Distributing Relevance Feedback in Content Based Image Retrieval Systems

Abstract

Most Content Based Image Retrieval (CBIR) systems use low level features such as texture, color and shape to formulate the query. Relevance feedback (RF) from the environment has also been used as a means of training CBIR systems and improving the performance of feature based query schemes. Query schemes based on feature extraction methods generally make recognition errors of different types, and hence a scheme that would exploit this “error independence” among these schemes could be used to improve the performance of a combined system using these features. We propose a scheme for combining results from a number of low level feature based image classifiers based on the relative relevance of the features and distributing RF from the environment to each of the low level classiers to improve their performance.