Loading [MathJax]/extensions/MathZoom.js
Color image retrieval based on the hypergraph and the fusion of two descriptors | IEEE Conference Publication | IEEE Xplore

Color image retrieval based on the hypergraph and the fusion of two descriptors


Abstract:

Recent years, the efficiency and accuracy of content based on image retrieval (CBIR) are two research directions. In order to improve retrieval precision, firstly, we use...Show More

Abstract:

Recent years, the efficiency and accuracy of content based on image retrieval (CBIR) are two research directions. In order to improve retrieval precision, firstly, we use a fusion framework, combined with Color Difference Histogram (CDH) and Micro-structure Descriptor (MSD) which are two kinds of image descriptors to calculate distances between all images and transform the distances between images into similarities. Then we utilize the similarities to construct a similarity matrix. Secondly, by using the similarity matrix, we construct a hypergraph, the hypergraph combined with relevance feedback technique is exploited to rank images and get similar images. Extensive experiments are carried out on the Corel-5K dataset and get a very good performance.
Date of Conference: 14-16 October 2017
Date Added to IEEE Xplore: 26 February 2018
ISBN Information:
Conference Location: Shanghai, China

Contact IEEE to Subscribe

References

References is not available for this document.