Abstract
Efficient CBIR systems are based on three things, (1) how they represent the repository images in the form of signature; (2) how they measure the similarity of the database images with query image, (3) how they retrieve the semantically similar images in response of a query image. The paper is focusing on these three things. For signature development, curvelet transform, wavelet packets, and Gabor filters based signature development is introduced. For measuring the similarity, Pearson correlation is used as a distance measure; and for retrieving the semantically similar images in response of query images, Neural Network based architecture for content based image retrieval is presented. These things ensure the retrieval of images in a robust way. To elaborate the effectiveness of the presented work, the proposed method is compared with several existing CBIR systems, and it is proved that the proposed method has performed better than all comparative systems.