Design and Implementation of a Texture Image Retrieval System Based on Curvelets
Niu Zhen-shan · Computer Engineering and Science · 2011
In order to manage and query massive images,there is an urgent need for a content-based image retrieval system with high retrieval rates.This paper proposes an image retrieval method based on curvelet transform and integrated Shannon entropy and frequency sub-band energy features.This method uses the Shannon entropy to pre-classify data,adopts the energy sub-band features to measure image similarity,and joins the feedback information of searchers to achieve accurate image retrieval.The retrieval experimental results conducted on the Brodatz texture image database show that the system has a high retrieval rate and a certain practical value.