The objective of Content-Based Image Retrieval (CBIR) methods is essentially to extract, from large (image) databases, a specified number of images similar in visual and semantic content to a so- called query image. To bridge the semantic gap that exists between the representation of an image by low-level features (namely, colour, shape, texture) and its high-level semantic content as perceived by humans, CBIR systems typically make use of the relevance feedback (RF) mechanism. RF iteratively incorporates user-given inputs regarding the relevance of retrieved images, to improve retrieval efficiency. One approach is to vary the weights of the features dynamically via feature reweighting. In this work, a novel approach has been proposed for improving the retrieval accuracy of CBIR system which incorporates RF based on feature reweighting using discriminant analysis. Results of a number of experiments have been presented to illustrate the significant improvement is retrieval accuracy with the proposed approach.