size of SIFT, resulting in 4 times faster query times when performing exact search on descriptor index built from 262 images.

Mots clés: max-tree; pattern spectra; CBIR; local region descriptors

Domaines: Traitement des images [eess.IV]

Petra Bosilj, Ewa Kijak, Michael H.F. Wilkinson, Sébastien Lefèvre. Short Local Descriptors from 2D Connected Pattern Spectra. IEEE International Conference on Image Processing, 2015, Quebec City, Canada. ⟨hal-01134071⟩