Complicated scene retrieval using block voting mechanism and weak feature selection based on bag-of-features

Bingrong Wang*, Lei Sun, Jia Su, Takeshi Ikenaga

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In this paper, we focus on the problem of complicated scene retrieval and give two proposals to improve accuracy of the recent image search system based on bag-of-features: block voting mechanism and weak feature selection. Both the methods aim to reduce effects of incorrect matching between descriptors. Block voting mechanism separates query and database images into blocks when computing image matching scores. It can be integrated into inverted file for an efficient and compact indexing structure. Weak feature selection provides a simple approach to select good feature points for matching. Experiments performed on a dataset with complicated scene and various transformations including viewpoint and illumination changes show an about 20 percent improvement rather than baseline bag-of-features due to my proposals.

Original languageEnglish
Title of host publicationNISS2010 - 4th International Conference on New Trends in Information Science and Service Science
Pages287-292
Number of pages6
Publication statusPublished - 2010 Oct 15
Event4th International Conference on New Trends in Information Science and Service Science, NISS2010 - Gyeongju, Korea, Republic of
Duration: 2010 May 112010 May 13

Publication series

NameNISS2010 - 4th International Conference on New Trends in Information Science and Service Science

Conference

Conference4th International Conference on New Trends in Information Science and Service Science, NISS2010
Country/TerritoryKorea, Republic of
CityGyeongju
Period10/5/1110/5/13

Keywords

  • Bag-of-features
  • Cotent-based image retrieval
  • Feature selection
  • Inverted file
  • Voting system

ASJC Scopus subject areas

  • Information Systems and Management

Fingerprint

Dive into the research topics of 'Complicated scene retrieval using block voting mechanism and weak feature selection based on bag-of-features'. Together they form a unique fingerprint.

Cite this