HSOG: a novel local descriptor based on histograms of second order gradients for object categorization

  • Authors:
  • Di Huang;Chao Zhu;Charles-Edmond Bichot;Yunhong Wang;Liming Chen

  • Affiliations:
  • Beihang University, Beijing, China;Ecole Centrale de Lyon, Lyon, France;Ecole Centrale de Lyon, Lyon, France;Beihang University, Beijing, China;Ecole Centrale de Lyon, Lyon, France

  • Venue:
  • Proceedings of the 3rd ACM conference on International conference on multimedia retrieval
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper presents a novel local image descriptor for object categorization that extracts the Histograms of the Second Order Gradients and is thereby named as HSOG. The HSOG descriptor is in contrast to the widely used ones in the literature, e.g. SIFT, DAISY, HOG, LBP, etc., which are based on the first order gradient information. The contributions of this work can be summarized as: (1) the design of HSOG; (2) the prove of its discriminative power and its complementation to the first order gradient based descriptors; (3) the analysis of performance variation caused by different parameter settings; and (4) the multi-scale extension which further improves the categorization accuracy. The experimental results achieved on the Caltech 101 and Caltech 256 databases clearly highlight the effectiveness of the proposed approach.