Title: Relevance feedback techniques and genetic algorithm for image retrieval based on multiple features

Authors: Qi-ming Fu; Quan Liu; Xiao-yan Wang; Le Zhang

Addresses: Institute of Computer Science and Technology, Soochow University, Suzhou 215006, China. ' Institute of Computer Science and Technology, Soochow University, Suzhou 215006, China. ' Institute of Computer Science and Technology, Soochow University, Suzhou 215006, China. ' Institute of Computer Science and Technology, Soochow University, Suzhou 215006, China

Abstract: Content-based image retrieval (CBIR) is a new information retrieval technology along with development of the digital multimedia technology. In allusion to the problem of inaccurate description, low query precision and high frequency of feedback, the paper puts forward a new retrieval method of relevance feedback techniques and genetic algorithm for image retrieval based on multiple features, which can avoid causing the problem of different images with the same single feature. Compared with the existing methods, the method can automatically adjust the image feature weights, has higher query precision and lower frequency of feedback. The experiments show that the method has strong robustness to rotation, translation and scale change, has the performance of higher query precision and lower frequency of feedback simultaneously.

Keywords: content based image retrieval; CBIR; genetic algorithms; relevance feedback; image representation; information retrieval; multimedia; image features.

DOI: 10.1504/IJMIC.2011.043151

International Journal of Modelling, Identification and Control, 2011 Vol.14 No.4, pp.279 - 285

Published online: 21 Mar 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article