Extracting Categories By Hierarchical Clustering Using Global Relational Features

Research output: Chapter in Book/Report/Conference proceedingArticle in proceedingsResearchpeer-review

Abstract

We introduce an object categorization system which uses hierarchical clustering to extract categories. The system is able to assign multiple, nested categories for unseen objects. In our system, objects are represented with global pair-wise relations computed from 3D features extracted by three RGB-D sensors. We show that our system outperforms a state-of-the-art approach particularly when only a few number of training samples is used.

Original languageEnglish
Title of host publicationPattern Recognition and Image Analysis : 7th Iberian Conference, IbPRIA 2015, Santiago de Compostela, Spain, June 17-19, 2015, Proceedings
EditorsRoberto Paredes, Jaime S. Cardoso, Xosé M. Pardo
PublisherSpringer
Publication date2015
Pages541-551
ISBN (Print)978-3-319-19389-2
ISBN (Electronic)978-3-319-19390-8
DOIs
Publication statusPublished - 2015
Event7th Iberian Conference on Pattern Recognition and Image Analysis - Santiago de Compostela, Spain
Duration: 17. Jul 201519. Jul 2015

Conference

Conference7th Iberian Conference on Pattern Recognition and Image Analysis
Country/TerritorySpain
CitySantiago de Compostela
Period17/07/201519/07/2015
SeriesLecture Notes in Computer Science
Volume9117
ISSN0302-9743

Fingerprint

Dive into the research topics of 'Extracting Categories By Hierarchical Clustering Using Global Relational Features'. Together they form a unique fingerprint.

Cite this