An Adaptive Weight Method for Image Retrieval Based Multi-Feature Fusion

With the rapid development of information storage technology and the spread of the Internet, large capacity image databases that contain different contents in the images are generated. It becomes imperative to establish an automatic and efficient image retrieval system. This paper proposes a novel adaptive weighting method based on entropy theory and relevance feedback. Firstly, we obtain single feature trust by relevance feedback (supervised) or entropy (unsupervised). Then, we construct a transfer matrix based on trust. Finally, based on the transfer matrix, we get the weight of single feature through several iterations. It has three outstanding advantages: (1) The retrieval system combines the performance of multiple features and has better retrieval accuracy and generalization ability than single feature retrieval system; (2) In each query, the weight of a single feature is updated dynamically with the query image, which makes the retrieval system make full use of the performance of several single features; (3) The method can be applied in two cases: supervised and unsupervised. The experimental results show that our method significantly outperforms the previous approaches. The top 20 retrieval accuracy is 97.09%, 92.85%, and 94.42% on the dataset of Wang, UC Merced Land Use, and RSSCN7, respectively. The Mean Average Precision is 88.45% on the dataset of Holidays.

Abstract licence: CC BY

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.