Navigation-pattern based relevance feedback for high efficient content-based image retrieval

This paper studies about the research on ways to extend and improve query methods for image databases is widespread, we have developed the QBIC (Query by Image Content) system to explore content-based retrieval methods. To achieve the high efficiency and effectiveness of CBIR we are using two type of methods for feature extraction like SVM(support vector machine)and NPRF(navigation-pattern based relevance feedback). By using svm classifier as a category predictor of query and database images, they are exploited at first to filter out irrelevant images by its different low-level, concept and key point-based features. Thus we may reduce the size of query search in the db then we may apply NPRF algorithm and refinement strategies for further extraction then we may combine the color and the texture of the given query image to Obtain optimal solution.