Boosting content based image retrieval performance through integration of parametric & nonparametric approaches

•Hybrid CBIR method is proposed by fusing parametric and nonparametric features.•Different similarity metrics are investigated to retrieve more relevant images.•The proposed model is compared with seven existing methods over five datasets.•Hypothesis test is carried out to establish the significance of the proposed work.•Hypothesis test infers the obtained metrics are true and accepted for all datasets. The collection of digital images is growing at ever-increasing rate which rises the interest of mining the embedded information. The appropriate representation of an image is inconceivable by a single feature. Thus, the research addresses that point for content based image retrieval (CBIR) by fusing parametric color and shape features with nonparametric texture feature. The color moments, and moment invariants which are parametric methods and applied to describe color distribution and shapes of an image. The nonparametric ranklet transformation is performed to narrate the texture features. Experimentally these parametric and nonparametric features are integrated to propose a robust and effective algorithm. The proposed work is compared with seven existing techniques by determining statistical metrics across five image databases. Finally, a hypothesis test is carried out to establish the significance of the proposed work which, infers evaluated precision and recall values are true and accepted for the all image database.