An efficient and effective image representation for region-based image retrieval

  • Authors:
  • ZhiYong Zeng;ZhiQiang Yao;ShiGang Liu

  • Affiliations:
  • Fujian Normal University, Minhou Section, Fuzhou, China;Fujian Normal University, Minhou Section, Fuzhou, China;Xi'an Jiaotong University, Xi'an, China

  • Venue:
  • Proceedings of the 2nd International Conference on Interaction Sciences: Information Technology, Culture and Human
  • Year:
  • 2009

Quantified Score

Hi-index 0.00

Visualization

Abstract

This paper present an efficient and effective image representation for region-based image retrieval. We explore the issue of hybrid feature-integrated and compact region-based image retrieval for huge image database. Firstly, to describe regions of an image, we present an image segmentation algorithm. Secondly, a compact, fixed-number and computation effective representaton is designed for the color contents of each region of an image, which can be computed from color space without quantizing color space to construct color histogram. Finally, we use the hybrid feature including color, texture and shape as feature vector of the regions to match images, experimental results on a database of 1000 general-purposed images demonstrate the efficiency and effectiveness of the proposed image representation for region-based image retrieval.