Title :
Using spatial pyramids with compacted VLAT for image categorization
Author :
Negrel, Romain ; Picard, David ; Gosselin, Philippe-Henri
Author_Institution :
ETIS, Univ. of Cergy-Pontoise, Cergy-Pontoise, France
Abstract :
In this paper, we propose a compact image signature based on VLAT. Our method integrates spatial information while significantly reducing the size of original VLAT by using two projection steps. we carry out experiments showing our approach is competitive with state of the art signatures.
Keywords :
feature extraction; image classification; learning (artificial intelligence); tensors; classifier learning; compact image signature; compacted VLAT; content based image categorization; descriptors aggregation; local image descriptor extraction; projection steps; spatial pyramids; vector-of-locally aggregated tensors; Approximation methods; Encoding; Kernel; Tensile stress; Training; Vectors; Visualization;
Conference_Titel :
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location :
Tsukuba
Print_ISBN :
978-1-4673-2216-4
