Color image retrieval using statistical model and radial basis function neural network

This paper proposes a new and effective framework for color image retrieval based on Full Range Autoregressive Model (FRAR). Bayesian approach (BA) is used to estimate the parameters of the FRAR model. The color autocorrelogram, a new version of edge histogram descriptor (EHD) and micro-texture (MT) features are extracted using a common framework based on the FRAR model with BA. The extracted features are combined to form a feature vector, which is normalized and stored in image feature vector database. The feature vector database is categorized according to the nature of the images using the radial basis function neural network (RBFNN) and k-means clustering algorithm. The proposed system adopted Manhattan distance measure of order one to measure the similarity between the query and target images in the categorized and indexed feature vector database. The query refinement approach of short-term learning based relevance feedback mechanism is adopted to reduce the semantic gap. The experimental results, based on precision and recall method are reported. It demonstrates the performance of the improved EHD, effectiveness and efficiency achieved by the proposed framework.