Tensor Decomposition of Dense SIFT Descriptors in Object Recognition

Tan Vo, Dat TRAN, Wanli MA

Research output: A Conference proceeding or a Chapter in BookConference contributionpeer-review

1 Citation (Scopus)

Abstract

In machine vision, Scale-invariant feature transform (SIFT) and its variants have been widely used in image classification task. However, the high dimensionality nature of SIFT features, usually in the order of multiple thousands per image, would require careful consideration in place to achieve accurate and timely categorization of objects within images. This paper explores the possibility of processing SIFT features as tensors and uses tensor decomposition techniques on high-order SIFT tensors for dimensionality reduction. The method focuses on both accuracy and efficiency aspects and the validation result with the Caltech 101 dataset confirms the improvement with notable margins.

Original languageEnglish
Title of host publicationESANN 2014 European Symposium of Artificial Neural Networks, Computational Intelligence and Machine Learning
EditorsMichel Verleysen
Place of PublicationBruges, Belgium
PublisherEuropean Symposium of Artificial Neural Networks
Pages319-324
Number of pages6
Volume1
ISBN (Print)9782874190957
Publication statusPublished - 23 Apr 2014
EventEuropean Symposium on Artificial Neural Networks 2014: ESANN 2014 - Brugge, Brugge, Belgium
Duration: 23 Apr 201425 Apr 2014

Publication series

Name22nd European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2014 - Proceedings

Conference

ConferenceEuropean Symposium on Artificial Neural Networks 2014
Abbreviated titleESANN 2014
Country/TerritoryBelgium
CityBrugge
Period23/04/1425/04/14

Fingerprint

Dive into the research topics of 'Tensor Decomposition of Dense SIFT Descriptors in Object Recognition'. Together they form a unique fingerprint.

Cite this