On the spatial extents of SIFT descriptors for visual concept detection

  • Authors:

  • Markus Mühling;Ralph Ewerth;Bernd Freisleben

  • Affiliations:

  • Department of Mathematics & Computer Science, University of Marburg, Marburg, Germany;Department of Mathematics & Computer Science, University of Marburg, Marburg, Germany;Department of Mathematics & Computer Science, University of Marburg, Marburg, Germany

  • Venue:
  • ICVS'11 Proceedings of the 8th international conference on Computer vision systems
  • Year:
  • 2011

Quantified Score

Hi-index 0.00

Visualization

Abstract

State-of-the-art systems for visual concept detection typically rely on the Bag-of-Visual-Words representation. While several aspects of this representation have been investigated, such as keypoint sampling strategy, vocabulary size, projection method, weighting scheme or the integration of color, the impact of the spatial extents of local SIFT descriptors has not been studied in previous work. In this paper, the effect of different spatial extents in a state-of-the-art system for visual concept detection is investigated. Based on the observation that SIFT descriptors with different spatial extents yield large performance differences, we propose a concept detection system that combines feature representations for different spatial extents using multiple kernel learning. It is shown experimentally on a large set of 101 concepts from the Mediamill Challenge and on the PASCAL Visual Object Classes Challenge that these feature representations are complementary: Superior performance can be achieved on both test sets using the proposed system.