Image retrieval based on semantics

Yong Sheng Bao, Jian Feng Ren, Lei Guo

Research output: Contribution to journalArticlepeer-review

Abstract

How to narrow the gap between low level features and high level features is still a challenging problem in computer vision field. The word-net is used to solve this problem in terms of image retrieval. Firstly, dominant colors from the images are extracted. Then the links between the dominant colors and image content using the word-net are established. And in the semantics based image retrieval system, relevance feedback is used to improve the retrieval accuracy. Experimental results show that the algorithm can be applied to the large amount of images and the high accuracy is obtained.

Original languageEnglish
Pages (from-to)75-78
Number of pages4
JournalNanjing Hangkong Hangtian Daxue Xuebao/Journal of Nanjing University of Aeronautics and Astronautics
Volume37
Issue number1
StatePublished - Feb 2005

Keywords

  • Dominant color
  • Image retrieval
  • Relevance feedback
  • Word-net

Fingerprint

Dive into the research topics of 'Image retrieval based on semantics'. Together they form a unique fingerprint.

Cite this