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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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.

Original languageEnglish
Title of host publicationICMR 2013 - Proceedings of the 3rd ACM International Conference on Multimedia Retrieval
PublisherAssociation for Computing Machinery
Pages199-206
Number of pages8
ISBN (Print)9781450320337
DOIs
StatePublished - 16 Apr 2013
Event3rd ACM International Conference on Multimedia Retrieval, ICMR 2013 - Dallas, TX, United States
Duration: 16 Apr 201320 Apr 2013

Publication series

NameICMR 2013 - Proceedings of the 3rd ACM International Conference on Multimedia Retrieval

Conference

Conference3rd ACM International Conference on Multimedia Retrieval, ICMR 2013
Country/TerritoryUnited States
CityDallas, TX
Period16/04/1320/04/13

Keywords

  • feature extraction
  • local descriptor
  • object categorization

Fingerprint

Dive into the research topics of 'HSOG: A novel local descriptor based on histograms of second order gradients for object categorization'. Together they form a unique fingerprint.

Cite this