Image Retrieval based on HSV Feature and Regional Shannon Entropy

  • Authors:
  • Jun Peng;Liang Lei;Bo Yang

  • Affiliations:
  • Chongqing University of Science and Technology, China;Chongqing University of Science and Technology, China;Chongqing University of Science and Technology, China

  • Venue:
  • International Journal of Software Science and Computational Intelligence
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

How to quickly retrieve the image is a very action research topic in the research of image retrieval based on Web. This paper focuses on dimensionality reduction and similarity measure of Web image. First, the paper presents the current commercial search engines how to look for Web images. Then, it describes commonly used methods of the dimension reduction for Web images, followed by proposing the conversion from RGB to HSV and dominant color extraction algorithm based on HSV features, where the HSV color histogram intersection was used as the function of similarity judgments. And the similarity measure based on regional Shannon entropy is discussed. Finally, some improvements are made on computing the regional Shannon mutual information. The experiments and results, which based on FERET database, MIT face database and Corel database, showed that this method has greatly improved the image retrieval in time and precision rates.