Content-Based Image Retrieval Based on Relevance Feedback and Reinforcement Learning for Medical Images

Abstract

To enable a relevance feedback paradigm to evolve itself by users’ feedback, a reinforcement learning method is proposed. The feature space of the medical images is partitioned into positive and negative hypercubes by the system. Each hypercube constitutes an individual in a genetic algorithm infrastructure. The rules take recombination and mutation operators to make new rules for better exploring the feature space. The effectiveness of the rules is checked by a scoring method by which the ineffective rules will be omitted gradually and the effective ones survive. Our experiments on a set of 10,004 images from the IRMA database show that the proposed approach can better describe the semantic content of images for image retrieval with respect to other existing approaches in the literature.

Content-Based Image Retrieval System with Combining Color features and Gradient feature

“…Roberts's operator (16) Variance and standard deviation are measurements for measuring spread of data and both of them are purely 1dimensional .You can only calculate the standard deviation or variance for each dimension of the data set independently from the other dimension. However, it is useful to have a similar measure to find out how much the dimensions vary from the mean with respect to each other.…”

Automatic medical image annotation and keyword-based image retrieval using relevance feedback

“…Lakdashti and Ajorloo [15] proposed a relevance feedback retrieval system based on interactive genetic algorithm to reduce the semantic gap of the present medical image retrieval systems. This system learns the user's semantics using relevance feedback and stores them in system's rules using n-dimensional hypercubes.…”

“…In relevance feedback mechanism, the user only needs to mark which images he or she thinks are relevant to execute the query. By the user's feedback action, weights for similarity [2,7] or parameters for learning methods [8][9][10][11][12][13][14][15] are readjusted.…”