SIFT features in multiple color spaces for improved image classification

Abhishek Verma, Chengjun Liu

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Scopus citations

Abstract

This chapter first discusses oRGB-SIFT descriptor, and then integrates it with other color SIFT features to produce the Color SIFT Fusion (CSF), the Color Grayscale SIFT Fusion (CGSF), and the CGSF+PHOG descriptors for image classification with special applications to image search and video retrieval. Classification is implemented using the EFM-NN classifier, which combines the Enhanced Fisher Model (EFM) and the Nearest Neighbor (NN) decision rule. The effectiveness of the proposed descriptors and classification method is evaluated using two large scale and challenging datasets: the Caltech 256 database and the UPOL Iris database. The experimental results show that (i) the proposed oRGB-SIFT descriptor improves recognition performance upon other color SIFT descriptors; and (ii) the CSF, the CGSF, and the CGSF+PHOG descriptors perform better than the other color SIFT descriptors.

Original languageEnglish (US)
Title of host publicationIntelligent Systems Reference Library
PublisherSpringer Science and Business Media Deutschland GmbH
Pages145-166
Number of pages22
DOIs
StatePublished - 2017

Publication series

NameIntelligent Systems Reference Library
Volume121
ISSN (Print)1868-4394
ISSN (Electronic)1868-4408

All Science Journal Classification (ASJC) codes

  • Computer Science(all)
  • Information Systems and Management
  • Library and Information Sciences

Fingerprint Dive into the research topics of 'SIFT features in multiple color spaces for improved image classification'. Together they form a unique fingerprint.

Cite this