跳到主要导航 跳到搜索 跳到主要内容

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

  • LIRIS UMR5205

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

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.

源语言英语
主期刊名ICMR 2013 - Proceedings of the 3rd ACM International Conference on Multimedia Retrieval
出版商Association for Computing Machinery
199-206
页数8
ISBN(印刷版)9781450320337
DOI
出版状态已出版 - 16 4月 2013
活动3rd ACM International Conference on Multimedia Retrieval, ICMR 2013 - Dallas, TX, 美国
期限: 16 4月 201320 4月 2013

出版系列

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

会议

会议3rd ACM International Conference on Multimedia Retrieval, ICMR 2013
国家/地区美国
Dallas, TX
时期16/04/1320/04/13

学术指纹

探究 'HSOG: A novel local descriptor based on histograms of second order gradients for object categorization' 的科研主题。它们共同构成独一无二的学术指纹。

引用此